Add RSS reading functionality

.gitignore

@@ -0,0 +1 @@
+*.json

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/encodings.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Encoding" addBOMForNewFiles="with BOM under Windows, with no BOM otherwise" />
+</project>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/mastofeeds.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (mastofeeds)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/mastofeeds.iml" filepath="$PROJECT_DIR$/.idea/mastofeeds.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

main.py

@@ -0,0 +1,60 @@
+import feedparser
+import json
+from markdownify import markdownify
+import re
+import time
+
+
+def process_html(html: str) -> str:
+    return re.sub(r"\n{3,}", "\n\n",
+                  re.sub(r"\\(\W)", r"\1", re.sub(r"^(\s*)\* ", r"\1- ", markdownify(html), 0, re.MULTILINE))).strip()
+
+
+def split_notes(text: str, limit: int) -> list[str]:
+    notes = []
+
+    prev = 0
+    while len(text[prev:prev + limit]) >= limit:
+        sub = text[prev:prev + limit]
+
+        i = sub.rfind("\n")
+        if i == -1:
+            i = sub.rfind(" ")
+
+        notes.append(sub[:i].strip())
+        prev += i + 1
+
+    return notes
+
+
+if __name__ == "__main__":
+    config_file = open("./config.json", "r")
+    config = json.load(config_file)
+    config_file.close()
+
+    for url in config.keys():
+        print("Updating", url)
+        rss = feedparser.parse(url)
+
+        rss.entries.sort(key=lambda entry: entry.published_parsed)
+
+        if config[url] is None:
+            config[url] = 0.0
+        if time.mktime(rss.entries[-1].published_parsed) <= config[url]:
+            continue
+
+        for entry in rss.entries:
+            if time.mktime(rss.feed.published_parsed) <= config[url]:
+                continue
+
+            notes = split_notes("[" + entry.title + "](" + entry.link + ")\n" + process_html(
+                entry.content[0].value) + "\n\n" + entry.link, 500)
+            [print(note) for note in notes]
+            print()
+
+        config[url] = time.mktime(rss.entries[-1].published_parsed)
+
+    print("Saving config", config)
+    config_file = open("./config.json", "w")
+    json.dump(config, config_file, indent=4)
+    config_file.close()

requirements.txt

@@ -0,0 +1,16 @@
+beautifulsoup4==4.12.3
+blurhash==1.1.4
+certifi==2024.8.30
+charset-normalizer==3.4.0
+decorator==5.1.1
+feedparser==6.0.11
+idna==3.10
+markdownify==0.13.1
+Mastodon.py==1.8.1
+python-dateutil==2.9.0.post0
+python-magic==0.4.27
+requests==2.32.3
+sgmllib3k==1.0.0
+six==1.16.0
+soupsieve==2.6
+urllib3==2.2.3