Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Al Jazeera in English

Browse Source 
Merge branch 'patch-1' of https://github.com/rogeliodh/calibre
This commit is contained in:
Kovid Goyal 2018-12-11 06:35:32 +05:30
commit 25b8f19c01
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 2 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/al_jazeera.recipe
View File

@ -25,20 +25,16 @@ class AlJazeera(BasicNewsRecipe):
use_embedded_content = False
extra_css = """
body{font-family: Arial,sans-serif}
#ctl00_cphBody_dvSummary{font-weight: bold}
#dvArticleDate{font-size: small; color: #999999}
"""
conversion_options = {
'comment': description, 'tags': category,
'publisher': publisher, 'language': language
}
keep_only_tags = [
dict(id='main-story'),
dict(id='article-page'),
]
remove_tags = [
has_cls('MoreOnTheStory'), has_cls(
'ArticleBottomToolbar'), dict(smtitle="ShowMore"),
dict(name=['object', 'link', 'table',
'meta', 'base', 'iframe', 'embed']),
]
@ -48,21 +44,13 @@ class AlJazeera(BasicNewsRecipe):
def get_article_url(self, article):
artlurl = article.get('link', None)
return artlurl.replace('http://english.aljazeera.net//', 'http://english.aljazeera.net/')
return artlurl
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(face=True):
del item['face']
td = soup.find('td', attrs={'class': 'DetailedSummary'})
if td:
td.name = 'div'
spn = soup.find('span', attrs={'id': 'DetailedTitle'})
if spn:
spn.name = 'h1'
for itm in soup.findAll('span', attrs={'id': ['dvArticleDate', 'ctl00_cphBody_lblDate']}):
itm.name = 'div'
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string