From a4f22b95b779dfb4bfe0e2e33e20754639670266 Mon Sep 17 00:00:00 2001 From: knoflook Date: Thu, 3 Feb 2022 15:57:01 +0100 Subject: [PATCH 01/48] feed: truncate file name if too long --- lumbunglib/feed.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 93ae387..5b4ccb1 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -1,6 +1,7 @@ import os import shutil import time +from hashlib import md5 from ast import literal_eval as make_tuple from pathlib import Path from urllib.parse import urlparse @@ -238,6 +239,13 @@ def main(): entry["feed_name"] = feed_name post_name = slugify(entry.title) + # pixelfed returns the whole post text as the post name. max + # filename length is 255 on many systems. here we're shortening + # the name and adding a hash to it to avoid a conflict in a + # situation where 2 posts start with exactly the same text. + if len(post_name) > 150: + post_hash = md5(bytes(post_name, "utf-8")) + post_name = post_name[:150] + "-" + post_hash.hexdigest() post_dir = os.path.join(output_dir, feed_name, post_name) if post_name not in existing_posts: -- 2.49.0 From 77b8c9e0af2c2fd8f28b9c496450b9e776fdb0f8 Mon Sep 17 00:00:00 2001 From: knoflook Date: Thu, 3 Feb 2022 16:09:05 +0100 Subject: [PATCH 02/48] video: use video title for filename --- lumbunglib/video.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/lumbunglib/video.py b/lumbunglib/video.py index 4194467..327c4e7 100644 --- a/lumbunglib/video.py +++ b/lumbunglib/video.py @@ -97,6 +97,11 @@ def update_post(post_directory, video_metadata, host): # compat for when there is no timestamp yet.. create_post(post_directory, video_metadata, host) +def sanitize_name(name): + sanitized = "".join([c if c.isalnum() or c == " " else "-" for c in name]) + if len(sanitized) > 40: + return sanitized[:40] + return sanitized def main(): v = peertube.VideoApi(client) @@ -114,7 +119,7 @@ def main(): existing_posts = os.listdir(output_dir) for video_metadata in videos: - post_dir = os.path.join(output_dir, video_metadata["uuid"]) + post_dir = os.path.join(output_dir, sanitize_name(video_metadata["name"]) + "-" + video_metadata["uuid"]) if ( video_metadata["uuid"] not in existing_posts -- 2.49.0 From 5366ef3abe7eafe67c4e7251d8b245a9726d562f Mon Sep 17 00:00:00 2001 From: knoflook Date: Fri, 4 Feb 2022 11:57:46 +0100 Subject: [PATCH 03/48] hash: add new hashtag --- lumbunglib/hashtag.py | 1 + 1 file changed, 1 insertion(+) diff --git a/lumbunglib/hashtag.py b/lumbunglib/hashtag.py index c159c07..6cdd3e6 100644 --- a/lumbunglib/hashtag.py +++ b/lumbunglib/hashtag.py @@ -17,6 +17,7 @@ hashtags = [ "majelisakakbar", "majelisakbar", "warungkopi", + "lumbungkios", ] -- 2.49.0 From 58024c775a4a1c6e11c5d74a2020f50b78b8e8ca Mon Sep 17 00:00:00 2001 From: knoflook Date: Mon, 7 Feb 2022 11:45:00 +0100 Subject: [PATCH 04/48] vid: fix post deletion logic --- lumbunglib/video.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/lumbunglib/video.py b/lumbunglib/video.py index 327c4e7..2945286 100644 --- a/lumbunglib/video.py +++ b/lumbunglib/video.py @@ -119,10 +119,11 @@ def main(): existing_posts = os.listdir(output_dir) for video_metadata in videos: - post_dir = os.path.join(output_dir, sanitize_name(video_metadata["name"]) + "-" + video_metadata["uuid"]) + post_name = sanitize_name(video_metadata["name"]) + "-" + video_metadata["uuid"] + post_dir = os.path.join(output_dir, post_name) if ( - video_metadata["uuid"] not in existing_posts + post_name not in existing_posts ): # if there is a video we dont already have, make it print( "New: ", video_metadata["name"], "({})".format(video_metadata["uuid"]) @@ -130,11 +131,11 @@ def main(): create_post(post_dir, video_metadata, host) elif ( - video_metadata["uuid"] in existing_posts + post_name in existing_posts ): # if we already have the video do nothing, possibly update update_post(post_dir, video_metadata, host) existing_posts.remove( - video_metadata["uuid"] + post_name ) # create list of posts which have not been returned by peertube for post in existing_posts: -- 2.49.0 From 40bf9416b8792c08683ad8ac878093c7ef1b2f5d Mon Sep 17 00:00:00 2001 From: knoflook Date: Mon, 7 Feb 2022 11:50:41 +0100 Subject: [PATCH 05/48] cal: fix post deletion logic --- lumbunglib/cloudcal.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/lumbunglib/cloudcal.py b/lumbunglib/cloudcal.py index 2375f31..7f67017 100644 --- a/lumbunglib/cloudcal.py +++ b/lumbunglib/cloudcal.py @@ -193,18 +193,18 @@ def update_event_post(post_dir, event): def main(): for event in list(cal.events): + post_name = sanitize_name(event.name) + "-" + event.uid + post_dir = os.path.join(output_dir, post_name) - post_dir = os.path.join(output_dir, sanitize_name(event.name) + "-" + event.uid) - - if event.uid not in existing_posts: + if post_name not in existing_posts: # if there is an event we dont already have, make it create_event_post(post_dir, event) - elif event.uid in existing_posts: + elif post_name in existing_posts: # if we already have it, update update_event_post(post_dir, event) existing_posts.remove( - event.uid + post_name ) # create list of posts which have not been returned by the calendar for post in existing_posts: -- 2.49.0 From 709921daf17b633fa810c6f6f2a4dc59ff634b70 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Mon, 7 Feb 2022 13:47:11 +0100 Subject: [PATCH 06/48] hacking docs --- README.md | 38 +++++++++++++++++++++++++++++++++++--- 1 file changed, 35 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index df45967..3deeeb2 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,40 @@ # lumbunglib -> Python lib which powers `lumbung[dot]space` automation +> Python lib which powers `lumbung.space` automation ## hacking -- run `poetry run poetry2setup > setup.py` if updating the poetry dependencies -- if adding a new cli command, extend `pyproject.toml` with a new `[tool.poetry.scripts]` entry +Install [poetry](https://python-poetry.org/docs/#osx--linux--bashonwindows-install-instructions): + +```bash +curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/get-poetry.py | python - +``` + +We use Poetry because it locks the dependencies all the way down and makes it +easier to manage installation & maintenance in the long-term. Then install the +dependencies & have them managed by Poetry: + +``` +poetry install +``` + +Each script requires some environment variables to run, you can see the latest +deployment configuration over +[here](https://git.autonomic.zone/ruangrupa/lumbung.space/src/branch/main/compose.yml), +look for the values under the `environment: ...` stanza. + +All scripts have an entrypoint described in the +[`pypoetry.toml`](https://git.autonomic.zone/ruangrupa/lumbunglib/src/commit/40bf9416b8792c08683ad8ac878093c7ef1b2f5d/pyproject.toml#L27-L31) +which you can run via `poetry run ...`. For example, if you want to run the +[`lumbunglib/video.py`](./lumbunglib/video.py) script, you'd do: + +``` +mkdir -p testdir +export OUTPUT_DIR=/testdir +poetry run lumbunglib-vid +``` + +Run `poetry run poetry2setup > setup.py` if updating the poetry dependencies. +This allows us to run `pip install .` in the deployment and Pip will understand +that it is just a regular Python package. If adding a new cli command, extend +`pyproject.toml` with a new `[tool.poetry.scripts]` entry. -- 2.49.0 From 34d84dcde2247620811bcedb12867f9bffbae6ec Mon Sep 17 00:00:00 2001 From: knoflook Date: Thu, 10 Feb 2022 12:52:55 +0100 Subject: [PATCH 07/48] cal, vid: slugify instead of sanitize_name --- lumbunglib/cloudcal.py | 9 ++------- lumbunglib/video.py | 9 ++------- 2 files changed, 4 insertions(+), 14 deletions(-) diff --git a/lumbunglib/cloudcal.py b/lumbunglib/cloudcal.py index 7f67017..0645e45 100644 --- a/lumbunglib/cloudcal.py +++ b/lumbunglib/cloudcal.py @@ -3,6 +3,7 @@ import re import shutil from pathlib import Path from urllib.parse import urlparse +from slugify import slugify import arrow import jinja2 @@ -111,12 +112,6 @@ def localize_time(date): ) return localized_begins -def sanitize_name(name): - sanitized = "".join([c if c.isalnum() or c == " " else "-" for c in name]) - if len(sanitized) > 20: - return sanitized[:20] - return sanitized - def create_event_post(post_dir, event): """ Create HUGO post based on calendar event metadata @@ -193,7 +188,7 @@ def update_event_post(post_dir, event): def main(): for event in list(cal.events): - post_name = sanitize_name(event.name) + "-" + event.uid + post_name = slugify(event.name) + "-" + event.uid post_dir = os.path.join(output_dir, post_name) if post_name not in existing_posts: diff --git a/lumbunglib/video.py b/lumbunglib/video.py index 2945286..94a1908 100644 --- a/lumbunglib/video.py +++ b/lumbunglib/video.py @@ -4,6 +4,7 @@ import json import os import shutil from pathlib import Path +from slugify import slugify import arrow import jinja2 @@ -97,12 +98,6 @@ def update_post(post_directory, video_metadata, host): # compat for when there is no timestamp yet.. create_post(post_directory, video_metadata, host) -def sanitize_name(name): - sanitized = "".join([c if c.isalnum() or c == " " else "-" for c in name]) - if len(sanitized) > 40: - return sanitized[:40] - return sanitized - def main(): v = peertube.VideoApi(client) @@ -119,7 +114,7 @@ def main(): existing_posts = os.listdir(output_dir) for video_metadata in videos: - post_name = sanitize_name(video_metadata["name"]) + "-" + video_metadata["uuid"] + post_name = slugify(video_metadata["name"]) + "-" + video_metadata["uuid"] post_dir = os.path.join(output_dir, post_name) if ( -- 2.49.0 From ab1f8d9d7a454ba82b2ffcb39aa3d8469c06bd65 Mon Sep 17 00:00:00 2001 From: knoflook Date: Tue, 15 Feb 2022 12:10:17 +0100 Subject: [PATCH 08/48] video: paginate results --- lumbunglib/video.py | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/lumbunglib/video.py b/lumbunglib/video.py index 94a1908..3623381 100644 --- a/lumbunglib/video.py +++ b/lumbunglib/video.py @@ -100,11 +100,26 @@ def update_post(post_directory, video_metadata, host): def main(): v = peertube.VideoApi(client) - - response = v.videos_get(count=100, filter="local", tags_one_of="publish") + count = 100 + page = 0 + response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) videos = response.to_dict() - videos = videos["data"] + total = videos['total'] + videos = videos['data'] + total -= count + if total > 0: + to_download = total // count + last_page = total % count + for i in range(to_download): + page += 1 + response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) + videos += response.to_dict()['data'] + if last_page > 0: + page += 1 + response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) + videos += response.to_dict()['data'][-1*last_page:] + output_dir = os.environ.get("OUTPUT_DIR") -- 2.49.0 From 633972451039669939e599974cad02bc1ec6036b Mon Sep 17 00:00:00 2001 From: knoflook Date: Tue, 15 Feb 2022 13:31:33 +0100 Subject: [PATCH 09/48] hashtag: escape quotation marks for display_name --- lumbunglib/hashtag.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/lumbunglib/hashtag.py b/lumbunglib/hashtag.py index 6cdd3e6..8467554 100644 --- a/lumbunglib/hashtag.py +++ b/lumbunglib/hashtag.py @@ -1,6 +1,7 @@ import os import shutil from pathlib import Path +from re import sub import jinja2 import requests @@ -68,7 +69,9 @@ def create_post(post_directory, post_metadata): template_dir = os.path.join(Path(__file__).parent.resolve(), "templates") env = jinja2.Environment(loader=jinja2.FileSystemLoader(template_dir)) - + name = post_metadata['account']['display_name'] + name = sub('"', '\\"', name) + post_metadata['account']['display_name'] = name env.filters["localize_media_url"] = localize_media_url env.filters["filter_mastodon_urls"] = filter_mastodon_urls -- 2.49.0 From 9d9c87809d309c7aea1b716079ab48138f606adf Mon Sep 17 00:00:00 2001 From: rra Date: Wed, 16 Feb 2022 12:12:41 +0100 Subject: [PATCH 10/48] add method to escape " from YAML frontmatter https://git.autonomic.zone/ruangrupa/lumbung.space/issues/33 --- lumbunglib/feed.py | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 5b4ccb1..abaf586 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -12,6 +12,7 @@ import jinja2 import requests from bs4 import BeautifulSoup from slugify import slugify +from re import sub def write_etag(feed_name, feed_data): @@ -84,6 +85,27 @@ def create_frontmatter(entry): return frontmatter +def sanitize_yaml (frontmatter): + """ + Escapes any occurences of double quotes + in any of the frontmatter fields + See: https://docs.octoprint.org/en/master/configuration/yaml.html#interesting-data-types + """ + for k, v in frontmatter.items(): + if type(v) == type([]): + #some fields are lists + l = [] + for i in v: + i = sub('"', '\\"', i) + l.append(i) + frontmatter[k] = l + + else: + v = sub('"', '\\"', v) + frontmatter[k] = v + + return frontmatter + def create_post(post_dir, entry): """ @@ -105,7 +127,7 @@ def create_post(post_dir, entry): env = jinja2.Environment(loader=jinja2.FileSystemLoader(template_dir)) template = env.get_template("feed.md") with open(os.path.join(post_dir, "index.html"), "w") as f: # n.b. .html - post = template.render(frontmatter=frontmatter, content=parsed_content) + post = template.render(frontmatter=sanitize_yaml(frontmatter), content=parsed_content) f.write(post) print("created post for", entry.title, "({})".format(entry.link)) -- 2.49.0 From 1f1bb7874e57b99cb3f04f011bb5c4d7c38f7bc0 Mon Sep 17 00:00:00 2001 From: rra Date: Wed, 16 Feb 2022 13:02:28 +0100 Subject: [PATCH 11/48] feed: support the parsing of OPDS type feeds --- lumbunglib/feed.py | 168 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 134 insertions(+), 34 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index abaf586..983a90a 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -48,40 +48,63 @@ def get_etag(feed_name): def create_frontmatter(entry): """ - parse RSS metadata and return as frontmatter + parse RSS metadata and return as frontmatter """ - if "published" in entry: + if 'published' in entry: published = entry.published_parsed - if "updated" in entry: + if 'updated' in entry: published = entry.updated_parsed published = arrow.get(published) - if "author" in entry: + if 'author' in entry: author = entry.author else: - author = "" + author = '' + + if 'authors' in entry: + authors = [] + for a in entry.authors: + authors.append(a['name']) - if "title" in entry: - title = entry.title + if 'summary' in entry: + summary = entry.summary else: - title = "" + summary = '' + + if 'publisher' in entry: + publisher = entry.publisher + else: + publisher = '' tags = [] - if "tags" in entry: - # TODO finish categories + if 'tags' in entry: + #TODO finish categories for t in entry.tags: - tags.append(t["term"]) + tags.append(t['term']) - frontmatter = { - "title": title, - "date": published.format(), - "summary": "", - "author": author, - "original_link": entry.link, - "feed_name": entry["feed_name"], - "tags": str(tags), - } + if "opds" in entry: + frontmatter = { + 'title':entry.title, + 'date': published.format(), + 'summary': summary, + 'author': ",".join(authors), + 'publisher': publisher, + 'original_link': entry.links[0]['href'].replace('opds/cover/','books/'), + 'feed_name': entry['feed_name'], + 'tags': str(tags), + 'category': "books" + } + else: + frontmatter = { + 'title':entry.title, + 'date': published.format(), + 'summary': '', + 'author': author, + 'original_link': entry.link, + 'feed_name': entry['feed_name'], + 'tags': str(tags) + } return frontmatter @@ -132,28 +155,31 @@ def create_post(post_dir, entry): print("created post for", entry.title, "({})".format(entry.link)) -def grab_media(post_directory, url): +def grab_media(post_directory, url, prefered_name=None): """ download media linked in post to have local copy if download succeeds return new local path otherwise return url """ - image = urlparse(url).path.split("/")[-1] + media_item = urlparse(url).path.split('/')[-1] + + if prefered_name: + media_item = prefered_name try: - if not os.path.exists(os.path.join(post_directory, image)): - # TODO: stream is true is a conditional so we could check the headers for things, mimetype etc + if not os.path.exists(os.path.join(post_directory, media_item)): + #TODO: stream is true is a conditional so we could check the headers for things, mimetype etc response = requests.get(url, stream=True) if response.ok: - with open(os.path.join(post_directory, image), "wb") as img_file: - shutil.copyfileobj(response.raw, img_file) - print("Downloaded cover image", image) - return image - return image - elif os.path.exists(os.path.join(post_directory, image)): - return image + with open(os.path.join(post_directory, media_item), 'wb') as media_file: + shutil.copyfileobj(response.raw, media_file) + print('Downloaded media item', media_item) + return media_item + return media_item + elif os.path.exists(os.path.join(post_directory, media_item)): + return media_item except Exception as e: - print("Failed to download image", url) + print('Failed to download image', url) print(e) return url @@ -208,6 +234,58 @@ def grab_feed(feed_url): return data return False +def create_opds_post(post_dir, entry): + """ + create a HUGO post based on OPDS entry + or update it if the timestamp is newer + Downloads the cover & file + """ + + frontmatter = create_frontmatter(entry) + + template_dir = os.path.join(Path(__file__).parent.resolve(), "templates") + env = jinja2.Environment(loader=jinja2.FileSystemLoader(template_dir)) + template = env.get_template("feed.md") + + if not os.path.exists(post_dir): + os.makedirs(post_dir) + + if os.path.exists(os.path.join(post_dir, '.timestamp')): + old_timestamp = open(os.path.join(post_dir, '.timestamp')).read() + old_timestamp = arrow.get(float(old_timestamp)) + current_timestamp = arrow.get(entry['updated_parsed']) + + if current_timestamp > old_timestamp: + pass + else: + print('Book "{}..." already up to date'.format(entry['title'][:32])) + return + + for item in entry.links: + ft = item['type'].split('/')[-1] + fn = item['rel'].split('/')[-1] + + if fn == "acquisition": + fn = "publication" #calling the publications acquisition is weird + + prefered_name = "{}-{}.{}".format(fn, slugify(entry['title']), ft) + + grab_media(post_dir, item['href'], prefered_name) + + if "summary" in entry: + summary = entry.summary + else: + summary = "" + + with open(os.path.join(post_dir,'index.md'),'w') as f: + post = template.render(frontmatter=sanitize_yaml(frontmatter), content=summary) + f.write(post) + print('created post for Book', entry.title) + + with open(os.path.join(post_dir, '.timestamp'), 'w') as f: + timestamp = arrow.get(entry['updated_parsed']) + f.write(timestamp.format('X')) + def main(): feed_urls = open("feeds_list.txt", "r").read().splitlines() @@ -252,6 +330,15 @@ def main(): data = grab_feed(feed_url) if data: + + opds_feed = False + for i in data.feed['links']: + if i['rel'] == 'self': + if 'opds' in i['type']: + opds_feed = True + print("OPDS type feed!") + + for entry in data.entries: # if 'tags' in entry: # for tag in entry.tags: @@ -261,6 +348,7 @@ def main(): entry["feed_name"] = feed_name post_name = slugify(entry.title) + # pixelfed returns the whole post text as the post name. max # filename length is 255 on many systems. here we're shortening # the name and adding a hash to it to avoid a conflict in a @@ -268,15 +356,27 @@ def main(): if len(post_name) > 150: post_hash = md5(bytes(post_name, "utf-8")) post_name = post_name[:150] + "-" + post_hash.hexdigest() + + if opds_feed: + entry['opds'] = True + #format: Beyond-Debiasing-Report_Online-75535a4886e3 + post_name = slugify(entry['title'])+'-'+entry['id'].split('-')[-1] + post_dir = os.path.join(output_dir, feed_name, post_name) if post_name not in existing_posts: # if there is a blog entry we dont already have, make it - create_post(post_dir, entry) + if opds_feed: + create_opds_post(post_dir, entry) + else: + create_post(post_dir, entry) elif post_name in existing_posts: # if we already have it, update it - create_post(post_dir, entry) + if opds_feed: + create_opds_post(post_dir, entry) + else: + create_post(post_dir, entry) existing_posts.remove( post_name ) # create list of posts which have not been returned by the feed -- 2.49.0 From 41690c0a898f554d86e087b4224850847bd74af2 Mon Sep 17 00:00:00 2001 From: rra Date: Wed, 16 Feb 2022 13:02:55 +0100 Subject: [PATCH 12/48] add agplv3 license --- LICENSE.md | 660 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 660 insertions(+) create mode 100644 LICENSE.md diff --git a/LICENSE.md b/LICENSE.md new file mode 100644 index 0000000..cba6f6a --- /dev/null +++ b/LICENSE.md @@ -0,0 +1,660 @@ +### GNU AFFERO GENERAL PUBLIC LICENSE + +Version 3, 19 November 2007 + +Copyright (C) 2007 Free Software Foundation, Inc. + + +Everyone is permitted to copy and distribute verbatim copies of this +license document, but changing it is not allowed. + +### Preamble + +The GNU Affero General Public License is a free, copyleft license for +software and other kinds of works, specifically designed to ensure +cooperation with the community in the case of network server software. + +The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +our General Public Licenses are intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains +free software for all its users. + +When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + +Developers that use our General Public Licenses protect your rights +with two steps: (1) assert copyright on the software, and (2) offer +you this License which gives you legal permission to copy, distribute +and/or modify the software. + +A secondary benefit of defending all users' freedom is that +improvements made in alternate versions of the program, if they +receive widespread use, become available for other developers to +incorporate. Many developers of free software are heartened and +encouraged by the resulting cooperation. However, in the case of +software used on network servers, this result may fail to come about. +The GNU General Public License permits making a modified version and +letting the public access it on a server without ever releasing its +source code to the public. + +The GNU Affero General Public License is designed specifically to +ensure that, in such cases, the modified source code becomes available +to the community. It requires the operator of a network server to +provide the source code of the modified version running there to the +users of that server. Therefore, public use of a modified version, on +a publicly accessible server, gives the public access to the source +code of the modified version. + +An older license, called the Affero General Public License and +published by Affero, was designed to accomplish similar goals. This is +a different license, not a version of the Affero GPL, but Affero has +released a new version of the Affero GPL which permits relicensing +under this license. + +The precise terms and conditions for copying, distribution and +modification follow. + +### TERMS AND CONDITIONS + +#### 0. Definitions. + +"This License" refers to version 3 of the GNU Affero General Public +License. + +"Copyright" also means copyright-like laws that apply to other kinds +of works, such as semiconductor masks. + +"The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + +To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of +an exact copy. The resulting work is called a "modified version" of +the earlier work or a work "based on" the earlier work. + +A "covered work" means either the unmodified Program or a work based +on the Program. + +To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + +To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user +through a computer network, with no transfer of a copy, is not +conveying. + +An interactive user interface displays "Appropriate Legal Notices" to +the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + +#### 1. Source Code. + +The "source code" for a work means the preferred form of the work for +making modifications to it. "Object code" means any non-source form of +a work. + +A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + +The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + +The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + +The Corresponding Source need not include anything that users can +regenerate automatically from other parts of the Corresponding Source. + +The Corresponding Source for a work in source code form is that same +work. + +#### 2. Basic Permissions. + +All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + +You may make, run and propagate covered works that you do not convey, +without conditions so long as your license otherwise remains in force. +You may convey covered works to others for the sole purpose of having +them make modifications exclusively for you, or provide you with +facilities for running those works, provided that you comply with the +terms of this License in conveying all material for which you do not +control copyright. Those thus making or running the covered works for +you must do so exclusively on your behalf, under your direction and +control, on terms that prohibit them from making any copies of your +copyrighted material outside their relationship with you. + +Conveying under any other circumstances is permitted solely under the +conditions stated below. Sublicensing is not allowed; section 10 makes +it unnecessary. + +#### 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + +No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + +When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such +circumvention is effected by exercising rights under this License with +respect to the covered work, and you disclaim any intention to limit +operation or modification of the work as a means of enforcing, against +the work's users, your or third parties' legal rights to forbid +circumvention of technological measures. + +#### 4. Conveying Verbatim Copies. + +You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + +You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + +#### 5. Conveying Modified Source Versions. + +You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these +conditions: + +- a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. +- b) The work must carry prominent notices stating that it is + released under this License and any conditions added under + section 7. This requirement modifies the requirement in section 4 + to "keep intact all notices". +- c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. +- d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + +A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + +#### 6. Conveying Non-Source Forms. + +You may convey a covered work in object code form under the terms of +sections 4 and 5, provided that you also convey the machine-readable +Corresponding Source under the terms of this License, in one of these +ways: + +- a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. +- b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the Corresponding + Source from a network server at no charge. +- c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. +- d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. +- e) Convey the object code using peer-to-peer transmission, + provided you inform other peers where the object code and + Corresponding Source of the work are being offered to the general + public at no charge under subsection 6d. + +A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + +A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, +family, or household purposes, or (2) anything designed or sold for +incorporation into a dwelling. In determining whether a product is a +consumer product, doubtful cases shall be resolved in favor of +coverage. For a particular product received by a particular user, +"normally used" refers to a typical or common use of that class of +product, regardless of the status of the particular user or of the way +in which the particular user actually uses, or expects or is expected +to use, the product. A product is a consumer product regardless of +whether the product has substantial commercial, industrial or +non-consumer uses, unless such uses represent the only significant +mode of use of the product. + +"Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to +install and execute modified versions of a covered work in that User +Product from a modified version of its Corresponding Source. The +information must suffice to ensure that the continued functioning of +the modified object code is in no case prevented or interfered with +solely because modification has been made. + +If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + +The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or +updates for a work that has been modified or installed by the +recipient, or for the User Product in which it has been modified or +installed. Access to a network may be denied when the modification +itself materially and adversely affects the operation of the network +or violates the rules and protocols for communication across the +network. + +Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + +#### 7. Additional Terms. + +"Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + +When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + +Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders +of that material) supplement the terms of this License with terms: + +- a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or +- b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or +- c) Prohibiting misrepresentation of the origin of that material, + or requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or +- d) Limiting the use for publicity purposes of names of licensors + or authors of the material; or +- e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or +- f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions + of it) with contractual assumptions of liability to the recipient, + for any liability that these contractual assumptions directly + impose on those licensors and authors. + +All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + +If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + +Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; the +above requirements apply either way. + +#### 8. Termination. + +You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + +However, if you cease all violation of this License, then your license +from a particular copyright holder is reinstated (a) provisionally, +unless and until the copyright holder explicitly and finally +terminates your license, and (b) permanently, if the copyright holder +fails to notify you of the violation by some reasonable means prior to +60 days after the cessation. + +Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + +Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + +#### 9. Acceptance Not Required for Having Copies. + +You are not required to accept this License in order to receive or run +a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + +#### 10. Automatic Licensing of Downstream Recipients. + +Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + +An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + +You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + +#### 11. Patents. + +A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + +A contributor's "essential patent claims" are all patent claims owned +or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + +Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + +In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + +If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + +If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + +A patent license is "discriminatory" if it does not include within the +scope of its coverage, prohibits the exercise of, or is conditioned on +the non-exercise of one or more of the rights that are specifically +granted under this License. You may not convey a covered work if you +are a party to an arrangement with a third party that is in the +business of distributing software, under which you make payment to the +third party based on the extent of your activity of conveying the +work, and under which the third party grants, to any of the parties +who would receive the covered work from you, a discriminatory patent +license (a) in connection with copies of the covered work conveyed by +you (or copies made from those copies), or (b) primarily for and in +connection with specific products or compilations that contain the +covered work, unless you entered into that arrangement, or that patent +license was granted, prior to 28 March 2007. + +Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + +#### 12. No Surrender of Others' Freedom. + +If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under +this License and any other pertinent obligations, then as a +consequence you may not convey it at all. For example, if you agree to +terms that obligate you to collect a royalty for further conveying +from those to whom you convey the Program, the only way you could +satisfy both those terms and this License would be to refrain entirely +from conveying the Program. + +#### 13. Remote Network Interaction; Use with the GNU General Public License. + +Notwithstanding any other provision of this License, if you modify the +Program, your modified version must prominently offer all users +interacting with it remotely through a computer network (if your +version supports such interaction) an opportunity to receive the +Corresponding Source of your version by providing access to the +Corresponding Source from a network server at no charge, through some +standard or customary means of facilitating copying of software. This +Corresponding Source shall include the Corresponding Source for any +work covered by version 3 of the GNU General Public License that is +incorporated pursuant to the following paragraph. + +Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the work with which it is combined will remain governed by version +3 of the GNU General Public License. + +#### 14. Revised Versions of this License. + +The Free Software Foundation may publish revised and/or new versions +of the GNU Affero General Public License from time to time. Such new +versions will be similar in spirit to the present version, but may +differ in detail to address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies that a certain numbered version of the GNU Affero General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU Affero General Public License, you may choose any version ever +published by the Free Software Foundation. + +If the Program specifies that a proxy can decide which future versions +of the GNU Affero General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + +Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + +#### 15. Disclaimer of Warranty. + +THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT +WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND +PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE +DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR +CORRECTION. + +#### 16. Limitation of Liability. + +IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR +CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES +ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT +NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR +LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM +TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER +PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. + +#### 17. Interpretation of Sections 15 and 16. + +If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + +END OF TERMS AND CONDITIONS + +### How to Apply These Terms to Your New Programs + +If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these +terms. + +To do so, attach the following notices to the program. It is safest to +attach them to the start of each source file to most effectively state +the exclusion of warranty; and each file should have at least the +"copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as + published by the Free Software Foundation, either version 3 of the + License, or (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper +mail. + +If your software can interact with users remotely through a computer +network, you should also make sure that it provides a way for users to +get its source. For example, if your program is a web application, its +interface could display a "Source" link that leads users to an archive +of the code. There are many ways you could offer source, and different +solutions will be better for different programs; see section 13 for +the specific requirements. + +You should also get your employer (if you work as a programmer) or +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. For more information on this, and how to apply and follow +the GNU AGPL, see . -- 2.49.0 From f69c092548518f7ca2901ed21e9a0a97b360799b Mon Sep 17 00:00:00 2001 From: knoflook Date: Thu, 17 Feb 2022 16:15:43 +0100 Subject: [PATCH 13/48] feed: escape quotation marks --- lumbunglib/feed.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 5b4ccb1..6d2e14e 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -5,6 +5,7 @@ from hashlib import md5 from ast import literal_eval as make_tuple from pathlib import Path from urllib.parse import urlparse +from re import sub import arrow import feedparser @@ -57,12 +58,12 @@ def create_frontmatter(entry): published = arrow.get(published) if "author" in entry: - author = entry.author + author = sub('"', '\\"', entry.author) else: author = "" if "title" in entry: - title = entry.title + title = sub('"', '\\"', entry.title) else: title = "" -- 2.49.0 From b147d465359fcca8621fd79798656c8809fea1a0 Mon Sep 17 00:00:00 2001 From: knoflook Date: Mon, 21 Feb 2022 11:19:12 +0100 Subject: [PATCH 14/48] feed: compile regex once --- lumbunglib/feed.py | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 983a90a..10ba290 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -12,7 +12,8 @@ import jinja2 import requests from bs4 import BeautifulSoup from slugify import slugify -from re import sub +from re import compile as re_compile +yamlre = re_compile('"') def write_etag(feed_name, feed_data): @@ -48,7 +49,7 @@ def get_etag(feed_name): def create_frontmatter(entry): """ - parse RSS metadata and return as frontmatter + parse RSS metadata and return as frontmatter """ if 'published' in entry: published = entry.published_parsed @@ -61,7 +62,7 @@ def create_frontmatter(entry): author = entry.author else: author = '' - + if 'authors' in entry: authors = [] for a in entry.authors: @@ -119,12 +120,12 @@ def sanitize_yaml (frontmatter): #some fields are lists l = [] for i in v: - i = sub('"', '\\"', i) + i = yamlre.sub('\\"', i) l.append(i) frontmatter[k] = l else: - v = sub('"', '\\"', v) + v = yamlre.sub('\\"', v) frontmatter[k] = v return frontmatter @@ -348,7 +349,7 @@ def main(): entry["feed_name"] = feed_name post_name = slugify(entry.title) - + # pixelfed returns the whole post text as the post name. max # filename length is 255 on many systems. here we're shortening # the name and adding a hash to it to avoid a conflict in a @@ -356,7 +357,7 @@ def main(): if len(post_name) > 150: post_hash = md5(bytes(post_name, "utf-8")) post_name = post_name[:150] + "-" + post_hash.hexdigest() - + if opds_feed: entry['opds'] = True #format: Beyond-Debiasing-Report_Online-75535a4886e3 @@ -376,7 +377,7 @@ def main(): if opds_feed: create_opds_post(post_dir, entry) else: - create_post(post_dir, entry) + create_post(post_dir, entry) existing_posts.remove( post_name ) # create list of posts which have not been returned by the feed -- 2.49.0 From 0aaa71153877054751c4d2f41fba7d0b2cec8b7b Mon Sep 17 00:00:00 2001 From: rra Date: Sun, 3 Apr 2022 16:40:22 +0200 Subject: [PATCH 15/48] Update 'lumbunglib/hashtag.py' added extra tags on request --- lumbunglib/hashtag.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/lumbunglib/hashtag.py b/lumbunglib/hashtag.py index 8467554..04054bf 100644 --- a/lumbunglib/hashtag.py +++ b/lumbunglib/hashtag.py @@ -19,6 +19,9 @@ hashtags = [ "majelisakbar", "warungkopi", "lumbungkios", + "kassel_ecosystem", + "ruruhaus", + "offbeatentrack_kassel" ] -- 2.49.0 From dfa4b40d52c98b9f2250ffa577b14b2a25d06726 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Wed, 6 Apr 2022 09:44:14 +0200 Subject: [PATCH 16/48] more hashtags --- lumbunglib/hashtag.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lumbunglib/hashtag.py b/lumbunglib/hashtag.py index 04054bf..2d46e0e 100644 --- a/lumbunglib/hashtag.py +++ b/lumbunglib/hashtag.py @@ -21,7 +21,8 @@ hashtags = [ "lumbungkios", "kassel_ecosystem", "ruruhaus", - "offbeatentrack_kassel" + "offbeatentrack_kassel", + "lumbungofpublishers", ] -- 2.49.0 From 8c4a36791f1bcf7001d27eca7b51d69f21e8a0d1 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Wed, 6 Apr 2022 09:44:19 +0200 Subject: [PATCH 17/48] autoformatter says change this so i change --- lumbunglib/hashtag.py | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/lumbunglib/hashtag.py b/lumbunglib/hashtag.py index 2d46e0e..baf21c9 100644 --- a/lumbunglib/hashtag.py +++ b/lumbunglib/hashtag.py @@ -28,8 +28,7 @@ hashtags = [ def login_mastodon_bot(): mastodon = Mastodon( - access_token=os.environ.get("MASTODON_AUTH_TOKEN"), - api_base_url = instance + access_token=os.environ.get("MASTODON_AUTH_TOKEN"), api_base_url=instance ) return mastodon @@ -73,9 +72,9 @@ def create_post(post_directory, post_metadata): template_dir = os.path.join(Path(__file__).parent.resolve(), "templates") env = jinja2.Environment(loader=jinja2.FileSystemLoader(template_dir)) - name = post_metadata['account']['display_name'] + name = post_metadata["account"]["display_name"] name = sub('"', '\\"', name) - post_metadata['account']['display_name'] = name + post_metadata["account"]["display_name"] = name env.filters["localize_media_url"] = localize_media_url env.filters["filter_mastodon_urls"] = filter_mastodon_urls @@ -140,7 +139,10 @@ def main(): create_post(post_dir, post_metadata) all_existing_posts.append(str(post_metadata["id"])) else: - print("not pulling post %s (post is local only)" % (post_metadata["id"])) + print( + "not pulling post %s (post is local only)" + % (post_metadata["id"]) + ) # if we already have the post do nothing, possibly update elif str(post_metadata["id"]) in existing_posts: @@ -149,7 +151,10 @@ def main(): str(post_metadata["id"]) ) # create list of posts which have not been returned in the feed elif str(post_metadata["id"]) in all_existing_posts: - print("skipping post %s as it was already pulled with a different hashtag." % (str(post_metadata["id"]))) + print( + "skipping post %s as it was already pulled with a different hashtag." + % (str(post_metadata["id"])) + ) for post in existing_posts: print( -- 2.49.0 From bac9bbd7b3c6d48a41a6692e9d9e5cf08f16e20c Mon Sep 17 00:00:00 2001 From: knoflook Date: Mon, 11 Apr 2022 13:46:52 +0200 Subject: [PATCH 18/48] vid: remove all vids if API down --- lumbunglib/video.py | 84 +++++++++++++++++++++++++-------------------- 1 file changed, 46 insertions(+), 38 deletions(-) diff --git a/lumbunglib/video.py b/lumbunglib/video.py index 3623381..f120c1f 100644 --- a/lumbunglib/video.py +++ b/lumbunglib/video.py @@ -102,52 +102,60 @@ def main(): v = peertube.VideoApi(client) count = 100 page = 0 - response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) - - videos = response.to_dict() - total = videos['total'] - videos = videos['data'] - total -= count - if total > 0: - to_download = total // count - last_page = total % count - for i in range(to_download): - page += 1 - response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) - videos += response.to_dict()['data'] - if last_page > 0: - page += 1 - response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) - videos += response.to_dict()['data'][-1*last_page:] + try: + response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) + videos = response.to_dict() + total = videos['total'] + videos = videos['data'] + total -= count + if total > 0: + to_download = total // count + last_page = total % count + for i in range(to_download): + page += 1 + response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) + videos += response.to_dict()['data'] + if last_page > 0: + page += 1 + response = v.videos_get(count=count, filter="local", tags_one_of="publish", start=page) + videos += response.to_dict()['data'][-1*last_page:] - output_dir = os.environ.get("OUTPUT_DIR") + output_dir = os.environ.get("OUTPUT_DIR") - if not os.path.exists(output_dir): - os.mkdir(output_dir) + if not os.path.exists(output_dir): + os.mkdir(output_dir) - existing_posts = os.listdir(output_dir) + existing_posts = os.listdir(output_dir) - for video_metadata in videos: - post_name = slugify(video_metadata["name"]) + "-" + video_metadata["uuid"] - post_dir = os.path.join(output_dir, post_name) + for video_metadata in videos: + post_name = slugify(video_metadata["name"]) + "-" + video_metadata["uuid"] + post_dir = os.path.join(output_dir, post_name) - if ( - post_name not in existing_posts - ): # if there is a video we dont already have, make it - print( - "New: ", video_metadata["name"], "({})".format(video_metadata["uuid"]) - ) - create_post(post_dir, video_metadata, host) + if ( + post_name not in existing_posts + ): # if there is a video we dont already have, make it + print( + "New: ", video_metadata["name"], "({})".format(video_metadata["uuid"]) + ) + create_post(post_dir, video_metadata, host) - elif ( - post_name in existing_posts - ): # if we already have the video do nothing, possibly update - update_post(post_dir, video_metadata, host) - existing_posts.remove( - post_name - ) # create list of posts which have not been returned by peertube + elif ( + post_name in existing_posts + ): # if we already have the video do nothing, possibly update + update_post(post_dir, video_metadata, host) + existing_posts.remove( + post_name + ) # create list of posts which have not been returned by peertube + + except: + print("didn't get a response from peertube, instance might have been taken down or made private. removing all posts.") + output_dir = os.environ.get("OUTPUT_DIR") + if not os.path.exists(output_dir): + os.mkdir(output_dir) + existing_posts = os.listdir(output_dir) for post in existing_posts: print("deleted", post) # rm posts not returned shutil.rmtree(os.path.join(output_dir, post)) + -- 2.49.0 From 2fbc952a72c8de97a1b7782bc7076fc9b75e50de Mon Sep 17 00:00:00 2001 From: knoflook Date: Fri, 18 Mar 2022 13:59:14 +0100 Subject: [PATCH 19/48] feat: sanitize all yaml --- lumbunglib/feed.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 8c2bba0..b2f30df 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -5,7 +5,6 @@ from hashlib import md5 from ast import literal_eval as make_tuple from pathlib import Path from urllib.parse import urlparse -from re import sub import arrow import feedparser @@ -14,7 +13,8 @@ import requests from bs4 import BeautifulSoup from slugify import slugify from re import compile as re_compile -yamlre = re_compile('"') +from re import sub +yamlre = re_compile('[_\?:\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') def write_etag(feed_name, feed_data): @@ -121,12 +121,12 @@ def sanitize_yaml (frontmatter): #some fields are lists l = [] for i in v: - i = yamlre.sub('\\"', i) + i = yamlre.sub(r'\\\g<0>', i) l.append(i) frontmatter[k] = l else: - v = yamlre.sub('\\"', v) + v = yamlre.sub(r'\\\g<0>', v) frontmatter[k] = v return frontmatter -- 2.49.0 From cf8b1ff7e98209d9e75c4a201bd57270edee70b4 Mon Sep 17 00:00:00 2001 From: knoflook Date: Thu, 24 Mar 2022 15:13:53 +0100 Subject: [PATCH 20/48] fix: don't escape some characters --- lumbunglib/feed.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index b2f30df..6c04da5 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -14,7 +14,7 @@ from bs4 import BeautifulSoup from slugify import slugify from re import compile as re_compile from re import sub -yamlre = re_compile('[_\?:\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') +yamlre = re_compile('[_\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') def write_etag(feed_name, feed_data): -- 2.49.0 From a809433410827ced9c2d734bd375c45c6969824d Mon Sep 17 00:00:00 2001 From: knoflook Date: Tue, 12 Apr 2022 13:41:34 +0200 Subject: [PATCH 21/48] feed: move to saneyaml --- lumbunglib/feed.py | 7 +++-- poetry.lock | 64 +++++++++++++++++++++++++++++++++++++++++++++- pyproject.toml | 1 + 3 files changed, 67 insertions(+), 5 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 6c04da5..1348e02 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -13,8 +13,7 @@ import requests from bs4 import BeautifulSoup from slugify import slugify from re import compile as re_compile -from re import sub -yamlre = re_compile('[_\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') +import saneyaml def write_etag(feed_name, feed_data): @@ -121,12 +120,12 @@ def sanitize_yaml (frontmatter): #some fields are lists l = [] for i in v: - i = yamlre.sub(r'\\\g<0>', i) + i = saneyaml.load(i) l.append(i) frontmatter[k] = l else: - v = yamlre.sub(r'\\\g<0>', v) + v = saneyaml.load(v) frontmatter[k] = v return frontmatter diff --git a/poetry.lock b/poetry.lock index 24631e5..ebc7b53 100644 --- a/poetry.lock +++ b/poetry.lock @@ -242,6 +242,14 @@ category = "main" optional = false python-versions = "*" +[[package]] +name = "pyyaml" +version = "6.0" +description = "YAML parser and emitter for Python" +category = "main" +optional = false +python-versions = ">=3.6" + [[package]] name = "requests" version = "2.27.1" @@ -260,6 +268,21 @@ urllib3 = ">=1.21.1,<1.27" socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"] use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"] +[[package]] +name = "saneyaml" +version = "0.5.2" +description = "Read and write readable YAML safely preserving order and avoiding bad surprises with unwanted infered type conversions. This library is a PyYaml wrapper with sane behaviour to read and write readable YAML safely, typically when used for configuration." +category = "main" +optional = false +python-versions = "<4,>=3.6.*" + +[package.dependencies] +PyYAML = "*" + +[package.extras] +docs = ["Sphinx (>=3.3.1)", "sphinx-rtd-theme (>=0.5.0)", "doc8 (>=0.8.1)"] +testing = ["pytest (>=6)", "pytest-xdist (>=2)"] + [[package]] name = "sgmllib3k" version = "1.0.0" @@ -319,7 +342,7 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"] [metadata] lock-version = "1.1" python-versions = "^3.9" -content-hash = "c5c987253f949737210f4a3d3c3c24b0affd4a9c7d06de386c9bd514c592db8b" +content-hash = "86ebded9dbd151b57502b40d3e58d6d92f837bc776184afa84d297c40d6daa7a" [metadata.files] arrow = [ @@ -469,10 +492,49 @@ pytz = [ {file = "pytz-2021.3-py2.py3-none-any.whl", hash = "sha256:3672058bc3453457b622aab7a1c3bfd5ab0bdae451512f6cf25f64ed37f5b87c"}, {file = "pytz-2021.3.tar.gz", hash = "sha256:acad2d8b20a1af07d4e4c9d2e9285c5ed9104354062f275f3fcd88dcef4f1326"}, ] +pyyaml = [ + {file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"}, + {file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"}, + {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77f396e6ef4c73fdc33a9157446466f1cff553d979bd00ecb64385760c6babdc"}, + {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a80a78046a72361de73f8f395f1f1e49f956c6be882eed58505a15f3e430962b"}, + {file = "PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f84fbc98b019fef2ee9a1cb3ce93e3187a6df0b2538a651bfb890254ba9f90b5"}, + {file = "PyYAML-6.0-cp310-cp310-win32.whl", hash = "sha256:2cd5df3de48857ed0544b34e2d40e9fac445930039f3cfe4bcc592a1f836d513"}, + {file = "PyYAML-6.0-cp310-cp310-win_amd64.whl", hash = "sha256:daf496c58a8c52083df09b80c860005194014c3698698d1a57cbcfa182142a3a"}, + {file = "PyYAML-6.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:897b80890765f037df3403d22bab41627ca8811ae55e9a722fd0392850ec4d86"}, + {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50602afada6d6cbfad699b0c7bb50d5ccffa7e46a3d738092afddc1f9758427f"}, + {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:48c346915c114f5fdb3ead70312bd042a953a8ce5c7106d5bfb1a5254e47da92"}, + {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:98c4d36e99714e55cfbaaee6dd5badbc9a1ec339ebfc3b1f52e293aee6bb71a4"}, + {file = "PyYAML-6.0-cp36-cp36m-win32.whl", hash = "sha256:0283c35a6a9fbf047493e3a0ce8d79ef5030852c51e9d911a27badfde0605293"}, + {file = "PyYAML-6.0-cp36-cp36m-win_amd64.whl", hash = "sha256:07751360502caac1c067a8132d150cf3d61339af5691fe9e87803040dbc5db57"}, + {file = "PyYAML-6.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:819b3830a1543db06c4d4b865e70ded25be52a2e0631ccd2f6a47a2822f2fd7c"}, + {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:473f9edb243cb1935ab5a084eb238d842fb8f404ed2193a915d1784b5a6b5fc0"}, + {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ce82d761c532fe4ec3f87fc45688bdd3a4c1dc5e0b4a19814b9009a29baefd4"}, + {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:231710d57adfd809ef5d34183b8ed1eeae3f76459c18fb4a0b373ad56bedcdd9"}, + {file = "PyYAML-6.0-cp37-cp37m-win32.whl", hash = "sha256:c5687b8d43cf58545ade1fe3e055f70eac7a5a1a0bf42824308d868289a95737"}, + {file = "PyYAML-6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:d15a181d1ecd0d4270dc32edb46f7cb7733c7c508857278d3d378d14d606db2d"}, + {file = "PyYAML-6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0b4624f379dab24d3725ffde76559cff63d9ec94e1736b556dacdfebe5ab6d4b"}, + {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:213c60cd50106436cc818accf5baa1aba61c0189ff610f64f4a3e8c6726218ba"}, + {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fa600030013c4de8165339db93d182b9431076eb98eb40ee068700c9c813e34"}, + {file = "PyYAML-6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:277a0ef2981ca40581a47093e9e2d13b3f1fbbeffae064c1d21bfceba2030287"}, + {file = "PyYAML-6.0-cp38-cp38-win32.whl", hash = "sha256:d4eccecf9adf6fbcc6861a38015c2a64f38b9d94838ac1810a9023a0609e1b78"}, + {file = "PyYAML-6.0-cp38-cp38-win_amd64.whl", hash = "sha256:1e4747bc279b4f613a09eb64bba2ba602d8a6664c6ce6396a4d0cd413a50ce07"}, + {file = "PyYAML-6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:055d937d65826939cb044fc8c9b08889e8c743fdc6a32b33e2390f66013e449b"}, + {file = "PyYAML-6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e61ceaab6f49fb8bdfaa0f92c4b57bcfbea54c09277b1b4f7ac376bfb7a7c174"}, + {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d67d839ede4ed1b28a4e8909735fc992a923cdb84e618544973d7dfc71540803"}, + {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cba8c411ef271aa037d7357a2bc8f9ee8b58b9965831d9e51baf703280dc73d3"}, + {file = "PyYAML-6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:40527857252b61eacd1d9af500c3337ba8deb8fc298940291486c465c8b46ec0"}, + {file = "PyYAML-6.0-cp39-cp39-win32.whl", hash = "sha256:b5b9eccad747aabaaffbc6064800670f0c297e52c12754eb1d976c57e4f74dcb"}, + {file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"}, + {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"}, +] requests = [ {file = "requests-2.27.1-py2.py3-none-any.whl", hash = "sha256:f22fa1e554c9ddfd16e6e41ac79759e17be9e492b3587efa038054674760e72d"}, {file = "requests-2.27.1.tar.gz", hash = "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61"}, ] +saneyaml = [ + {file = "saneyaml-0.5.2-py3-none-any.whl", hash = "sha256:e54ed827973647ee9be8e8c091536b55ad22b3f9b1296e36701a3544822e7eac"}, + {file = "saneyaml-0.5.2.tar.gz", hash = "sha256:d6074f1959041342ab41d74a6f904720ffbcf63c94467858e0e22e17e3c43d41"}, +] sgmllib3k = [ {file = "sgmllib3k-1.0.0.tar.gz", hash = "sha256:7868fb1c8bfa764c1ac563d3cf369c381d1325d36124933a726f29fcdaa812e9"}, ] diff --git a/pyproject.toml b/pyproject.toml index 20ba70a..1a3fdcf 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -16,6 +16,7 @@ peertube = {git = "https://framagit.org/framasoft/peertube/clients/python.git"} feedparser = "^6.0.8" bs4 = "^0.0.1" "Mastodon.py" = "^1.5.1" +saneyaml = "^0.5.2" [tool.poetry.dev-dependencies] poetry2setup = "^1.0.0" -- 2.49.0 From 58afd189a74ae6b77fb779fbcc8abde6e3448b6b Mon Sep 17 00:00:00 2001 From: decentral1se Date: Wed, 13 Apr 2022 12:48:13 +0200 Subject: [PATCH 22/48] Revert "feed: move to saneyaml" This reverts commit a809433410827ced9c2d734bd375c45c6969824d. --- lumbunglib/feed.py | 7 ++--- poetry.lock | 64 +--------------------------------------------- pyproject.toml | 1 - 3 files changed, 5 insertions(+), 67 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 1348e02..6c04da5 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -13,7 +13,8 @@ import requests from bs4 import BeautifulSoup from slugify import slugify from re import compile as re_compile -import saneyaml +from re import sub +yamlre = re_compile('[_\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') def write_etag(feed_name, feed_data): @@ -120,12 +121,12 @@ def sanitize_yaml (frontmatter): #some fields are lists l = [] for i in v: - i = saneyaml.load(i) + i = yamlre.sub(r'\\\g<0>', i) l.append(i) frontmatter[k] = l else: - v = saneyaml.load(v) + v = yamlre.sub(r'\\\g<0>', v) frontmatter[k] = v return frontmatter diff --git a/poetry.lock b/poetry.lock index ebc7b53..24631e5 100644 --- a/poetry.lock +++ b/poetry.lock @@ -242,14 +242,6 @@ category = "main" optional = false python-versions = "*" -[[package]] -name = "pyyaml" -version = "6.0" -description = "YAML parser and emitter for Python" -category = "main" -optional = false -python-versions = ">=3.6" - [[package]] name = "requests" version = "2.27.1" @@ -268,21 +260,6 @@ urllib3 = ">=1.21.1,<1.27" socks = ["PySocks (>=1.5.6,!=1.5.7)", "win-inet-pton"] use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"] -[[package]] -name = "saneyaml" -version = "0.5.2" -description = "Read and write readable YAML safely preserving order and avoiding bad surprises with unwanted infered type conversions. This library is a PyYaml wrapper with sane behaviour to read and write readable YAML safely, typically when used for configuration." -category = "main" -optional = false -python-versions = "<4,>=3.6.*" - -[package.dependencies] -PyYAML = "*" - -[package.extras] -docs = ["Sphinx (>=3.3.1)", "sphinx-rtd-theme (>=0.5.0)", "doc8 (>=0.8.1)"] -testing = ["pytest (>=6)", "pytest-xdist (>=2)"] - [[package]] name = "sgmllib3k" version = "1.0.0" @@ -342,7 +319,7 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"] [metadata] lock-version = "1.1" python-versions = "^3.9" -content-hash = "86ebded9dbd151b57502b40d3e58d6d92f837bc776184afa84d297c40d6daa7a" +content-hash = "c5c987253f949737210f4a3d3c3c24b0affd4a9c7d06de386c9bd514c592db8b" [metadata.files] arrow = [ @@ -492,49 +469,10 @@ pytz = [ {file = "pytz-2021.3-py2.py3-none-any.whl", hash = "sha256:3672058bc3453457b622aab7a1c3bfd5ab0bdae451512f6cf25f64ed37f5b87c"}, {file = "pytz-2021.3.tar.gz", hash = "sha256:acad2d8b20a1af07d4e4c9d2e9285c5ed9104354062f275f3fcd88dcef4f1326"}, ] -pyyaml = [ - {file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"}, - {file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"}, - {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77f396e6ef4c73fdc33a9157446466f1cff553d979bd00ecb64385760c6babdc"}, - {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a80a78046a72361de73f8f395f1f1e49f956c6be882eed58505a15f3e430962b"}, - {file = "PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f84fbc98b019fef2ee9a1cb3ce93e3187a6df0b2538a651bfb890254ba9f90b5"}, - {file = "PyYAML-6.0-cp310-cp310-win32.whl", hash = "sha256:2cd5df3de48857ed0544b34e2d40e9fac445930039f3cfe4bcc592a1f836d513"}, - {file = "PyYAML-6.0-cp310-cp310-win_amd64.whl", hash = "sha256:daf496c58a8c52083df09b80c860005194014c3698698d1a57cbcfa182142a3a"}, - {file = "PyYAML-6.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:897b80890765f037df3403d22bab41627ca8811ae55e9a722fd0392850ec4d86"}, - {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50602afada6d6cbfad699b0c7bb50d5ccffa7e46a3d738092afddc1f9758427f"}, - {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:48c346915c114f5fdb3ead70312bd042a953a8ce5c7106d5bfb1a5254e47da92"}, - {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:98c4d36e99714e55cfbaaee6dd5badbc9a1ec339ebfc3b1f52e293aee6bb71a4"}, - {file = "PyYAML-6.0-cp36-cp36m-win32.whl", hash = "sha256:0283c35a6a9fbf047493e3a0ce8d79ef5030852c51e9d911a27badfde0605293"}, - {file = "PyYAML-6.0-cp36-cp36m-win_amd64.whl", hash = "sha256:07751360502caac1c067a8132d150cf3d61339af5691fe9e87803040dbc5db57"}, - {file = "PyYAML-6.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:819b3830a1543db06c4d4b865e70ded25be52a2e0631ccd2f6a47a2822f2fd7c"}, - {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:473f9edb243cb1935ab5a084eb238d842fb8f404ed2193a915d1784b5a6b5fc0"}, - {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ce82d761c532fe4ec3f87fc45688bdd3a4c1dc5e0b4a19814b9009a29baefd4"}, - {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:231710d57adfd809ef5d34183b8ed1eeae3f76459c18fb4a0b373ad56bedcdd9"}, - {file = "PyYAML-6.0-cp37-cp37m-win32.whl", hash = "sha256:c5687b8d43cf58545ade1fe3e055f70eac7a5a1a0bf42824308d868289a95737"}, - {file = "PyYAML-6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:d15a181d1ecd0d4270dc32edb46f7cb7733c7c508857278d3d378d14d606db2d"}, - {file = "PyYAML-6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0b4624f379dab24d3725ffde76559cff63d9ec94e1736b556dacdfebe5ab6d4b"}, - {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:213c60cd50106436cc818accf5baa1aba61c0189ff610f64f4a3e8c6726218ba"}, - {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fa600030013c4de8165339db93d182b9431076eb98eb40ee068700c9c813e34"}, - {file = "PyYAML-6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:277a0ef2981ca40581a47093e9e2d13b3f1fbbeffae064c1d21bfceba2030287"}, - {file = "PyYAML-6.0-cp38-cp38-win32.whl", hash = "sha256:d4eccecf9adf6fbcc6861a38015c2a64f38b9d94838ac1810a9023a0609e1b78"}, - {file = "PyYAML-6.0-cp38-cp38-win_amd64.whl", hash = "sha256:1e4747bc279b4f613a09eb64bba2ba602d8a6664c6ce6396a4d0cd413a50ce07"}, - {file = "PyYAML-6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:055d937d65826939cb044fc8c9b08889e8c743fdc6a32b33e2390f66013e449b"}, - {file = "PyYAML-6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e61ceaab6f49fb8bdfaa0f92c4b57bcfbea54c09277b1b4f7ac376bfb7a7c174"}, - {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d67d839ede4ed1b28a4e8909735fc992a923cdb84e618544973d7dfc71540803"}, - {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cba8c411ef271aa037d7357a2bc8f9ee8b58b9965831d9e51baf703280dc73d3"}, - {file = "PyYAML-6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:40527857252b61eacd1d9af500c3337ba8deb8fc298940291486c465c8b46ec0"}, - {file = "PyYAML-6.0-cp39-cp39-win32.whl", hash = "sha256:b5b9eccad747aabaaffbc6064800670f0c297e52c12754eb1d976c57e4f74dcb"}, - {file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"}, - {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"}, -] requests = [ {file = "requests-2.27.1-py2.py3-none-any.whl", hash = "sha256:f22fa1e554c9ddfd16e6e41ac79759e17be9e492b3587efa038054674760e72d"}, {file = "requests-2.27.1.tar.gz", hash = "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61"}, ] -saneyaml = [ - {file = "saneyaml-0.5.2-py3-none-any.whl", hash = "sha256:e54ed827973647ee9be8e8c091536b55ad22b3f9b1296e36701a3544822e7eac"}, - {file = "saneyaml-0.5.2.tar.gz", hash = "sha256:d6074f1959041342ab41d74a6f904720ffbcf63c94467858e0e22e17e3c43d41"}, -] sgmllib3k = [ {file = "sgmllib3k-1.0.0.tar.gz", hash = "sha256:7868fb1c8bfa764c1ac563d3cf369c381d1325d36124933a726f29fcdaa812e9"}, ] diff --git a/pyproject.toml b/pyproject.toml index 1a3fdcf..20ba70a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -16,7 +16,6 @@ peertube = {git = "https://framagit.org/framasoft/peertube/clients/python.git"} feedparser = "^6.0.8" bs4 = "^0.0.1" "Mastodon.py" = "^1.5.1" -saneyaml = "^0.5.2" [tool.poetry.dev-dependencies] poetry2setup = "^1.0.0" -- 2.49.0 From f6a1a684c0f974c5f9889a98a6d595b16ba1a1d5 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Wed, 13 Apr 2022 12:48:20 +0200 Subject: [PATCH 23/48] Revert "fix: don't escape some characters" This reverts commit cf8b1ff7e98209d9e75c4a201bd57270edee70b4. --- lumbunglib/feed.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 6c04da5..b2f30df 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -14,7 +14,7 @@ from bs4 import BeautifulSoup from slugify import slugify from re import compile as re_compile from re import sub -yamlre = re_compile('[_\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') +yamlre = re_compile('[_\?:\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') def write_etag(feed_name, feed_data): -- 2.49.0 From 7d3863641dcb82859f9e99a43d96d41feee24b29 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Wed, 13 Apr 2022 12:48:42 +0200 Subject: [PATCH 24/48] Revert "feat: sanitize all yaml" This reverts commit 2fbc952a72c8de97a1b7782bc7076fc9b75e50de. --- lumbunglib/feed.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index b2f30df..8c2bba0 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -5,6 +5,7 @@ from hashlib import md5 from ast import literal_eval as make_tuple from pathlib import Path from urllib.parse import urlparse +from re import sub import arrow import feedparser @@ -13,8 +14,7 @@ import requests from bs4 import BeautifulSoup from slugify import slugify from re import compile as re_compile -from re import sub -yamlre = re_compile('[_\?:\'\[\]\{\}\#\&\*\!\|\>\`\"\%]') +yamlre = re_compile('"') def write_etag(feed_name, feed_data): @@ -121,12 +121,12 @@ def sanitize_yaml (frontmatter): #some fields are lists l = [] for i in v: - i = yamlre.sub(r'\\\g<0>', i) + i = yamlre.sub('\\"', i) l.append(i) frontmatter[k] = l else: - v = yamlre.sub(r'\\\g<0>', v) + v = yamlre.sub('\\"', v) frontmatter[k] = v return frontmatter -- 2.49.0 From 3ea798b301a88239db7c94c2cef0e7e4927b52ed Mon Sep 17 00:00:00 2001 From: knoflook Date: Thu, 21 Apr 2022 14:17:12 +0200 Subject: [PATCH 25/48] feed: assign pen category --- lumbunglib/feed.py | 14 ++++++++++---- lumbunglib/templates/feed.md | 2 +- 2 files changed, 11 insertions(+), 5 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 8c2bba0..1e25fdc 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -85,6 +85,10 @@ def create_frontmatter(entry): for t in entry.tags: tags.append(t['term']) + card_type = "network" + if entry.feed_name == "pen.lumbung.space": + card_type = "pen" + if "opds" in entry: frontmatter = { 'title':entry.title, @@ -105,7 +109,8 @@ def create_frontmatter(entry): 'author': author, 'original_link': entry.link, 'feed_name': entry['feed_name'], - 'tags': str(tags) + 'tags': str(tags), + 'card_type': card_type } return frontmatter @@ -196,9 +201,10 @@ def parse_posts(post_dir, post_content): allowed_iframe_sources = ["youtube.com", "vimeo.com", "tv.lumbung.space"] for img in soup(["img", "object"]): - local_image = grab_media(post_dir, img["src"]) - if img["src"] != local_image: - img["src"] = local_image + if img.get("src") != None: + local_image = grab_media(post_dir, img["src"]) + if img["src"] != local_image: + img["src"] = local_image for iframe in soup(["iframe"]): if not any(source in iframe["src"] for source in allowed_iframe_sources): diff --git a/lumbunglib/templates/feed.md b/lumbunglib/templates/feed.md index 74ddc3a..ddef11d 100644 --- a/lumbunglib/templates/feed.md +++ b/lumbunglib/templates/feed.md @@ -6,7 +6,7 @@ summary: "{{ frontmatter.summary }}" author: "{{ frontmatter.author }}" original_link: "{{ frontmatter.original_link }}" feed_name: "{{ frontmatter.feed_name}}" -categories: ["network", "{{ frontmatter.feed_name}}"] +categories: ["{{ frontmatter.card_type }}", "{{ frontmatter.feed_name}}"] tags: {{ frontmatter.tags }} --- -- 2.49.0 From ce3bfc58b0fdc476249671140285e54ca15427d1 Mon Sep 17 00:00:00 2001 From: rra Date: Thu, 3 Mar 2022 07:00:09 +0100 Subject: [PATCH 26/48] remove orphaned " --- lumbunglib/templates/hashtag.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/lumbunglib/templates/hashtag.md b/lumbunglib/templates/hashtag.md index 786ff6b..49e2fea 100644 --- a/lumbunglib/templates/hashtag.md +++ b/lumbunglib/templates/hashtag.md @@ -1,12 +1,12 @@ --- -date: "{{ post_metadata.created_at }}" #2021-06-10T10:46:33+02:00 +date: {{ post_metadata.created_at }} #2021-06-10T10:46:33+02:00 draft: false -author: "{{ post_metadata.account.display_name }}" -avatar: "{{ post_metadata.account.avatar }}" +author: {{ post_metadata.account.display_name }} +avatar: {{ post_metadata.account.avatar }} categories: ["shouts"] -images: [{% for i in post_metadata.media_attachments %} "{{ i.url }}", {% endfor %}] -title: "{{ post_metadata.account.display_name }}" -tags: [{% for i in post_metadata.tags %} "{{ i.name }}", {% endfor %}] +images: [{% for i in post_metadata.media_attachments %} {{ i.url }}, {% endfor %}] +title: {{ post_metadata.account.display_name }} +tags: [{% for i in post_metadata.tags %} {{ i.name }} {% endfor %}] --- {% for item in post_metadata.media_attachments %} -- 2.49.0 From 3b390d1ecbb60a8a5ed7c91efb4328d88503c50f Mon Sep 17 00:00:00 2001 From: rra Date: Tue, 24 May 2022 08:42:56 +0200 Subject: [PATCH 27/48] change template to authors to accomodate author taxonomy --- lumbunglib/templates/feed.md | 2 +- lumbunglib/templates/hashtag.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/lumbunglib/templates/feed.md b/lumbunglib/templates/feed.md index ddef11d..f744bff 100644 --- a/lumbunglib/templates/feed.md +++ b/lumbunglib/templates/feed.md @@ -3,7 +3,7 @@ title: "{{ frontmatter.title }}" date: "{{ frontmatter.date }}" #2021-06-10T10:46:33+02:00 draft: false summary: "{{ frontmatter.summary }}" -author: "{{ frontmatter.author }}" +authors: ["{{ frontmatter.author }}"] original_link: "{{ frontmatter.original_link }}" feed_name: "{{ frontmatter.feed_name}}" categories: ["{{ frontmatter.card_type }}", "{{ frontmatter.feed_name}}"] diff --git a/lumbunglib/templates/hashtag.md b/lumbunglib/templates/hashtag.md index 49e2fea..bdcacba 100644 --- a/lumbunglib/templates/hashtag.md +++ b/lumbunglib/templates/hashtag.md @@ -1,7 +1,7 @@ --- date: {{ post_metadata.created_at }} #2021-06-10T10:46:33+02:00 draft: false -author: {{ post_metadata.account.display_name }} +authors: ["{{ post_metadata.account.display_name }}"] avatar: {{ post_metadata.account.avatar }} categories: ["shouts"] images: [{% for i in post_metadata.media_attachments %} {{ i.url }}, {% endfor %}] -- 2.49.0 From 6e64d6477295dcb41cf04fcd6675476353f3f160 Mon Sep 17 00:00:00 2001 From: rra Date: Tue, 24 May 2022 10:00:58 +0200 Subject: [PATCH 28/48] only return an author if there is one --- lumbunglib/templates/feed.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lumbunglib/templates/feed.md b/lumbunglib/templates/feed.md index f744bff..d9f3f9a 100644 --- a/lumbunglib/templates/feed.md +++ b/lumbunglib/templates/feed.md @@ -3,7 +3,7 @@ title: "{{ frontmatter.title }}" date: "{{ frontmatter.date }}" #2021-06-10T10:46:33+02:00 draft: false summary: "{{ frontmatter.summary }}" -authors: ["{{ frontmatter.author }}"] +authors: {% if frontmatter.author %} ["{{ frontmatter.author }}"] {% endif %} original_link: "{{ frontmatter.original_link }}" feed_name: "{{ frontmatter.feed_name}}" categories: ["{{ frontmatter.card_type }}", "{{ frontmatter.feed_name}}"] -- 2.49.0 From fecf5cd64e669fec8f488d92baadf404661d029e Mon Sep 17 00:00:00 2001 From: rra Date: Tue, 24 May 2022 15:39:11 +0200 Subject: [PATCH 29/48] add rudimentary support for enclosures & featured images --- lumbunglib/feed.py | 28 +++++++++++++++++++++++++++- lumbunglib/templates/feed.md | 1 + 2 files changed, 28 insertions(+), 1 deletion(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 1e25fdc..4113e52 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -85,6 +85,11 @@ def create_frontmatter(entry): for t in entry.tags: tags.append(t['term']) + if "featured_image" in entry: + featured_image = entry.featured_image + else: + featured_image = '' + card_type = "network" if entry.feed_name == "pen.lumbung.space": card_type = "pen" @@ -110,7 +115,8 @@ def create_frontmatter(entry): 'original_link': entry.link, 'feed_name': entry['feed_name'], 'tags': str(tags), - 'card_type': card_type + 'card_type': card_type, + 'featured_image': featured_image } return frontmatter @@ -136,11 +142,30 @@ def sanitize_yaml (frontmatter): return frontmatter +def parse_enclosures(post_dir, entry): + """ + Parses feed enclosures which are featured media + Can be featured image but also podcast entries + https://pythonhosted.org/feedparser/reference-entry-enclosures.html + """ + #TODO parse more than images + #TODO handle the fact it could be multiple items + + for e in entry.enclosures: + print("found enclosed media", e.type) + if "image/" in e.type: + featured_image = grab_media(post_dir, e.href) + entry["featured_image"] = featured_image + return entry + def create_post(post_dir, entry): """ write hugo post based on RSS entry """ + if "enclosures" in entry: + entry = parse_enclosures(post_dir, entry) + frontmatter = create_frontmatter(entry) if not os.path.exists(post_dir): @@ -202,6 +227,7 @@ def parse_posts(post_dir, post_content): for img in soup(["img", "object"]): if img.get("src") != None: + local_image = grab_media(post_dir, img["src"]) if img["src"] != local_image: img["src"] = local_image diff --git a/lumbunglib/templates/feed.md b/lumbunglib/templates/feed.md index d9f3f9a..71d984b 100644 --- a/lumbunglib/templates/feed.md +++ b/lumbunglib/templates/feed.md @@ -8,6 +8,7 @@ original_link: "{{ frontmatter.original_link }}" feed_name: "{{ frontmatter.feed_name}}" categories: ["{{ frontmatter.card_type }}", "{{ frontmatter.feed_name}}"] tags: {{ frontmatter.tags }} +{% if frontmatter.featured_image %}featured_image: "{{frontmatter.featured_image}}"{% endif %} --- {{ content }} -- 2.49.0 From c84a9758871766897b08b9f6ae2eae536bc26a26 Mon Sep 17 00:00:00 2001 From: rra Date: Sun, 29 May 2022 12:30:55 +0200 Subject: [PATCH 30/48] add reason for failure --- lumbunglib/feed.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index 4113e52..a78c032 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -206,6 +206,9 @@ def grab_media(post_directory, url, prefered_name=None): shutil.copyfileobj(response.raw, media_file) print('Downloaded media item', media_item) return media_item + else: + print("Download failed", response.status_code) + return url return media_item elif os.path.exists(os.path.join(post_directory, media_item)): return media_item @@ -227,7 +230,6 @@ def parse_posts(post_dir, post_content): for img in soup(["img", "object"]): if img.get("src") != None: - local_image = grab_media(post_dir, img["src"]) if img["src"] != local_image: img["src"] = local_image -- 2.49.0 From cab36c8ac63acd7ceadcfcf8856cf2f3607bf8ed Mon Sep 17 00:00:00 2001 From: rra Date: Sun, 29 May 2022 14:45:11 +0200 Subject: [PATCH 31/48] add less generic headers --- lumbunglib/feed.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index a78c032..f5a8d42 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -194,13 +194,17 @@ def grab_media(post_directory, url, prefered_name=None): """ media_item = urlparse(url).path.split('/')[-1] + headers = { + 'User-Agent': 'https://git.autonomic.zone/ruangrupa/lumbunglib', + 'From': 'info@lumbung.space' # This is another valid field + } if prefered_name: media_item = prefered_name try: if not os.path.exists(os.path.join(post_directory, media_item)): #TODO: stream is true is a conditional so we could check the headers for things, mimetype etc - response = requests.get(url, stream=True) + response = requests.get(url, headers=headers, stream=True) if response.ok: with open(os.path.join(post_directory, media_item), 'wb') as media_file: shutil.copyfileobj(response.raw, media_file) -- 2.49.0 From ad591ea9cf89d896a53fdc3b649f0b45f9371c00 Mon Sep 17 00:00:00 2001 From: rra Date: Wed, 1 Jun 2022 05:51:25 +0200 Subject: [PATCH 32/48] add more checks for failures --- lumbunglib/feed.py | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/lumbunglib/feed.py b/lumbunglib/feed.py index f5a8d42..f51d3e9 100644 --- a/lumbunglib/feed.py +++ b/lumbunglib/feed.py @@ -152,10 +152,13 @@ def parse_enclosures(post_dir, entry): #TODO handle the fact it could be multiple items for e in entry.enclosures: - print("found enclosed media", e.type) - if "image/" in e.type: - featured_image = grab_media(post_dir, e.href) - entry["featured_image"] = featured_image + if "type" in e: + print("found enclosed media", e.type) + if "image/" in e.type: + featured_image = grab_media(post_dir, e.href) + entry["featured_image"] = featured_image + else: + print("FIXME:ignoring enclosed", e.type) return entry @@ -267,11 +270,12 @@ def grab_feed(feed_url): print(e) return False - print(data.status, feed_url) - if data.status == 200: - # 304 means the feed has not been modified since we last checked - write_etag(feed_name, data) - return data + if "status" in data: + print(data.status, feed_url) + if data.status == 200: + # 304 means the feed has not been modified since we last checked + write_etag(feed_name, data) + return data return False def create_opds_post(post_dir, entry): -- 2.49.0 From b0f77831bd10be9566a95cee889a3c8061295a6e Mon Sep 17 00:00:00 2001 From: rra Date: Thu, 2 Jun 2022 06:45:54 +0200 Subject: [PATCH 33/48] add 'contributors' as metadata category --- lumbunglib/templates/feed.md | 1 + lumbunglib/templates/hashtag.md | 3 ++- lumbunglib/templates/video.md | 1 + 3 files changed, 4 insertions(+), 1 deletion(-) diff --git a/lumbunglib/templates/feed.md b/lumbunglib/templates/feed.md index 71d984b..29d8e91 100644 --- a/lumbunglib/templates/feed.md +++ b/lumbunglib/templates/feed.md @@ -7,6 +7,7 @@ authors: {% if frontmatter.author %} ["{{ frontmatter.author }}"] {% endif %} original_link: "{{ frontmatter.original_link }}" feed_name: "{{ frontmatter.feed_name}}" categories: ["{{ frontmatter.card_type }}", "{{ frontmatter.feed_name}}"] +contributors: ["{{ frontmatter.feed_name}}"] tags: {{ frontmatter.tags }} {% if frontmatter.featured_image %}featured_image: "{{frontmatter.featured_image}}"{% endif %} --- diff --git a/lumbunglib/templates/hashtag.md b/lumbunglib/templates/hashtag.md index bdcacba..4a61a7a 100644 --- a/lumbunglib/templates/hashtag.md +++ b/lumbunglib/templates/hashtag.md @@ -2,11 +2,12 @@ date: {{ post_metadata.created_at }} #2021-06-10T10:46:33+02:00 draft: false authors: ["{{ post_metadata.account.display_name }}"] +contributors: ["{{ post_metadata.account.acct}}"] avatar: {{ post_metadata.account.avatar }} categories: ["shouts"] images: [{% for i in post_metadata.media_attachments %} {{ i.url }}, {% endfor %}] title: {{ post_metadata.account.display_name }} -tags: [{% for i in post_metadata.tags %} {{ i.name }} {% endfor %}] +tags: [{% for i in post_metadata.tags %} "{{ i.name }}", {% endfor %}] --- {% for item in post_metadata.media_attachments %} diff --git a/lumbunglib/templates/video.md b/lumbunglib/templates/video.md index 96761ec..076a1bf 100644 --- a/lumbunglib/templates/video.md +++ b/lumbunglib/templates/video.md @@ -6,6 +6,7 @@ uuid: "{{v.uuid}}" video_duration: "{{ v.duration | duration }} " video_channel: "{{ v.channel.display_name }}" channel_url: "{{ v.channel.url }}" +contributors: ["{{ v.account.display_name }}"] preview_image: "{{ preview_image }}" images: ["./{{ preview_image }}"] categories: ["tv","{{ v.channel.display_name }}"] -- 2.49.0 From 00f795f16de4018632109b6e1415f95afe9d3e75 Mon Sep 17 00:00:00 2001 From: rra Date: Thu, 2 Jun 2022 09:23:58 +0200 Subject: [PATCH 34/48] rename project to konfluks for legibility, add docs --- README.md | 54 ++++++++++++++++++- docs/konfluks.svg | 31 +++++++++++ {lumbunglib => konfluks}/cloudcal.py | 0 {lumbunglib => konfluks}/feed.py | 0 {lumbunglib => konfluks}/hashtag.py | 0 .../templates/calendar.md | 0 {lumbunglib => konfluks}/templates/feed.md | 0 {lumbunglib => konfluks}/templates/hashtag.md | 0 {lumbunglib => konfluks}/templates/video.md | 0 {lumbunglib => konfluks}/video.py | 0 pyproject.toml | 12 ++--- setup.py | 14 ++--- 12 files changed, 96 insertions(+), 15 deletions(-) create mode 100644 docs/konfluks.svg rename {lumbunglib => konfluks}/cloudcal.py (100%) rename {lumbunglib => konfluks}/feed.py (100%) rename {lumbunglib => konfluks}/hashtag.py (100%) rename {lumbunglib => konfluks}/templates/calendar.md (100%) rename {lumbunglib => konfluks}/templates/feed.md (100%) rename {lumbunglib => konfluks}/templates/hashtag.md (100%) rename {lumbunglib => konfluks}/templates/video.md (100%) rename {lumbunglib => konfluks}/video.py (100%) diff --git a/README.md b/README.md index 3deeeb2..85a1be8 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,56 @@ -# lumbunglib +![Konfluks logo is a stylized and schematic representation of a drainage basin](docs/Konfluks.svg) + +# Konfluks + +A drainage basin is a geographical feature that collects all precipitation in an area, first in to smaller streams and finally together in to the large river. Similarly, Konfluks can bring together small and dispersed streams of web content from different applications and websites together in a single large stream. + +Specifically, Konfluks turns Peertube videos, iCal calendar events, other websites through their RSS and OPDS feeds and Mastodon posts under a hashtag in to Hugo page bundles. This allows one to publish from diverse sources to a single stream. + +Konfluks was first made by Roel Roscam Abbing as part of , together with ruangrupa and Autonomic. + +## Philosophy + +Konfluks tries to act as a mirror representation of the input sources. That means that whenever something remote is deleted, changed or becomes unavailable, it is also changed or deleted by Konfluks. + +Konfluks tries to preserve intention. That means the above, but also by requiring explicit ways of publishing. + +Konfluks works by periodically polling the remote sources, taking care not to duplicate work. It caches files, asks for last-modified headers, and skips things it has already. This makes every poll as fast and as light as possible. + +Konfluks is written for clarity, not brevity nor cleverness. + +Konfluks is extendable, a work in progress and a messy undertaking. + +## High-level overview + +Konfluks consists of different Python scripts which each poll a particular service, say, a Peertube server, to download information and convert it in to [Hugo Page Bundles](https://gohugo.io/content-management/page-bundles/) + +Each script part of Konfluks will essentially to the following: + * Parse a source and request posts/updates/videos/a feed + * Taking care of publish ques + * Create a Hugo post for each item returned, by: + * Making a folder per post in the `output` directory + * Formatting post metadata as [Hugo Post Frontmatter](https://gohugo.io/content-management/front-matter/) in a file called `index.md` + * Grabbing local copies of media and saving them in the post folder + * Adding the post content to `index.md` + * According to jinja2 templates (see `Konfluks/templates/`) + +The page bundles created, where possible, are given human friendly names. + + +Here is a typical output structure: +`user@server: ~/Konfluks/output: tree tv/ +tv/ +├── forum-27an-mother-earth-353f93f3-5fee-49d6-b71d-8aef753f7041 +│   ├── 86ccae63-3df9-443c-91f3-edce146055db.jpg +│   └── index.md +├── keroncong-tugu-cafrinho-live-at-ruru-gallery-ruangrupa-jakarta-19-august-2014-e6d5bb2a-d77f-4a00-a449-992a579c8c0d +│   ├── 32291aa2-a391-4219-a413-87521ff373ba.jpg +│   └── index.md +├── lecture-series-1-camp-notes-on-education-8d54d3c9-0322-42af-ab6e-e954d251e076 +│   ├── 0f3c835b-42c2-48a3-a2a3-a75ddac8688a.jpg +│   └── index.md +` -> Python lib which powers `lumbung.space` automation ## hacking diff --git a/docs/konfluks.svg b/docs/konfluks.svg new file mode 100644 index 0000000..1a91ef3 --- /dev/null +++ b/docs/konfluks.svg @@ -0,0 +1,31 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/lumbunglib/cloudcal.py b/konfluks/cloudcal.py similarity index 100% rename from lumbunglib/cloudcal.py rename to konfluks/cloudcal.py diff --git a/lumbunglib/feed.py b/konfluks/feed.py similarity index 100% rename from lumbunglib/feed.py rename to konfluks/feed.py diff --git a/lumbunglib/hashtag.py b/konfluks/hashtag.py similarity index 100% rename from lumbunglib/hashtag.py rename to konfluks/hashtag.py diff --git a/lumbunglib/templates/calendar.md b/konfluks/templates/calendar.md similarity index 100% rename from lumbunglib/templates/calendar.md rename to konfluks/templates/calendar.md diff --git a/lumbunglib/templates/feed.md b/konfluks/templates/feed.md similarity index 100% rename from lumbunglib/templates/feed.md rename to konfluks/templates/feed.md diff --git a/lumbunglib/templates/hashtag.md b/konfluks/templates/hashtag.md similarity index 100% rename from lumbunglib/templates/hashtag.md rename to konfluks/templates/hashtag.md diff --git a/lumbunglib/templates/video.md b/konfluks/templates/video.md similarity index 100% rename from lumbunglib/templates/video.md rename to konfluks/templates/video.md diff --git a/lumbunglib/video.py b/konfluks/video.py similarity index 100% rename from lumbunglib/video.py rename to konfluks/video.py diff --git a/pyproject.toml b/pyproject.toml index 20ba70a..c94fcf0 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,9 +1,9 @@ [tool.poetry] -name = "lumbunglib" +name = "konfluks" version = "0.1.0" description = "Python lib which powers lumbung[dot]space automation" authors = ["rra", "decentral1se"] -license = "GPLv3+" +license = "AGPLv3+" [tool.poetry.dependencies] python = "^3.9" @@ -25,7 +25,7 @@ requires = ["poetry-core>=1.0.0"] build-backend = "poetry.core.masonry.api" [tool.poetry.scripts] -lumbunglib-cal = "lumbunglib.cloudcal:main" -lumbunglib-vid = "lumbunglib.video:main" -lumbunglib-feed = "lumbunglib.feed:main" -lumbunglib-hash = "lumbunglib.hashtag:main" +konfluks-cal = "konfluks.cloudcal:main" +konfluks-vid = "konfluks.video:main" +konfluks-feed = "konfluks.feed:main" +konfluks-hash = "konfluks.hashtag:main" diff --git a/setup.py b/setup.py index e1e1af7..34c0444 100644 --- a/setup.py +++ b/setup.py @@ -2,10 +2,10 @@ from setuptools import setup packages = \ -['lumbunglib'] +['konfluks'] package_data = \ -{'': ['*'], 'lumbunglib': ['templates/*']} +{'': ['*'], 'konfluks': ['templates/*']} install_requires = \ ['Jinja2>=3.0.3,<4.0.0', @@ -20,13 +20,13 @@ install_requires = \ 'requests>=2.26.0,<3.0.0'] entry_points = \ -{'console_scripts': ['lumbunglib-cal = lumbunglib.cloudcal:main', - 'lumbunglib-feed = lumbunglib.feed:main', - 'lumbunglib-hash = lumbunglib.hashtag:main', - 'lumbunglib-vid = lumbunglib.video:main']} +{'console_scripts': ['konfluks-cal = konfluks.cloudcal:main', + 'konfluks-feed = konfluks.feed:main', + 'konfluks-hash = konfluks.hashtag:main', + 'konfluks-vid = konfluks.video:main']} setup_kwargs = { - 'name': 'lumbunglib', + 'name': 'konfluks', 'version': '0.1.0', 'description': 'Python lib which powers lumbung[dot]space automation', 'long_description': None, -- 2.49.0 From f162bb946a4e8b61f81d3511f7cb3432eb0712db Mon Sep 17 00:00:00 2001 From: rra Date: Thu, 2 Jun 2022 09:28:37 +0200 Subject: [PATCH 35/48] Update 'README.md' correcting markup / styling --- README.md | 46 ++++++++++++++++++++++++---------------------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/README.md b/README.md index 85a1be8..f8b2b2b 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -![Konfluks logo is a stylized and schematic representation of a drainage basin](docs/Konfluks.svg) +![Konfluks logo is a stylized and schematic representation of a drainage basin](https://git.autonomic.zone/r/konfluks/raw/branch/konfluks-renaming/docs/konfluks.svg) # Konfluks @@ -25,34 +25,36 @@ Konfluks is extendable, a work in progress and a messy undertaking. Konfluks consists of different Python scripts which each poll a particular service, say, a Peertube server, to download information and convert it in to [Hugo Page Bundles](https://gohugo.io/content-management/page-bundles/) Each script part of Konfluks will essentially to the following: - * Parse a source and request posts/updates/videos/a feed - * Taking care of publish ques - * Create a Hugo post for each item returned, by: - * Making a folder per post in the `output` directory - * Formatting post metadata as [Hugo Post Frontmatter](https://gohugo.io/content-management/front-matter/) in a file called `index.md` - * Grabbing local copies of media and saving them in the post folder - * Adding the post content to `index.md` - * According to jinja2 templates (see `Konfluks/templates/`) +* Parse a source and request posts/updates/videos/a feed + * Taking care of publish ques +* Create a Hugo post for each item returned, by: + * Making a folder per post in the `output` directory + * Formatting post metadata as [Hugo Post Frontmatter](https://gohugo.io/content-management/front-matter/) in a file called `index.md` + * Grabbing local copies of media and saving them in the post folder + * Adding the post content to `index.md` + * According to jinja2 templates (see `Konfluks/templates/`) The page bundles created, where possible, are given human friendly names. Here is a typical output structure: -`user@server: ~/Konfluks/output: tree tv/ -tv/ -├── forum-27an-mother-earth-353f93f3-5fee-49d6-b71d-8aef753f7041 -│   ├── 86ccae63-3df9-443c-91f3-edce146055db.jpg -│   └── index.md -├── keroncong-tugu-cafrinho-live-at-ruru-gallery-ruangrupa-jakarta-19-august-2014-e6d5bb2a-d77f-4a00-a449-992a579c8c0d -│   ├── 32291aa2-a391-4219-a413-87521ff373ba.jpg -│   └── index.md -├── lecture-series-1-camp-notes-on-education-8d54d3c9-0322-42af-ab6e-e954d251e076 -│   ├── 0f3c835b-42c2-48a3-a2a3-a75ddac8688a.jpg -│   └── index.md -` +``` + user@server: ~/Konfluks/output: tree tv/ + tv/ + ├── forum-27an-mother-earth-353f93f3-5fee-49d6-b71d-8aef753f7041 + │   ├── 86ccae63-3df9-443c-91f3-edce146055db.jpg + │   └── index.md + ├── keroncong-tugu-cafrinho-live-at-ruru-gallery-ruangrupa-jakarta-19-august-2014-e6d5bb2a-d77f-4a00-a449-992a579c8c0d + │   ├── 32291aa2-a391-4219-a413-87521ff373ba.jpg + │   └── index.md + ├── lecture-series-1-camp-notes-on-education-8d54d3c9-0322-42af-ab6e-e954d251e076 + │   ├── 0f3c835b-42c2-48a3-a2a3-a75ddac8688a.jpg + │   └── index.md +``` -## hacking + +## Hacking Install [poetry](https://python-poetry.org/docs/#osx--linux--bashonwindows-install-instructions): -- 2.49.0 From 845a54787b9dc0b0d272b50c78e072aa04e4add6 Mon Sep 17 00:00:00 2001 From: rra Date: Thu, 2 Jun 2022 09:29:20 +0200 Subject: [PATCH 36/48] Update 'README.md' --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f8b2b2b..1af1154 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ A drainage basin is a geographical feature that collects all precipitation in an Specifically, Konfluks turns Peertube videos, iCal calendar events, other websites through their RSS and OPDS feeds and Mastodon posts under a hashtag in to Hugo page bundles. This allows one to publish from diverse sources to a single stream. -Konfluks was first made by Roel Roscam Abbing as part of , together with ruangrupa and Autonomic. +Konfluks was first made by Roel Roscam Abbing as part of [lumbung.space](https://lumbung.space), together with ruangrupa and Autonomic. ## Philosophy -- 2.49.0 From 41bc532ebc2238917633bb19d828507e15e1efdb Mon Sep 17 00:00:00 2001 From: Aadil Ayub Date: Fri, 10 Jun 2022 15:55:17 +0500 Subject: [PATCH 37/48] separate hashtags by comma --- lumbunglib/templates/hashtag.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lumbunglib/templates/hashtag.md b/lumbunglib/templates/hashtag.md index bdcacba..36a9308 100644 --- a/lumbunglib/templates/hashtag.md +++ b/lumbunglib/templates/hashtag.md @@ -6,7 +6,7 @@ avatar: {{ post_metadata.account.avatar }} categories: ["shouts"] images: [{% for i in post_metadata.media_attachments %} {{ i.url }}, {% endfor %}] title: {{ post_metadata.account.display_name }} -tags: [{% for i in post_metadata.tags %} {{ i.name }} {% endfor %}] +tags: [{% for i in post_metadata.tags %} "{{ i.name }}", {% endfor %}] --- {% for item in post_metadata.media_attachments %} -- 2.49.0 From ff76378cdd2657a8820625a71f1c09e398c46ae6 Mon Sep 17 00:00:00 2001 From: Aadil Ayub Date: Tue, 14 Jun 2022 19:27:31 +0500 Subject: [PATCH 38/48] merge christopher's changes pulling the timeline from pen.lumbung.space --- lumbunglib/templates/timeline.md | 14 ++ lumbunglib/timeline.py | 381 +++++++++++++++++++++++++++++++ pyproject.toml | 1 + setup.py | 1 + 4 files changed, 397 insertions(+) create mode 100644 lumbunglib/templates/timeline.md create mode 100644 lumbunglib/timeline.py diff --git a/lumbunglib/templates/timeline.md b/lumbunglib/templates/timeline.md new file mode 100644 index 0000000..0cc9c2b --- /dev/null +++ b/lumbunglib/templates/timeline.md @@ -0,0 +1,14 @@ +--- +title: "{{ frontmatter.title }}" +date: "{{ frontmatter.date }}" #2021-06-10T10:46:33+02:00 +draft: false +summary: "{{ frontmatter.summary }}" +authors: {% if frontmatter.author %} ["{{ frontmatter.author }}"] {% endif %} +original_link: "{{ frontmatter.original_link }}" +feed_name: "{{ frontmatter.feed_name}}" +categories: ["timeline", "{{ frontmatter.feed_name}}"] +timelines: {{ frontmatter.timelines }} +hidden: true +--- + +{{ content }} \ No newline at end of file diff --git a/lumbunglib/timeline.py b/lumbunglib/timeline.py new file mode 100644 index 0000000..d1382de --- /dev/null +++ b/lumbunglib/timeline.py @@ -0,0 +1,381 @@ +import os +import shutil +import time +from hashlib import md5 +from ast import literal_eval as make_tuple +from pathlib import Path +from urllib.parse import urlparse +from re import sub + +import arrow +import feedparser +import jinja2 +import requests +from bs4 import BeautifulSoup +from slugify import slugify +from re import compile as re_compile +yamlre = re_compile('"') + + +def write_etag(feed_name, feed_data): + """ + save timestamp of when feed was last modified + """ + etag = "" + modified = "" + + if "etag" in feed_data: + etag = feed_data.etag + if "modified" in feed_data: + modified = feed_data.modified + + if etag or modified: + with open(os.path.join("etags", feed_name + ".txt"), "w") as f: + f.write(str((etag, modified))) + + +def get_etag(feed_name): + """ + return timestamp of when feed was last modified + """ + fn = os.path.join("etags", feed_name + ".txt") + etag = "" + modified = "" + + if os.path.exists(fn): + etag, modified = make_tuple(open(fn, "r").read()) + + return etag, modified + + +def create_frontmatter(entry): + """ + parse RSS metadata and return as frontmatter + """ + if 'published' in entry: + published = entry.published_parsed + if 'updated' in entry: + published = entry.updated_parsed + + published = arrow.get(published) + + if 'author' in entry: + author = entry.author + else: + author = '' + + if 'authors' in entry: + authors = [] + for a in entry.authors: + authors.append(a['name']) + + if 'summary' in entry: + summary = entry.summary + else: + summary = '' + + if 'publisher' in entry: + publisher = entry.publisher + else: + publisher = '' + + tags = [] + if 'tags' in entry: + #TODO finish categories + for t in entry.tags: + tags.append(t['term']) + + frontmatter = { + 'title':entry.title, + 'date': published.format(), + 'summary': '', + 'author': author, + 'original_link': entry.link, + 'feed_name': entry['feed_name'], + 'timelines': str(tags), + } + + return frontmatter + +def sanitize_yaml (frontmatter): + """ + Escapes any occurences of double quotes + in any of the frontmatter fields + See: https://docs.octoprint.org/en/master/configuration/yaml.html#interesting-data-types + """ + for k, v in frontmatter.items(): + if type(v) == type([]): + #some fields are lists + l = [] + for i in v: + i = yamlre.sub('\\"', i) + l.append(i) + frontmatter[k] = l + + else: + v = yamlre.sub('\\"', v) + frontmatter[k] = v + + return frontmatter + + +def create_post(post_dir, entry): + """ + write hugo post based on RSS entry + """ + frontmatter = create_frontmatter(entry) + + if not os.path.exists(post_dir): + os.makedirs(post_dir) + + if "content" in entry: + post_content = entry.content[0].value + else: + post_content = entry.summary + + parsed_content = parse_posts(post_dir, post_content) + + template_dir = os.path.join(Path(__file__).parent.resolve(), "templates") + env = jinja2.Environment(loader=jinja2.FileSystemLoader(template_dir)) + template = env.get_template("timeline.md") + with open(os.path.join(post_dir, "index.html"), "w") as f: # n.b. .html + post = template.render(frontmatter=sanitize_yaml(frontmatter), content=parsed_content) + f.write(post) + print("created post for", entry.title, "({})".format(entry.link)) + + +def grab_media(post_directory, url, prefered_name=None): + """ + download media linked in post to have local copy + if download succeeds return new local path otherwise return url + """ + media_item = urlparse(url).path.split('/')[-1] + + if prefered_name: + media_item = prefered_name + + try: + if not os.path.exists(os.path.join(post_directory, media_item)): + #TODO: stream is true is a conditional so we could check the headers for things, mimetype etc + response = requests.get(url, stream=True) + if response.ok: + with open(os.path.join(post_directory, media_item), 'wb') as media_file: + shutil.copyfileobj(response.raw, media_file) + print('Downloaded media item', media_item) + return media_item + return media_item + elif os.path.exists(os.path.join(post_directory, media_item)): + return media_item + + except Exception as e: + print('Failed to download image', url) + print(e) + return url + + +def parse_posts(post_dir, post_content): + """ + parse the post content to for media items + replace foreign image with local copy + filter out iframe sources not in allowlist + """ + soup = BeautifulSoup(post_content, "html.parser") + allowed_iframe_sources = ["youtube.com", "vimeo.com", "tv.lumbung.space"] + + for img in soup(["img", "object"]): + if img.get("src") != None: + local_image = grab_media(post_dir, img["src"]) + if img["src"] != local_image: + img["src"] = local_image + + for iframe in soup(["iframe"]): + if not any(source in iframe["src"] for source in allowed_iframe_sources): + print("filtered iframe: {}...".format(iframe["src"][:25])) + iframe.decompose() + return soup.decode() + + +def grab_feed(feed_url): + """ + check whether feed has been updated + download & return it if it has + """ + feed_name = urlparse(feed_url).netloc + + etag, modified = get_etag(feed_name) + + try: + if modified: + data = feedparser.parse(feed_url, modified=modified) + elif etag: + data = feedparser.parse(feed_url, etag=etag) + else: + data = feedparser.parse(feed_url) + except Exception as e: + print("Error grabbing feed") + print(feed_name) + print(e) + return False + + print(data.status, feed_url) + if data.status == 200: + # 304 means the feed has not been modified since we last checked + write_etag(feed_name, data) + return data + return False + +def create_opds_post(post_dir, entry): + """ + create a HUGO post based on OPDS entry + or update it if the timestamp is newer + Downloads the cover & file + """ + + frontmatter = create_frontmatter(entry) + + template_dir = os.path.join(Path(__file__).parent.resolve(), "templates") + env = jinja2.Environment(loader=jinja2.FileSystemLoader(template_dir)) + template = env.get_template("feed.md") + + if not os.path.exists(post_dir): + os.makedirs(post_dir) + + if os.path.exists(os.path.join(post_dir, '.timestamp')): + old_timestamp = open(os.path.join(post_dir, '.timestamp')).read() + old_timestamp = arrow.get(float(old_timestamp)) + current_timestamp = arrow.get(entry['updated_parsed']) + + if current_timestamp > old_timestamp: + pass + else: + print('Book "{}..." already up to date'.format(entry['title'][:32])) + return + + for item in entry.links: + ft = item['type'].split('/')[-1] + fn = item['rel'].split('/')[-1] + + if fn == "acquisition": + fn = "publication" #calling the publications acquisition is weird + + prefered_name = "{}-{}.{}".format(fn, slugify(entry['title']), ft) + + grab_media(post_dir, item['href'], prefered_name) + + if "summary" in entry: + summary = entry.summary + else: + summary = "" + + with open(os.path.join(post_dir,'index.md'),'w') as f: + post = template.render(frontmatter=sanitize_yaml(frontmatter), content=summary) + f.write(post) + print('created post for Book', entry.title) + + with open(os.path.join(post_dir, '.timestamp'), 'w') as f: + timestamp = arrow.get(entry['updated_parsed']) + f.write(timestamp.format('X')) + + +def main(): + feed_urls = open("feeds_list_timeline.txt", "r").read().splitlines() + + start = time.time() + + if not os.path.exists("etags"): + os.mkdir("etags") + + output_dir = os.environ.get("OUTPUT_DIR") + + if not os.path.exists(output_dir): + os.makedirs(output_dir) + + feed_dict = dict() + for url in feed_urls: + feed_name = urlparse(url).netloc + feed_dict[url] = feed_name + + feed_names = feed_dict.values() + content_dirs = os.listdir(output_dir) + for i in content_dirs: + if i not in feed_names: + shutil.rmtree(os.path.join(output_dir, i)) + print("%s not in feeds_list.txt, removing local data" %(i)) + + # add iframe to the allowlist of feedparser's sanitizer, + # this is now handled in parse_post() + feedparser.sanitizer._HTMLSanitizer.acceptable_elements |= {"iframe"} + + for feed_url in feed_urls: + + feed_name = feed_dict[feed_url] + + feed_dir = os.path.join(output_dir, feed_name) + + if not os.path.exists(feed_dir): + os.makedirs(feed_dir) + + existing_posts = os.listdir(feed_dir) + + data = grab_feed(feed_url) + + if data: + + opds_feed = False + for i in data.feed['links']: + if i['rel'] == 'self': + if 'opds' in i['type']: + opds_feed = True + print("OPDS type feed!") + + + for entry in data.entries: + # if 'tags' in entry: + # for tag in entry.tags: + # for x in ['lumbung.space', 'D15', 'lumbung']: + # if x in tag['term']: + # print(entry.title) + entry["feed_name"] = feed_name + + post_name = slugify(entry.title) + + # pixelfed returns the whole post text as the post name. max + # filename length is 255 on many systems. here we're shortening + # the name and adding a hash to it to avoid a conflict in a + # situation where 2 posts start with exactly the same text. + if len(post_name) > 150: + post_hash = md5(bytes(post_name, "utf-8")) + post_name = post_name[:150] + "-" + post_hash.hexdigest() + + if opds_feed: + entry['opds'] = True + #format: Beyond-Debiasing-Report_Online-75535a4886e3 + post_name = slugify(entry['title'])+'-'+entry['id'].split('-')[-1] + + post_dir = os.path.join(output_dir, feed_name, post_name) + + if post_name not in existing_posts: + # if there is a blog entry we dont already have, make it + if opds_feed: + create_opds_post(post_dir, entry) + else: + create_post(post_dir, entry) + + elif post_name in existing_posts: + # if we already have it, update it + if opds_feed: + create_opds_post(post_dir, entry) + else: + create_post(post_dir, entry) + existing_posts.remove( + post_name + ) # create list of posts which have not been returned by the feed + + for post in existing_posts: + # remove blog posts no longer returned by the RSS feed + print("deleted", post) + shutil.rmtree(os.path.join(feed_dir, slugify(post))) + + end = time.time() + + print(end - start) diff --git a/pyproject.toml b/pyproject.toml index 20ba70a..75e14df 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -28,4 +28,5 @@ build-backend = "poetry.core.masonry.api" lumbunglib-cal = "lumbunglib.cloudcal:main" lumbunglib-vid = "lumbunglib.video:main" lumbunglib-feed = "lumbunglib.feed:main" +lumbunglib-timeline = "lumbunglib.timeline:main" lumbunglib-hash = "lumbunglib.hashtag:main" diff --git a/setup.py b/setup.py index e1e1af7..9aae1b7 100644 --- a/setup.py +++ b/setup.py @@ -22,6 +22,7 @@ install_requires = \ entry_points = \ {'console_scripts': ['lumbunglib-cal = lumbunglib.cloudcal:main', 'lumbunglib-feed = lumbunglib.feed:main', + 'lumbunglib-timeline = lumbunglib.timeline:main', 'lumbunglib-hash = lumbunglib.hashtag:main', 'lumbunglib-vid = lumbunglib.video:main']} -- 2.49.0 From e66e3202dae46fbbc65688ea33e9fdcf9586afd1 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Tue, 21 Jun 2022 00:00:32 +0200 Subject: [PATCH 39/48] add new hashtag --- lumbunglib/hashtag.py | 1 + 1 file changed, 1 insertion(+) diff --git a/lumbunglib/hashtag.py b/lumbunglib/hashtag.py index baf21c9..ff29707 100644 --- a/lumbunglib/hashtag.py +++ b/lumbunglib/hashtag.py @@ -23,6 +23,7 @@ hashtags = [ "ruruhaus", "offbeatentrack_kassel", "lumbungofpublishers", + "lumbungkiosproducts", ] -- 2.49.0 From 6020db4d15a881dfdd07b52f3298f1d072bd6b79 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Mon, 18 Jul 2022 12:16:52 +0200 Subject: [PATCH 40/48] additional gardening for konfluks rename --- README.md | 41 ++++++++++---------------- docs/konfluks.svg => konfluks.svg | 0 konfluks/{cloudcal.py => calendars.py} | 0 pyproject.toml | 6 ++-- setup.py | 2 +- 5 files changed, 19 insertions(+), 30 deletions(-) rename docs/konfluks.svg => konfluks.svg (100%) rename konfluks/{cloudcal.py => calendars.py} (100%) diff --git a/README.md b/README.md index 1af1154..acb2c2e 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,12 @@ -![Konfluks logo is a stylized and schematic representation of a drainage basin](https://git.autonomic.zone/r/konfluks/raw/branch/konfluks-renaming/docs/konfluks.svg) +![Konfluks logo is a stylized and schematic representation of a drainage basin](./konfluks.svg) # Konfluks -A drainage basin is a geographical feature that collects all precipitation in an area, first in to smaller streams and finally together in to the large river. Similarly, Konfluks can bring together small and dispersed streams of web content from different applications and websites together in a single large stream. +A drainage basin is a geographical feature that collects all precipitation in an area, first in to smaller streams and finally together in to the large river. Similarly, Konfluks can bring together small and dispersed streams of web content from different applications and websites together in a single large stream. -Specifically, Konfluks turns Peertube videos, iCal calendar events, other websites through their RSS and OPDS feeds and Mastodon posts under a hashtag in to Hugo page bundles. This allows one to publish from diverse sources to a single stream. +Specifically, Konfluks turns Peertube videos, iCal calendar events, other websites through their RSS and OPDS feeds and Mastodon posts under a hashtag in to Hugo page bundles. This allows one to publish from diverse sources to a single stream. -Konfluks was first made by Roel Roscam Abbing as part of [lumbung.space](https://lumbung.space), together with ruangrupa and Autonomic. +Konfluks was first made by [Roel Roscam Abbing](https://test.roelof.info/) as part of [lumbung.space](https://lumbung.space), together with [ruangrupa](https://ruangrupa.id) and [Autonomic](https://autonomic.zone). ## Philosophy @@ -22,24 +22,26 @@ Konfluks is extendable, a work in progress and a messy undertaking. ## High-level overview -Konfluks consists of different Python scripts which each poll a particular service, say, a Peertube server, to download information and convert it in to [Hugo Page Bundles](https://gohugo.io/content-management/page-bundles/) +Konfluks consists of different Python scripts which each poll a particular service, say, a [Peertube](https://joinpeertube.org) server, to download information and convert it in to [Hugo Page Bundles](https://gohugo.io/content-management/page-bundles/) Each script part of Konfluks will essentially to the following: + * Parse a source and request posts/updates/videos/a feed * Taking care of publish ques + * Create a Hugo post for each item returned, by: * Making a folder per post in the `output` directory * Formatting post metadata as [Hugo Post Frontmatter](https://gohugo.io/content-management/front-matter/) in a file called `index.md` * Grabbing local copies of media and saving them in the post folder * Adding the post content to `index.md` - * According to jinja2 templates (see `Konfluks/templates/`) + * According to jinja2 templates (see `konfluks/templates/`) The page bundles created, where possible, are given human friendly names. - Here is a typical output structure: + ``` - user@server: ~/Konfluks/output: tree tv/ + user@server: ~/konfluks/output: tree tv/ tv/ ├── forum-27an-mother-earth-353f93f3-5fee-49d6-b71d-8aef753f7041 │   ├── 86ccae63-3df9-443c-91f3-edce146055db.jpg @@ -52,8 +54,6 @@ Here is a typical output structure: │   └── index.md ``` - - ## Hacking Install [poetry](https://python-poetry.org/docs/#osx--linux--bashonwindows-install-instructions): @@ -62,31 +62,20 @@ Install [poetry](https://python-poetry.org/docs/#osx--linux--bashonwindows-insta curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/get-poetry.py | python - ``` -We use Poetry because it locks the dependencies all the way down and makes it -easier to manage installation & maintenance in the long-term. Then install the -dependencies & have them managed by Poetry: +We use Poetry because it locks the dependencies all the way down and makes it easier to manage installation & maintenance in the long-term. Then install the dependencies & have them managed by Poetry: ``` poetry install ``` -Each script requires some environment variables to run, you can see the latest -deployment configuration over -[here](https://git.autonomic.zone/ruangrupa/lumbung.space/src/branch/main/compose.yml), -look for the values under the `environment: ...` stanza. +Each script requires some environment variables to run, you can see the latest deployment configuration over [here](https://git.autonomic.zone/ruangrupa/lumbung.space/src/branch/main/compose.yml), look for the values under the `environment: ...` stanza. -All scripts have an entrypoint described in the -[`pypoetry.toml`](https://git.autonomic.zone/ruangrupa/lumbunglib/src/commit/40bf9416b8792c08683ad8ac878093c7ef1b2f5d/pyproject.toml#L27-L31) -which you can run via `poetry run ...`. For example, if you want to run the -[`lumbunglib/video.py`](./lumbunglib/video.py) script, you'd do: +All scripts have an entrypoint described in the [`pypoetry.toml`](https://git.autonomic.zone/ruangrupa/konfluks/src/commit/40bf9416b8792c08683ad8ac878093c7ef1b2f5d/pyproject.toml#L27-L31) which you can run via `poetry run ...`. For example, if you want to run the [`konfluks/video.py`](./knofluks/video.py) script, you'd do: ``` mkdir -p testdir export OUTPUT_DIR=/testdir -poetry run lumbunglib-vid +poetry run konfluks-vid ``` -Run `poetry run poetry2setup > setup.py` if updating the poetry dependencies. -This allows us to run `pip install .` in the deployment and Pip will understand -that it is just a regular Python package. If adding a new cli command, extend -`pyproject.toml` with a new `[tool.poetry.scripts]` entry. +Run `poetry run poetry2setup > setup.py` if updating the poetry dependencies. This allows us to run `pip install .` in the deployment and Pip will understand that it is just a regular Python package. If adding a new cli command, extend `pyproject.toml` with a new `[tool.poetry.scripts]` entry. diff --git a/docs/konfluks.svg b/konfluks.svg similarity index 100% rename from docs/konfluks.svg rename to konfluks.svg diff --git a/konfluks/cloudcal.py b/konfluks/calendars.py similarity index 100% rename from konfluks/cloudcal.py rename to konfluks/calendars.py diff --git a/pyproject.toml b/pyproject.toml index 33b9ded..14e518a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,8 +1,8 @@ [tool.poetry] name = "konfluks" version = "0.1.0" -description = "Python lib which powers lumbung[dot]space automation" -authors = ["rra", "decentral1se"] +description = "Brings together small and dispersed streams of web content from different applications and websites together in a single large stream." +authors = ["rra", "decentral1se", "knoflook"] license = "AGPLv3+" [tool.poetry.dependencies] @@ -25,7 +25,7 @@ requires = ["poetry-core>=1.0.0"] build-backend = "poetry.core.masonry.api" [tool.poetry.scripts] -konfluks-cal = "konfluks.cloudcal:main" +konfluks-cal = "konfluks.calendars:main" konfluks-vid = "konfluks.video:main" konfluks-feed = "konfluks.feed:main" konfluks-timeline = "konfluks.timeline:main" diff --git a/setup.py b/setup.py index b76bc40..2384fd2 100644 --- a/setup.py +++ b/setup.py @@ -20,7 +20,7 @@ install_requires = \ 'requests>=2.26.0,<3.0.0'] entry_points = \ -{'console_scripts': ['konfluks-cal = konfluks.cloudcal:main', +{'console_scripts': ['konfluks-cal = konfluks.calendars:main', 'konfluks-feed = konfluks.feed:main', 'konfluks-timeline = lumbunglib.timeline:main', 'konfluks-hash = konfluks.hashtag:main', -- 2.49.0 From 98299daa1be35aecfc0fc82da0b6c7a34ba6aa73 Mon Sep 17 00:00:00 2001 From: decentral1se Date: Mon, 18 Jul 2022 12:21:01 +0200 Subject: [PATCH 41/48] fix links --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index acb2c2e..311271d 100644 --- a/README.md +++ b/README.md @@ -70,7 +70,7 @@ poetry install Each script requires some environment variables to run, you can see the latest deployment configuration over [here](https://git.autonomic.zone/ruangrupa/lumbung.space/src/branch/main/compose.yml), look for the values under the `environment: ...` stanza. -All scripts have an entrypoint described in the [`pypoetry.toml`](https://git.autonomic.zone/ruangrupa/konfluks/src/commit/40bf9416b8792c08683ad8ac878093c7ef1b2f5d/pyproject.toml#L27-L31) which you can run via `poetry run ...`. For example, if you want to run the [`konfluks/video.py`](./knofluks/video.py) script, you'd do: +All scripts have an entrypoint described in the [`pypoetry.toml`](./pyproject.toml) which you can run via `poetry run ...`. For example, if you want to run the [`konfluks/video.py`](./konfluks/video.py) script, you'd do: ``` mkdir -p testdir -- 2.49.0 From d21158eb91ebf8c77082c2547a3d0b5262f474b8 Mon Sep 17 00:00:00 2001 From: rra Date: Fri, 9 Sep 2022 13:22:32 +0200 Subject: [PATCH 42/48] add support for videos in posts --- konfluks/hashtag.py | 44 +++++++++++++++++++++++------------ konfluks/templates/hashtag.md | 14 ++++++++++- 2 files changed, 42 insertions(+), 16 deletions(-) diff --git a/konfluks/hashtag.py b/konfluks/hashtag.py index ff29707..39c2a00 100644 --- a/konfluks/hashtag.py +++ b/konfluks/hashtag.py @@ -11,19 +11,19 @@ instance = "https://social.lumbung.space" email = "" password = "" hashtags = [ - "documentafifteen", - "harvestedbyputra", - "jalansesama", - "lumbungdotspace", - "majelisakakbar", - "majelisakbar", - "warungkopi", - "lumbungkios", - "kassel_ecosystem", - "ruruhaus", - "offbeatentrack_kassel", - "lumbungofpublishers", - "lumbungkiosproducts", + "documentafifteen"#, + # "harvestedbyputra", + # "jalansesama", + # "lumbungdotspace", + # "majelisakakbar", + # "majelisakbar", + # "warungkopi", + # "lumbungkios", + # "kassel_ecosystem", + # "ruruhaus", + # "offbeatentrack_kassel", + # "lumbungofpublishers", + # "lumbungkiosproducts", ] @@ -60,6 +60,21 @@ def download_media(post_directory, media_attachments): with open(os.path.join(post_directory, image), "wb") as img_file: shutil.copyfileobj(response.raw, img_file) print("Downloaded cover image", image) + elif item["type"] == "video": + video = localize_media_url(item["url"]) + if not os.path.exists(os.path.join(post_directory, video)): + # download video file + response = requests.get(item["url"], stream=True) + with open(os.path.join(post_directory, video), "wb") as video_file: + shutil.copyfileobj(response.raw, video_file) + print("Downloaded video in post", video) + if not os.path.exists(os.path.join(post_directory, "thumbnail.png")): + #download video preview + response = requests.get(item["preview_url"], stream=True) + with open(os.path.join(post_directory, "thumbnail.png"), "wb") as thumbnail: + shutil.copyfileobj(response.raw, thumbnail) + print("Downloaded thumbnail for", video) + def create_post(post_directory, post_metadata): @@ -78,7 +93,6 @@ def create_post(post_directory, post_metadata): post_metadata["account"]["display_name"] = name env.filters["localize_media_url"] = localize_media_url env.filters["filter_mastodon_urls"] = filter_mastodon_urls - template = env.get_template("hashtag.md") with open(os.path.join(post_directory, "index.html"), "w") as f: @@ -130,7 +144,7 @@ def main(): timeline ) # returns all the rest n.b. can take a while because of rate limit - for post_metadata in timeline: + for post_metadata in timeline[:6]: post_dir = os.path.join(hashtag_dir, str(post_metadata["id"])) # if there is a post in the feed we dont already have locally, make it if str(post_metadata["id"]) not in all_existing_posts: diff --git a/konfluks/templates/hashtag.md b/konfluks/templates/hashtag.md index 4a61a7a..1148b79 100644 --- a/konfluks/templates/hashtag.md +++ b/konfluks/templates/hashtag.md @@ -5,13 +5,25 @@ authors: ["{{ post_metadata.account.display_name }}"] contributors: ["{{ post_metadata.account.acct}}"] avatar: {{ post_metadata.account.avatar }} categories: ["shouts"] -images: [{% for i in post_metadata.media_attachments %} {{ i.url }}, {% endfor %}] title: {{ post_metadata.account.display_name }} tags: [{% for i in post_metadata.tags %} "{{ i.name }}", {% endfor %}] +images: [{% for i in post_metadata.media_attachments %}{% if i.type == "image" %}"{{ i.url | localize_media_url }}", {%endif%}{% endfor %}] +videos: [{% for i in post_metadata.media_attachments %}{% if i.type == "video" %}"{{ i.url | localize_media_url }}", {%endif%}{% endfor %}] --- {% for item in post_metadata.media_attachments %} +{% if item.type == "image" %} {{item.description}} +{% endif %} +{% endfor %} + +{% for item in post_metadata.media_attachments %} +{% if item.type == "video" %} + +{% endif %} {% endfor %} {{ post_metadata.content | filter_mastodon_urls }} -- 2.49.0 From 657ced1ceb7dce8d6a0fe1d7fee0bf33f78b7207 Mon Sep 17 00:00:00 2001 From: rra Date: Fri, 9 Sep 2022 13:27:29 +0200 Subject: [PATCH 43/48] undo dev setup changes --- konfluks/hashtag.py | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/konfluks/hashtag.py b/konfluks/hashtag.py index 39c2a00..baa39ed 100644 --- a/konfluks/hashtag.py +++ b/konfluks/hashtag.py @@ -11,19 +11,19 @@ instance = "https://social.lumbung.space" email = "" password = "" hashtags = [ - "documentafifteen"#, - # "harvestedbyputra", - # "jalansesama", - # "lumbungdotspace", - # "majelisakakbar", - # "majelisakbar", - # "warungkopi", - # "lumbungkios", - # "kassel_ecosystem", - # "ruruhaus", - # "offbeatentrack_kassel", - # "lumbungofpublishers", - # "lumbungkiosproducts", + "documentafifteen", + "harvestedbyputra", + "jalansesama", + "lumbungdotspace", + "majelisakakbar", + "majelisakbar", + "warungkopi", + "lumbungkios", + "kassel_ecosystem", + "ruruhaus", + "offbeatentrack_kassel", + "lumbungofpublishers", + "lumbungkiosproducts", ] @@ -144,7 +144,7 @@ def main(): timeline ) # returns all the rest n.b. can take a while because of rate limit - for post_metadata in timeline[:6]: + for post_metadata in timeline: post_dir = os.path.join(hashtag_dir, str(post_metadata["id"])) # if there is a post in the feed we dont already have locally, make it if str(post_metadata["id"]) not in all_existing_posts: -- 2.49.0 From 0ecc0ecd3ab2307485d7bd31375f50d5dcf8dd8a Mon Sep 17 00:00:00 2001 From: rra Date: Fri, 9 Sep 2022 14:19:19 +0200 Subject: [PATCH 44/48] handle paths and extensions properly, fix #41 --- konfluks/calendars.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/konfluks/calendars.py b/konfluks/calendars.py index 0645e45..6f53656 100644 --- a/konfluks/calendars.py +++ b/konfluks/calendars.py @@ -138,9 +138,9 @@ def create_event_post(post_dir, event): for img in event_metadata["images"]: # parse img url to safe local image name - img_name = img.split("/")[-1] - fn, ext = img_name.split(".") - img_name = slugify(fn) + "." + ext + img_name = os.path.basename(img) + fn, ext = os.path.splitext(img_name) + img_name = slugify(fn) + '.' + ext local_image = os.path.join(post_dir, img_name) -- 2.49.0 From a4f749ebd7383f1aa80722e1b72bd4f405bcd56d Mon Sep 17 00:00:00 2001 From: rra Date: Thu, 15 Sep 2022 18:37:25 +0200 Subject: [PATCH 45/48] adjust templates to new taxonomy --- konfluks/templates/calendar.md | 2 +- konfluks/templates/feed.md | 6 +++--- konfluks/templates/hashtag.md | 4 +--- konfluks/templates/timeline.md | 4 ++-- konfluks/templates/video.md | 2 +- 5 files changed, 8 insertions(+), 10 deletions(-) diff --git a/konfluks/templates/calendar.md b/konfluks/templates/calendar.md index e27acbe..f1072a2 100644 --- a/konfluks/templates/calendar.md +++ b/konfluks/templates/calendar.md @@ -2,7 +2,7 @@ title: "{{ event.name }}" date: "{{ event.begin }}" #2021-06-10T10:46:33+02:00 draft: false -categories: "calendar" +source: "lumbung calendar" event_begin: "{{ event.begin }}" event_end: "{{ event.end }}" duration: "{{ event.duration }}" diff --git a/konfluks/templates/feed.md b/konfluks/templates/feed.md index 29d8e91..54492f1 100644 --- a/konfluks/templates/feed.md +++ b/konfluks/templates/feed.md @@ -3,11 +3,11 @@ title: "{{ frontmatter.title }}" date: "{{ frontmatter.date }}" #2021-06-10T10:46:33+02:00 draft: false summary: "{{ frontmatter.summary }}" -authors: {% if frontmatter.author %} ["{{ frontmatter.author }}"] {% endif %} +contributors: {% if frontmatter.author %} ["{{ frontmatter.author }}"] {% endif %} original_link: "{{ frontmatter.original_link }}" feed_name: "{{ frontmatter.feed_name}}" -categories: ["{{ frontmatter.card_type }}", "{{ frontmatter.feed_name}}"] -contributors: ["{{ frontmatter.feed_name}}"] +card_type: "{{ frontmatter.card_type }}" +sources: ["{{ frontmatter.feed_name}}"] tags: {{ frontmatter.tags }} {% if frontmatter.featured_image %}featured_image: "{{frontmatter.featured_image}}"{% endif %} --- diff --git a/konfluks/templates/hashtag.md b/konfluks/templates/hashtag.md index 1148b79..ed41ffe 100644 --- a/konfluks/templates/hashtag.md +++ b/konfluks/templates/hashtag.md @@ -1,10 +1,8 @@ --- date: {{ post_metadata.created_at }} #2021-06-10T10:46:33+02:00 draft: false -authors: ["{{ post_metadata.account.display_name }}"] -contributors: ["{{ post_metadata.account.acct}}"] +contributors: ["{{ post_metadata.account.display_name }}"] avatar: {{ post_metadata.account.avatar }} -categories: ["shouts"] title: {{ post_metadata.account.display_name }} tags: [{% for i in post_metadata.tags %} "{{ i.name }}", {% endfor %}] images: [{% for i in post_metadata.media_attachments %}{% if i.type == "image" %}"{{ i.url | localize_media_url }}", {%endif%}{% endfor %}] diff --git a/konfluks/templates/timeline.md b/konfluks/templates/timeline.md index 0cc9c2b..b089a76 100644 --- a/konfluks/templates/timeline.md +++ b/konfluks/templates/timeline.md @@ -3,10 +3,10 @@ title: "{{ frontmatter.title }}" date: "{{ frontmatter.date }}" #2021-06-10T10:46:33+02:00 draft: false summary: "{{ frontmatter.summary }}" -authors: {% if frontmatter.author %} ["{{ frontmatter.author }}"] {% endif %} +contributors: {% if frontmatter.author %} ["{{ frontmatter.author }}"] {% endif %} original_link: "{{ frontmatter.original_link }}" feed_name: "{{ frontmatter.feed_name}}" -categories: ["timeline", "{{ frontmatter.feed_name}}"] +sources: ["timeline", "{{ frontmatter.feed_name}}"] timelines: {{ frontmatter.timelines }} hidden: true --- diff --git a/konfluks/templates/video.md b/konfluks/templates/video.md index 076a1bf..eafa1a8 100644 --- a/konfluks/templates/video.md +++ b/konfluks/templates/video.md @@ -9,7 +9,7 @@ channel_url: "{{ v.channel.url }}" contributors: ["{{ v.account.display_name }}"] preview_image: "{{ preview_image }}" images: ["./{{ preview_image }}"] -categories: ["tv","{{ v.channel.display_name }}"] +sources: ["{{ v.channel.display_name }}"] is_live: {{ v.is_live }} --- -- 2.49.0 From e01aa9a607bd7fd3f35d3c42a2df289a06d63c53 Mon Sep 17 00:00:00 2001 From: rra Date: Wed, 6 Nov 2024 16:48:41 +0100 Subject: [PATCH 46/48] Test whether a url still returns a feed, pass right filename as featured_image when handling enclosure, pass post_dir to existing_posts --- konfluks/feed.py | 100 ++++++++++++++++++++++++----------------------- 1 file changed, 52 insertions(+), 48 deletions(-) diff --git a/konfluks/feed.py b/konfluks/feed.py index f51d3e9..08606d2 100644 --- a/konfluks/feed.py +++ b/konfluks/feed.py @@ -156,7 +156,8 @@ def parse_enclosures(post_dir, entry): print("found enclosed media", e.type) if "image/" in e.type: featured_image = grab_media(post_dir, e.href) - entry["featured_image"] = featured_image + media_item = urlparse(e.href).path.split('/')[-1] + entry["featured_image"] = media_item else: print("FIXME:ignoring enclosed", e.type) return entry @@ -374,61 +375,64 @@ def main(): data = grab_feed(feed_url) if data: - opds_feed = False - for i in data.feed['links']: - if i['rel'] == 'self': - if 'opds' in i['type']: - opds_feed = True - print("OPDS type feed!") + if 'links' in data.feed: + for i in data.feed['links']: + if i['rel'] == 'self': + if 'opds' in i['type']: + opds_feed = True + print("OPDS type feed!") + if data.feed: + for entry in data.entries: + # if 'tags' in entry: + # for tag in entry.tags: + # for x in ['lumbung.space', 'D15', 'lumbung']: + # if x in tag['term']: + # print(entry.title) + entry["feed_name"] = feed_name - for entry in data.entries: - # if 'tags' in entry: - # for tag in entry.tags: - # for x in ['lumbung.space', 'D15', 'lumbung']: - # if x in tag['term']: - # print(entry.title) - entry["feed_name"] = feed_name + post_name = slugify(entry.title) - post_name = slugify(entry.title) + # pixelfed returns the whole post text as the post name. max + # filename length is 255 on many systems. here we're shortening + # the name and adding a hash to it to avoid a conflict in a + # situation where 2 posts start with exactly the same text. + if len(post_name) > 150: + post_hash = md5(bytes(post_name, "utf-8")) + post_name = post_name[:150] + "-" + post_hash.hexdigest() - # pixelfed returns the whole post text as the post name. max - # filename length is 255 on many systems. here we're shortening - # the name and adding a hash to it to avoid a conflict in a - # situation where 2 posts start with exactly the same text. - if len(post_name) > 150: - post_hash = md5(bytes(post_name, "utf-8")) - post_name = post_name[:150] + "-" + post_hash.hexdigest() - - if opds_feed: - entry['opds'] = True - #format: Beyond-Debiasing-Report_Online-75535a4886e3 - post_name = slugify(entry['title'])+'-'+entry['id'].split('-')[-1] - - post_dir = os.path.join(output_dir, feed_name, post_name) - - if post_name not in existing_posts: - # if there is a blog entry we dont already have, make it if opds_feed: - create_opds_post(post_dir, entry) - else: - create_post(post_dir, entry) + entry['opds'] = True + #format: Beyond-Debiasing-Report_Online-75535a4886e3 + post_name = slugify(entry['title'])+'-'+entry['id'].split('-')[-1] - elif post_name in existing_posts: - # if we already have it, update it - if opds_feed: - create_opds_post(post_dir, entry) - else: - create_post(post_dir, entry) - existing_posts.remove( - post_name - ) # create list of posts which have not been returned by the feed + post_dir = os.path.join(output_dir, feed_name, post_name) - for post in existing_posts: - # remove blog posts no longer returned by the RSS feed - print("deleted", post) - shutil.rmtree(os.path.join(feed_dir, slugify(post))) + if post_name not in existing_posts: + # if there is a blog entry we dont already have, make it + if opds_feed: + create_opds_post(post_dir, entry) + else: + create_post(post_dir, entry) + + elif post_name in existing_posts: + # if we already have it, update it + if opds_feed: + create_opds_post(post_dir, entry) + else: + create_post(post_dir, entry) + existing_posts.remove( + post_dir + ) # create list of posts which have not been returned by the feed + + + for post in existing_posts: + # remove blog posts no longer returned by the RSS feed + print("deleted", post) + shutil.rmtree(post) + else: + print(feed_url, "is not or no longer a feed!") end = time.time() -- 2.49.0 From 9d9f8f6d72840f6e90aa9e621237d559936b5a69 Mon Sep 17 00:00:00 2001 From: rra Date: Wed, 6 Nov 2024 17:24:55 +0100 Subject: [PATCH 47/48] do proper deletion --- konfluks/feed.py | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/konfluks/feed.py b/konfluks/feed.py index 08606d2..53435ba 100644 --- a/konfluks/feed.py +++ b/konfluks/feed.py @@ -374,16 +374,16 @@ def main(): data = grab_feed(feed_url) - if data: - opds_feed = False - if 'links' in data.feed: - for i in data.feed['links']: - if i['rel'] == 'self': - if 'opds' in i['type']: - opds_feed = True - print("OPDS type feed!") + if data: #whenever we get a 200 + if data.feed: #only if it is an actual feed + opds_feed = False + if 'links' in data.feed: + for i in data.feed['links']: + if i['rel'] == 'self': + if 'opds' in i['type']: + opds_feed = True + print("OPDS type feed!") - if data.feed: for entry in data.entries: # if 'tags' in entry: # for tag in entry.tags: @@ -423,14 +423,15 @@ def main(): else: create_post(post_dir, entry) existing_posts.remove( - post_dir + post_name ) # create list of posts which have not been returned by the feed for post in existing_posts: # remove blog posts no longer returned by the RSS feed - print("deleted", post) - shutil.rmtree(post) + post_dir = os.path.join(output_dir, feed_name, post) + shutil.rmtree(post_dir) + print("deleted", post_dir) else: print(feed_url, "is not or no longer a feed!") -- 2.49.0 From 028bc1df84c9089391bd20f4c90d4db8a3f3ec16 Mon Sep 17 00:00:00 2001 From: rra Date: Wed, 20 Nov 2024 11:25:26 +0100 Subject: [PATCH 48/48] fix issue where posts with enclosures would not download files because of missing dir --- konfluks/feed.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/konfluks/feed.py b/konfluks/feed.py index 53435ba..844e0da 100644 --- a/konfluks/feed.py +++ b/konfluks/feed.py @@ -155,6 +155,8 @@ def parse_enclosures(post_dir, entry): if "type" in e: print("found enclosed media", e.type) if "image/" in e.type: + if not os.path.exists(post_dir): #this might be redundant with create_post + os.makedirs(post_dir) featured_image = grab_media(post_dir, e.href) media_item = urlparse(e.href).path.split('/')[-1] entry["featured_image"] = media_item -- 2.49.0