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

Fix recipe cover_url for Foreign Affairs, Nature

Browse Source
This commit is contained in:
ping 2023-06-28 13:50:26 +08:00
parent 69ca92de92
commit c1634e6df5
No known key found for this signature in database
GPG Key ID: 6CCF56BCEDD24084
2 changed files with 10 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/foreignaffairs.recipe
View File

@ -6,13 +6,7 @@ import html5lib
import mechanize import mechanize
from lxml import html from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe, classes
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
def as_article(source, log): def as_article(source, log):
@ -155,9 +149,14 @@ class ForeignAffairsRecipe(BasicNewsRecipe):
self.timefmt = u' [%s]' % date self.timefmt = u' [%s]' % date
link = soup.find('link', rel='canonical', href=True)['href'] link = soup.find('link', rel='canonical', href=True)['href']
year, volnum, issue_vol = link.split('/')[-3:] year, volnum, issue_vol = link.split('/')[-3:]
self.cover_url = soup.find(**classes('subscribe-callout-image'))['srcset'].split()[-3] self.cover_url = re.sub(
self.cover_url = self.cover_url.split('?')[0] r"_webp_issue_small_\dx",
self.cover_url = self.cover_url.replace('_webp_issue_small_2x', '_webp_issue_large_2x') "_webp_issue_large_2x",
soup.find(class_="subscribe-callout-image")["srcset"]
.split(",")[0]
.strip()
.split(" ")[0],
)
cls = soup.find('body')['class'] cls = soup.find('body')['class']
if isinstance(cls, (list, tuple)): if isinstance(cls, (list, tuple)):

2
recipes/nature.recipe
View File

@ -51,7 +51,7 @@ class Nature(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.index_to_soup(BASE + '/nature/current-issue') soup = self.index_to_soup(BASE + '/nature/current-issue')
self.cover_url = 'https:' + soup.find( self.cover_url = soup.find(
'img', attrs={'data-test': check_words('issue-cover-image')} 'img', attrs={'data-test': check_words('issue-cover-image')}
)['src'] )['src']
try: try: