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

fixed bug : can't parse atlantic's article images

Browse Source
This commit is contained in:
hehonghui 2020-11-27 12:33:41 +08:00
parent c849f1fc68
commit 614be0d044
2 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
recipes/atlantic.recipe
View File

@ -87,7 +87,12 @@ class TheAtlantic(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-srcset': True}): for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset'].split()[0] #img['src'] = img['data-srcset'].split()[0]
data_srcset = img['data-srcset']
if ',' in data_srcset:
img['src'] = data_srcset.split(',')[0]
else:
img['src'] = data_srcset.split()[0]
for img in soup.findAll('img', attrs={'data-src': True}): for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src'] img['src'] = img['data-src']
return soup return soup

7
recipes/atlantic_com.recipe
View File

@ -87,7 +87,12 @@ class TheAtlantic(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-srcset': True}): for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-srcset'].split()[0] #img['src'] = img['data-srcset'].split()[0]
data_srcset = img['data-srcset']
if ',' in data_srcset:
img['src'] = data_srcset.split(',')[0]
else:
img['src'] = data_srcset.split()[0]
for img in soup.findAll('img', attrs={'data-src': True}): for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src'] img['src'] = img['data-src']
return soup return soup