Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update NYTimes

Browse Source
This commit is contained in:
Kovid Goyal 2020-11-27 16:40:19 +05:30
parent 197ec8c441
commit 975f23dd71
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
recipes/nytimes.recipe
View File

@ -145,6 +145,14 @@ class NewYorkTimes(BasicNewsRecipe):
if h1 is not None: if h1 is not None:
h1.extract() h1.extract()
soup.find('body').contents.insert(0, h1) soup.find('body').contents.insert(0, h1)
# Find lazy loaded images
for div in soup.findAll(itemtype='http://schema.org/ImageObject', itemid=True):
if div.find('img') is None:
span = div.find('span')
if span is not None and self.tag_to_string(span).strip().lower() == 'image':
span.name = 'img'
span['src'] = div['itemid']
return soup return soup
def read_todays_paper(self): def read_todays_paper(self):
@ -301,7 +309,7 @@ class NewYorkTimes(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
# return [('All articles', [ # return [('All articles', [
# {'title': 'XXXXX', 'url': 'https://www.nytimes.com/2018/05/31/theater/best-25-plays-how-we-made-the-list.html'}, # {'title': 'XXXXX', 'url': 'https://www.nytimes.com/2020/11/27/world/americas/coronavirus-migrants-venezuela.html'},
# ])] # ])]
if is_web_edition: if is_web_edition:
return self.parse_web_sections() return self.parse_web_sections()

8
recipes/nytimes_sub.recipe
View File

@ -145,6 +145,14 @@ class NewYorkTimes(BasicNewsRecipe):
if h1 is not None: if h1 is not None:
h1.extract() h1.extract()
soup.find('body').contents.insert(0, h1) soup.find('body').contents.insert(0, h1)
# Find lazy loaded images
for div in soup.findAll(itemtype='http://schema.org/ImageObject', itemid=True):
if div.find('img') is None:
span = div.find('span')
if span is not None and self.tag_to_string(span).strip().lower() == 'image':
span.name = 'img'
span['src'] = div['itemid']
return soup return soup
def read_todays_paper(self): def read_todays_paper(self):