Backup_Repos/calibre
1
0
Fork 0
mirror of git://github.com/kovidgoyal/calibre.git synced 2025-12-06 12:04:27 +01:00
Code Issues Projects Releases Wiki Activity

Update People Daily

Browse source
This commit is contained in:
Kovid Goyal 2021-06-15 08:13:16 +05:30
parent ec3744c661
commit 268d1d991c
No known key found for this signature in database
GPG key ID: 06BC317B515ACE7C
1 changed files with 11 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
recipes/people_daily.recipe
View file

@ -9,7 +9,7 @@ class AdvancedUserRecipe1277129332(BasicNewsRecipe):
title = u'人民日报'
oldest_article = 2
max_articles_per_feed = 100
__author__ = 'zzh'
__author__ = 'ceapas'
pubisher = 'people.com.cn'
description = 'People Daily Newspaper'
@ -70,16 +70,16 @@ class AdvancedUserRecipe1277129332(BasicNewsRecipe):
# (u'中国人大新闻', u'http://www.people.com.cn/rss/14576.xml'),
# (u'中国政协新闻', u'http://www.people.com.cn/rss/34948.xml'),
]
keep_only_tags = [
dict(name='div', attrs={'class': 'text_c'}),
]
# keep_only_tags = [
# dict(name='p'),
# ]
remove_tags = [
dict(name='div', attrs={'class': 'tools'}),
]
remove_tags_after = [
dict(name='div', attrs={'id': 'p_content'}),
dict(name='div', class_="channel cf")
]
remove_tags_before = [dict(name='div', class_="layout rm_txt cf")]
remove_tags_after = [dict(name='div', class_="edit cf")]
def append_page(self, soup, appendtag, position):
pager = soup.find('img', attrs={'src': '/img/next_b.gif'})
if pager:
@ -101,8 +101,7 @@ def skip_ad_pages(self, soup):
return None
def preprocess_html(self, soup):
mtag = '<meta http-equiv="content-type" content="text/html;charset=GB2312" />\n<meta http-equiv="content-language" content="GB2312" />'
soup.head.insert(0, mtag)
for item in soup.findAll(style=True):
del item['form']
self.append_page(soup, soup.body, 3)
@ -115,8 +114,8 @@ def get_cover_url(self):
year = time.strftime('%Y')
month = time.strftime('%m')
day = time.strftime('%d')
cover = 'http://paper.people.com.cn/rmrb/page/' + year + '-' + \
month + '/' + day + '/01/RMRB' + year + month + day + 'B001_b.jpg'
cover = 'http://paper.people.com.cn/rmrb/images/' + year + '-' + \
month + '/' + day + '/01/rmrb' + year + month + day + '01_b.jpg'
br = BasicNewsRecipe.get_browser(self)
try:
br.open(cover)