Initial commit of RSS converter application

1 files changed, 72 insertions, 0 deletions

diff --git a/telegram.py b/telegram.py
new file mode 100755
index 0000000..3058339
--- /dev/null
+++ b/telegram.py
@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+
+from urllib.request import urlopen, Request
+from datetime import datetime
+from bs4 import BeautifulSoup
+import sys
+
+def _format_date(dt):
+    """convert a datetime into an RFC 822 formatted date
+    Input date must be in GMT.
+    Stolen from PyRSS2Gen.
+    """
+    # Looks like:
+    #   Sat, 07 Sep 2002 00:00:01 GMT
+    # Can't use strftime because that's locale dependent
+    #
+    # Isn't there a standard way to do this for Python?  The
+    # rfc822 and email.Utils modules assume a timestamp.  The
+    # following is based on the rfc822 module.
+    return "%s, %02d %s %04d %02d:%02d:%02d GMT" % (
+            ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"][dt.weekday()],
+            dt.day,
+            ["Jan", "Feb", "Mar", "Apr", "May", "Jun",
+             "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"][dt.month-1],
+            dt.year, dt.hour, dt.minute, dt.second)
+
+def telegram(channel):
+    url = 'https://t.me/s/' + channel
+    res = urlopen(Request(url))
+    soup = BeautifulSoup(res, features="html.parser")
+
+    # messages = soup.find_all('div', attrs={'class': 'tgme_widget_message_wrap'})
+    messages = soup.find_all('div', attrs={'class': 'tgme_widget_message_bubble'})
+
+    for message in messages:
+        date = message.find('time', attrs={'class': 'time'})['datetime']
+        html = message.find('div', attrs={'class': 'tgme_widget_message_text'})
+        # preview = message.find('div', attrs={'class': 'tgme_widget_message_bubble'})
+        link = message.find('a', attrs={'class': 'tgme_widget_message_date'})
+        title = html.text if html else 'No text'
+        description = str(message) # if preview else '?'
+        link = link['href']
+        yield title, description, link, date
+
+def main(channel):
+    url = 'https://t.me/s/' + channel
+
+    print("""<?xml version="1.0" encoding="UTF-8"?>
+<rss version="2.0">
+  <channel>
+    <title>Telegram: """ + channel + """</title>
+    <link>""" + url + """</link>
+    <description>The latest entries of the telegram channel of """ +channel + """</description>
+    <lastBuildDate>""" + _format_date(datetime.now()) + """</lastBuildDate>""")
+
+    for title, description, link, date in telegram(channel):
+        print('    <item>')
+        print('      <title><![CDATA[' + title + ']]></title>')
+        print('      <link>' + link + '</link>')
+        print('      <description><![CDATA[' + description + ']]></description>')
+        print('      <pubDate>' + date + '</pubDate>')
+        # print('      <media:content url="' + thumbnail + b'" type="image/jpeg" />')
+        print('    </item>')
+
+    print('  </channel>')
+    print('</rss>')
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print('Usage:', sys.argv[0], '<telegram channel>')
+        sys.exit(1)
+    main(sys.argv[1])