Merge branch 'master' of ssh://git.autonomic.zone:2222/ruangrupa/lumbunglib

Reviewed-on: ruangrupa/lumbunglib#23

.gitignore

@@ -1,4 +1,7 @@
-test
+*.txt
+*.txt.*
 __pycache__
+etags
+test
 .venv
 content

README.md

@@ -1,3 +1,40 @@
 # lumbunglib
 
-> Python lib which powers `lumbung[dot]space` automation
+> Python lib which powers `lumbung.space` automation
+
+## hacking
+
+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.

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
@@ -75,6 +76,7 @@ def create_metadata(event):
         "duration": date.compress(event.duration),
         "location": event.location,
         "uid": event.uid,
+        "featured_image": "",
         "images": find_imageURLS(event.description),  # currently not used in template
     }
 
@@ -110,7 +112,6 @@ def localize_time(date):
         )
     return localized_begins
 
-
 def create_event_post(post_dir, event):
     """
     Create HUGO post based on calendar event metadata
@@ -146,12 +147,15 @@ def create_event_post(post_dir, event):
         if not os.path.exists(local_image):
             # download preview image
             response = requests.get(img, stream=True)
-            with open(local_image, "wb") as img_file:
+            if response.status_code == 200:
-                shutil.copyfileobj(response.raw, img_file)
+                with open(local_image, "wb") as img_file:
-                print('Downloaded image for event "{}"'.format(event.name))
+                    shutil.copyfileobj(response.raw, img_file)
-            event_metadata["description"] = event_metadata["description"].replace(
+                    print('Downloaded image for event "{}"'.format(event.name))
-                img, "![]({})".format(img_name)
+                event_metadata["description"] = event_metadata["description"].replace(
-            )
+                    img, "![]({})".format(img_name)
+                )
+                if event_metadata["featured_image"] == "":
+                    event_metadata["featured_image"] = img_name
         if img_name in existing_images:
             existing_images.remove(img_name)
 
@@ -184,18 +188,18 @@ def update_event_post(post_dir, event):
 
 def main():
     for event in list(cal.events):
+        post_name = slugify(event.name) + "-" + event.uid
+        post_dir = os.path.join(output_dir, post_name)
 
-        post_dir = os.path.join(output_dir, event.uid)
+        if post_name not in existing_posts:
-
-        if event.uid 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:

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
@@ -60,6 +61,11 @@ def create_frontmatter(entry):
     else:
         author = ""
 
+    if "title" in entry:
+        title = entry.title
+    else:
+        title = ""
+
     tags = []
     if "tags" in entry:
         # TODO finish categories
@@ -67,7 +73,7 @@ def create_frontmatter(entry):
             tags.append(t["term"])
 
     frontmatter = {
-        "title": entry.title,
+        "title": title,
         "date": published.format(),
         "summary": "",
         "author": author,
@@ -194,13 +200,25 @@ def main():
     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 = urlparse(feed_url).netloc
+        feed_name = feed_dict[feed_url]
 
         feed_dir = os.path.join(output_dir, feed_name)
 
@@ -221,6 +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:

lumbunglib/hashtag.py

@@ -9,7 +9,16 @@ from mastodon import Mastodon
 instance = "https://social.lumbung.space"
 email = ""
 password = ""
-hashtags = ["jalansesama"]
+hashtags = [
+    "documentafifteen",
+    "harvestedbyputra",
+    "jalansesama",
+    "lumbungdotspace",
+    "majelisakakbar",
+    "majelisakbar",
+    "warungkopi",
+    "lumbungkios",
+]
 
 
 def login_mastodon_bot():
@@ -95,6 +104,10 @@ def main():
     if not os.path.exists(output_dir):
         os.mkdir(output_dir)
 
+    all_existing_posts = []
+    for i in os.listdir(output_dir):
+        all_existing_posts += os.listdir(os.path.join(output_dir, i))
+
     for hashtag in hashtags:
 
         hashtag_dir = os.path.join(output_dir, hashtag)
@@ -112,14 +125,13 @@ def main():
 
         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 existing_posts:
+            if str(post_metadata["id"]) not in all_existing_posts:
-
                 if not post_metadata[
                     "local_only"
                 ]:  # if you get an error here then you are using vanilla Mastodon, this is a Hometown or Glitch only feature
                     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"]))
 
@@ -129,6 +141,8 @@ def main():
                 existing_posts.remove(
                     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"])))
 
         for post in existing_posts:
             print(

lumbunglib/templates/calendar.md

@@ -8,6 +8,9 @@ event_end: "{{ event.end }}"
 duration: "{{ event.duration }}"
 localized_begin: "{{ event.localized_begin }}"
 uid: "{{ event.uid }}"
+{% if event.featured_image %}
+featured_image: "{{ event.featured_image }}"
+{% endif %}
 {% if event.location %}
 location: "{{ event.location }}"
 {% endif %}

lumbunglib/templates/feed.md

@@ -7,7 +7,7 @@ author: "{{ frontmatter.author }}"
 original_link: "{{ frontmatter.original_link }}"
 feed_name: "{{ frontmatter.feed_name}}"
 categories: ["network", "{{ frontmatter.feed_name}}"]
-tags: { { frontmatter.tags } }
+tags: {{ frontmatter.tags }}
 ---
 
 {{ content }}

lumbunglib/templates/hashtag.md

@@ -4,6 +4,8 @@ draft: false
 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 %}]
 ---
 

lumbunglib/templates/video.md

@@ -7,6 +7,7 @@ video_duration: "{{ v.duration | duration }} "
 video_channel: "{{ v.channel.display_name }}"
 channel_url: "{{ v.channel.url }}"
 preview_image: "{{ preview_image }}"
+images: ["./{{ preview_image }}"]
 categories: ["tv","{{ v.channel.display_name }}"]
 is_live: {{ v.is_live }}
 ---

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
@@ -97,7 +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 main():
     v = peertube.VideoApi(client)
 
@@ -114,10 +114,11 @@ def main():
     existing_posts = os.listdir(output_dir)
 
     for video_metadata in videos:
-        post_dir = os.path.join(output_dir, video_metadata["uuid"])
+        post_name = slugify(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"])
@@ -125,11 +126,11 @@ 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:

poetry.lock

@@ -9,6 +9,21 @@ python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 [package.dependencies]
 python-dateutil = "*"
 
+[[package]]
+name = "beautifulsoup4"
+version = "4.10.0"
+description = "Screen-scraping library"
+category = "main"
+optional = false
+python-versions = ">3.0.0"
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
 [[package]]
 name = "blurhash"
 version = "1.1.4"
@@ -20,6 +35,17 @@ python-versions = "*"
 [package.extras]
 test = ["pillow", "numpy", "pytest"]
 
+[[package]]
+name = "bs4"
+version = "0.0.1"
+description = "Dummy package for Beautiful Soup"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+beautifulsoup4 = "*"
+
 [[package]]
 name = "certifi"
 version = "2021.10.8"
@@ -47,6 +73,17 @@ category = "main"
 optional = false
 python-versions = ">=3.5"
 
+[[package]]
+name = "feedparser"
+version = "6.0.8"
+description = "Universal feed parser, handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+sgmllib3k = "*"
+
 [[package]]
 name = "ics"
 version = "0.7"
@@ -223,6 +260,14 @@ 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 = "sgmllib3k"
+version = "1.0.0"
+description = "Py3k port of sgmllib."
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "six"
 version = "1.16.0"
@@ -231,6 +276,14 @@ category = "main"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
 
+[[package]]
+name = "soupsieve"
+version = "2.3.1"
+description = "A modern CSS selector implementation for Beautiful Soup."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
 [[package]]
 name = "tatsu"
 version = "5.7.0"
@@ -266,17 +319,24 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.9"
-content-hash = "d3c9d528613826932cb3f316a3a69066e87e69011d4c8d3a2492521833d3851f"
+content-hash = "c5c987253f949737210f4a3d3c3c24b0affd4a9c7d06de386c9bd514c592db8b"
 
 [metadata.files]
 arrow = [
     {file = "arrow-0.14.7-py2.py3-none-any.whl", hash = "sha256:4bfacea734ead51495dc47df00421ecfd4ca1f2c0fbe58b9a26eaeddedc31caf"},
     {file = "arrow-0.14.7.tar.gz", hash = "sha256:67f8be7c0cf420424bc62d8d7dc40b44e4bb2f7b515f9cc2954fb36e35797656"},
 ]
+beautifulsoup4 = [
+    {file = "beautifulsoup4-4.10.0-py3-none-any.whl", hash = "sha256:9a315ce70049920ea4572a4055bc4bd700c940521d36fc858205ad4fcde149bf"},
+    {file = "beautifulsoup4-4.10.0.tar.gz", hash = "sha256:c23ad23c521d818955a4151a67d81580319d4bf548d3d49f4223ae041ff98891"},
+]
 blurhash = [
     {file = "blurhash-1.1.4-py2.py3-none-any.whl", hash = "sha256:7611c1bc41383d2349b6129208587b5d61e8792ce953893cb49c38beeb400d1d"},
     {file = "blurhash-1.1.4.tar.gz", hash = "sha256:da56b163e5a816e4ad07172f5639287698e09d7f3dc38d18d9726d9c1dbc4cee"},
 ]
+bs4 = [
+    {file = "bs4-0.0.1.tar.gz", hash = "sha256:36ecea1fd7cc5c0c6e4a1ff075df26d50da647b75376626cc186e2212886dd3a"},
+]
 certifi = [
     {file = "certifi-2021.10.8-py2.py3-none-any.whl", hash = "sha256:d62a0163eb4c2344ac042ab2bdf75399a71a2d8c7d47eac2e2ee91b9d6339569"},
     {file = "certifi-2021.10.8.tar.gz", hash = "sha256:78884e7c1d4b00ce3cea67b44566851c4343c120abd683433ce934a68ea58872"},
@@ -289,6 +349,10 @@ decorator = [
     {file = "decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186"},
     {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
 ]
+feedparser = [
+    {file = "feedparser-6.0.8-py3-none-any.whl", hash = "sha256:1b7f57841d9cf85074deb316ed2c795091a238adb79846bc46dccdaf80f9c59a"},
+    {file = "feedparser-6.0.8.tar.gz", hash = "sha256:5ce0410a05ab248c8c7cfca3a0ea2203968ee9ff4486067379af4827a59f9661"},
+]
 ics = [
     {file = "ics-0.7-py2.py3-none-any.whl", hash = "sha256:bf5fbdef6e1e073afdadf1b996f0271186dd114a148e38e795919a1ae644d6ac"},
     {file = "ics-0.7-py3.7.egg", hash = "sha256:3b606205b9582ad27dff77f9b227a30d02fdac532731927fe39df1f1ddf8673f"},
@@ -409,10 +473,17 @@ requests = [
     {file = "requests-2.27.1-py2.py3-none-any.whl", hash = "sha256:f22fa1e554c9ddfd16e6e41ac79759e17be9e492b3587efa038054674760e72d"},
     {file = "requests-2.27.1.tar.gz", hash = "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61"},
 ]
+sgmllib3k = [
+    {file = "sgmllib3k-1.0.0.tar.gz", hash = "sha256:7868fb1c8bfa764c1ac563d3cf369c381d1325d36124933a726f29fcdaa812e9"},
+]
 six = [
     {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
 ]
+soupsieve = [
+    {file = "soupsieve-2.3.1-py3-none-any.whl", hash = "sha256:1a3cca2617c6b38c0343ed661b1fa5de5637f257d4fe22bd9f1338010a1efefb"},
+    {file = "soupsieve-2.3.1.tar.gz", hash = "sha256:b8d49b1cd4f037c7082a9683dfa1801aa2597fb11c3a1155b7a5b94829b4f1f9"},
+]
 tatsu = [
     {file = "TatSu-5.7.0-py2.py3-none-any.whl", hash = "sha256:9eebadfc2889d8e82e197df22913df56ff204bf4cfc62db49a5c7edd084e10b4"},
     {file = "TatSu-5.7.0.zip", hash = "sha256:428136cd4aa9600fcd01428bd5667fc752062f54bd0148dc1e64fee7b8d05fa4"},

pyproject.toml

@@ -13,6 +13,8 @@ natural = "^0.2.0"
 python-slugify = "^5.0.2"
 requests = "^2.26.0"
 peertube = {git = "https://framagit.org/framasoft/peertube/clients/python.git"}
+feedparser = "^6.0.8"
+bs4 = "^0.0.1"
 "Mastodon.py" = "^1.5.1"
 
 [tool.poetry.dev-dependencies]
@@ -25,4 +27,5 @@ 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"

setup.py

@@ -10,6 +10,8 @@ package_data = \
 install_requires = \
 ['Jinja2>=3.0.3,<4.0.0',
  'Mastodon.py>=1.5.1,<2.0.0',
+ 'bs4>=0.0.1,<0.0.2',
+ 'feedparser>=6.0.8,<7.0.0',
  'ics>=0.7,<0.8',
  'natural>=0.2.0,<0.3.0',
  'peertube @ '
@@ -19,6 +21,7 @@ install_requires = \
 
 entry_points = \
 {'console_scripts': ['lumbunglib-cal = lumbunglib.cloudcal:main',
+                     'lumbunglib-feed = lumbunglib.feed:main',
                      'lumbunglib-hash = lumbunglib.hashtag:main',
                      'lumbunglib-vid = lumbunglib.video:main']}