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 Yorker

Browse Source
This commit is contained in:
Kovid Goyal 2016-08-15 12:34:57 +05:30
parent ccecdfb0d4
commit 0951d3228d
1 changed files with 15 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
recipes/new_yorker.recipe
View File

@ -13,11 +13,6 @@ class NewYorker(BasicNewsRecipe):
masthead_url = 'http://www.newyorker.com/images/elements/print/newyorker_printlogo.gif' masthead_url = 'http://www.newyorker.com/images/elements/print/newyorker_printlogo.gif'
compress_news_images = True
compress_news_images_auto_size = 8
scale_news_images_to_device = False
scale_news_images = (768, 1024)
url_list = [] url_list = []
language = 'en' language = 'en'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
@ -31,8 +26,8 @@ class NewYorker(BasicNewsRecipe):
''' '''
needs_subscription = 'optional' needs_subscription = 'optional'
keep_only_tags = [ keep_only_tags = [
dict(itemprop=['headline', 'alternativeHeadline', dict(itemprop=['headline', 'alternativeHeadline', 'author', 'articleBody']),
'author', 'articleBody']), dict(id=['featured-item']),
] ]
remove_tags = [ remove_tags = [
dict(attrs={'class': lambda x: x and set(x.split()).intersection( dict(attrs={'class': lambda x: x and set(x.split()).intersection(
@ -84,11 +79,23 @@ class NewYorker(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img'): for img in soup.findAll('img'):
ds = img['data-src'] try:
ds = img['data-src']
except KeyError:
continue
if ds: if ds:
img['src'] = ds img['src'] = ds
return soup return soup
def postprocess_html(self, soup, *a):
ab = soup.find(id='articleBody')
if ab is not None:
fi = soup.find(id='featured-item')
if fi is not None:
p = fi.parent
p.insert(len(p) - 2, fi)
return soup
# The New Yorker changes the content it delivers based on cookies, so the # The New Yorker changes the content it delivers based on cookies, so the
# following ensures that we send no cookies # following ensures that we send no cookies
def get_browser(self, *args, **kwargs): def get_browser(self, *args, **kwargs):