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

Covers for mit tech review and seminar magazine

Browse Source
This commit is contained in:
Kovid Goyal 2022-05-04 07:20:58 +05:30
parent 38e1594921
commit c64eb65376
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
recipes/mit_technology_review.recipe
View File

@ -50,11 +50,11 @@ class MitTechnologyReview(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
# find cover # find cover
self.cover_url = absurl(soup.find( self.cover_url = soup.find(
"div", attrs={"class":lambda name: name.startswith("magazineHero__image") if name else False}).find( "div", attrs={"class":lambda name: name.startswith("magazineHero__image") if name else False}).find(
"img", "img",
src=True src=True, attrs={"class":lambda x: x.startswith('image__img') if x else False}
)['src']) )['src']
# parse articles # parse articles
current_articles = [] current_articles = []
classNamePrefixes = ["magazineHero__letter--", "teaserItem__title", "teaserItem--aside__title"] classNamePrefixes = ["magazineHero__letter--", "teaserItem__title", "teaserItem--aside__title"]

3
recipes/seminar_magazine.recipe
View File

@ -14,11 +14,12 @@ class Seminar(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
masthead_url = 'https://www.india-seminar.com/semlogo/semlogo_top_1.jpg' masthead_url = 'https://www.india-seminar.com/semlogo/semlogo_top_1.jpg'
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
remove_attributes = ['style', 'height', 'width']
def get_cover_url(self): def get_cover_url(self):
cover_url = None cover_url = None
soup = self.index_to_soup('https://www.india-seminar.com/') soup = self.index_to_soup('https://www.india-seminar.com/')
citem = soup.find('img', src=lambda x: x and x.endswith('cover.png')) citem = soup.find('img', src=lambda x: x and 'covers' in x)
if citem: if citem:
cover_url = "https://www.india-seminar.com/" + citem['src'] cover_url = "https://www.india-seminar.com/" + citem['src']
return cover_url return cover_url