fix: don't pull the same post twice

This reverts commit d9bcb29f85.

.gitignore

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

README.md

@@ -1,3 +1,8 @@
 # lumbunglib
 
 > Python lib which powers `lumbung[dot]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

lumbunglib/hashtag.py

@@ -9,7 +9,15 @@ from mastodon import Mastodon
 instance = "https://social.lumbung.space"
 email = ""
 password = ""
-hashtags = ["jalansesama"]
+hashtags = [
+    "documentafifteen",
+    "harvestedbyputra",
+    "jalansesama",
+    "lumbungdotspace",
+    "majelisakakbar",
+    "majelisakbar",
+    "warungkopi",
+]
 
 
 def login_mastodon_bot():
@@ -95,6 +103,10 @@ 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)
@@ -114,12 +126,13 @@ def main():
             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(post_metadata["id"])
                 else:
                     print("not pulling post %s (post is local only)" % (post_metadata["id"]))
 

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 }}

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']}