Quote:
Originally Posted by unkn0wn
Code:
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
br = self.get_browser()
try:
br.open(url)
except Exception as e:
url = e.hdrs.get('location')
soup = self.index_to_soup(url)
link = soup.find('a', href=True)
html = br.open(link['href']).read()
pt = PersistentTemporaryFile('.html')
pt.write(html)
pt.close()
return pt.name
try adding this to the recipe
|
I have tested many times and found that it still fails,The content is all empty and the links are gone please take another look, thank you very much
Test recipe:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1675504328(BasicNewsRecipe):
title = 'Google news-ceshi'
oldest_article = 1
max_articles_per_feed = 100
auto_cleanup = True
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
br = self.get_browser()
try:
br.open(url)
except Exception as e:
url = e.hdrs.get('location')
soup = self.index_to_soup(url)
link = soup.find('a', href=True)
html = br.open(link['href']).read()
pt = PersistentTemporaryFile('.html')
pt.write(html)
pt.close()
return pt.name
feeds = [
('"ASML" - Google News', 'https://news.google.com/news/rss/search?q=ASML&hl=en'),
('"intel" - Google News', 'https://news.google.com/news/rss/search?q=intel&hl=en'),
('amazon - Google News', 'http://news.google.com/news?hl=en&gl=us&q=amazon&um=1&ie=UTF-8&output=rss'),
('Ubuntu - Google News', 'http://news.google.com/news?hl=en&gl=us&q=Ubuntu&um=1&ie=UTF-8&output=rss'),
]
Google news-ceshi.recipe