1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
#!/usr/bin/env python3
from urllib.request import urlopen, Request
from datetime import datetime
from bs4 import BeautifulSoup
import sys
from rss import _format_date
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])
|
