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 New York Times

Browse Source
This commit is contained in:
Kovid Goyal 2018-06-02 07:59:28 +05:30
parent 32e83b742f
commit 4e0ada41f5
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
recipes/nytimes.recipe
View File

@ -79,9 +79,12 @@ class NewYorkTimes(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
compress_news_images = True compress_news_images = True
compress_news_images_auto_size = 5 compress_news_images_auto_size = 5
remove_attributes = ['style']
remove_tags = [ remove_tags = [
dict(attrs={'aria-label':'tools'.split()}), dict(attrs={'aria-label':'tools'.split()}),
dict(attrs={'aria-label': lambda x: x and 'New York Times Logo' in x}),
dict(href='#site-content #site-index'.split()),
dict(attrs={'aria-hidden':'true'}), dict(attrs={'aria-hidden':'true'}),
dict(attrs={'data-videoid':True}), dict(attrs={'data-videoid':True}),
dict(name='button meta link'.split()), dict(name='button meta link'.split()),
@ -125,6 +128,12 @@ class NewYorkTimes(BasicNewsRecipe):
for li in soup.findAll('li', attrs={'class': lambda x: x and x.startswith('css-')}): for li in soup.findAll('li', attrs={'class': lambda x: x and x.startswith('css-')}):
if not li.contents and not li.string: if not li.contents and not li.string:
li.extract() li.extract()
# Ensure the headline is first
h1 = soup.find('h1', itemprop='headline')
if h1 is not None:
h1.extract()
soup.find('body').contents.insert(0, h1)
return soup return soup
def read_nyt_metadata(self): def read_nyt_metadata(self):
@ -240,6 +249,9 @@ class NewYorkTimes(BasicNewsRecipe):
return feeds return feeds
def parse_index(self): def parse_index(self):
# return [('All articles', [
# {'title': 'XXXXX', 'url': 'https://www.nytimes.com/2018/05/31/theater/best-25-plays-how-we-made-the-list.html'},
# ])]
if is_web_edition: if is_web_edition:
return self.parse_web_sections() return self.parse_web_sections()
return self.parse_todays_page() return self.parse_todays_page()

12
recipes/nytimes_sub.recipe
View File

@ -79,9 +79,12 @@ class NewYorkTimes(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
compress_news_images = True compress_news_images = True
compress_news_images_auto_size = 5 compress_news_images_auto_size = 5
remove_attributes = ['style']
remove_tags = [ remove_tags = [
dict(attrs={'aria-label':'tools'.split()}), dict(attrs={'aria-label':'tools'.split()}),
dict(attrs={'aria-label': lambda x: x and 'New York Times Logo' in x}),
dict(href='#site-content #site-index'.split()),
dict(attrs={'aria-hidden':'true'}), dict(attrs={'aria-hidden':'true'}),
dict(attrs={'data-videoid':True}), dict(attrs={'data-videoid':True}),
dict(name='button meta link'.split()), dict(name='button meta link'.split()),
@ -125,6 +128,12 @@ class NewYorkTimes(BasicNewsRecipe):
for li in soup.findAll('li', attrs={'class': lambda x: x and x.startswith('css-')}): for li in soup.findAll('li', attrs={'class': lambda x: x and x.startswith('css-')}):
if not li.contents and not li.string: if not li.contents and not li.string:
li.extract() li.extract()
# Ensure the headline is first
h1 = soup.find('h1', itemprop='headline')
if h1 is not None:
h1.extract()
soup.find('body').contents.insert(0, h1)
return soup return soup
def read_nyt_metadata(self): def read_nyt_metadata(self):
@ -240,6 +249,9 @@ class NewYorkTimes(BasicNewsRecipe):
return feeds return feeds
def parse_index(self): def parse_index(self):
# return [('All articles', [
# {'title': 'XXXXX', 'url': 'https://www.nytimes.com/2018/05/31/theater/best-25-plays-how-we-made-the-list.html'},
# ])]
if is_web_edition: if is_web_edition:
return self.parse_web_sections() return self.parse_web_sections()
return self.parse_todays_page() return self.parse_todays_page()