Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update "Al Jazeera in English"

Browse Source 
"Al Jazeera in English" is broken currently, it only retrieves titles but no content. So I updated the recipe so content is preserved.
This commit is contained in:
Rogelio Domínguez Hernández 2018-12-10 16:14:10 -06:00 committed by GitHub
parent 6025101886
commit 78efc02b01
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
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 use_embedded_content = False
extra_css = """ extra_css = """
body{font-family: Arial,sans-serif} body{font-family: Arial,sans-serif}
#ctl00_cphBody_dvSummary{font-weight: bold}
#dvArticleDate{font-size: small; color: #999999}
""" """
conversion_options = { conversion_options = {
'comment': description, 'tags': category, 'comment': description, 'tags': category,
'publisher': publisher, 'language': language 'publisher': publisher, 'language': language
} }
keep_only_tags = [ keep_only_tags = [
dict(id='main-story'), dict(id='article-page'),
] ]
remove_tags = [ remove_tags = [
has_cls('MoreOnTheStory'), has_cls(
'ArticleBottomToolbar'), dict(smtitle="ShowMore"),
dict(name=['object', 'link', 'table', dict(name=['object', 'link', 'table',
'meta', 'base', 'iframe', 'embed']), 'meta', 'base', 'iframe', 'embed']),
] ]
@ -48,21 +44,13 @@ class AlJazeera(BasicNewsRecipe):
def get_article_url(self, article): def get_article_url(self, article):
artlurl = article.get('link', None) artlurl = article.get('link', None)
return artlurl.replace('http://english.aljazeera.net//', 'http://english.aljazeera.net/') return artlurl
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
for item in soup.findAll(face=True): for item in soup.findAll(face=True):
del item['face'] 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'): for alink in soup.findAll('a'):
if alink.string is not None: if alink.string is not None:
tstr = alink.string tstr = alink.string