Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

get the economist cover url from json

Browse Source
This commit is contained in:
xxyzz 2021-03-27 18:10:22 +08:00
parent 57302df132
commit 84741b17df
No known key found for this signature in database
GPG Key ID: F796163E6DCFEE9D
2 changed files with 6 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
recipes/economist.recipe
View File

@ -264,20 +264,9 @@ class Economist(BasicNewsRecipe):
return ans
def economist_parse_index(self, soup):
img = None
if edition_date:
archive_url = "https://www.economist.com/weeklyedition/archive?year={}".format(edition_date[:4])
archive = self.index_to_soup(archive_url)
q = edition_date.replace('-', '')
q = '/print-covers/{}_'.format(q)
img = archive.find('img', srcset=lambda x: x and q in x)
else:
archive = self.index_to_soup("https://www.economist.com/weeklyedition/archive")
div = archive.find(attrs={'class': 'edition-teaser__image'})
if div is not None:
img = div.find('img', srcset=True)
if img:
self.cover_url = img['srcset'].split(',')[-1].split()[0]
if (tag := soup.select_one("script#__NEXT_DATA__")) is not None:
data = json.loads(tag.string)
self.cover_url = data['props']['pageProps']['content']['image']['main']['url']['canonical']
self.log('Got cover:', self.cover_url)
feeds = []
for section in soup.findAll(**classes('layout-weekly-edition-section')):

17
recipes/economist_free.recipe
View File

@ -264,20 +264,9 @@ class Economist(BasicNewsRecipe):
return ans
def economist_parse_index(self, soup):
img = None
if edition_date:
archive_url = "https://www.economist.com/weeklyedition/archive?year={}".format(edition_date[:4])
archive = self.index_to_soup(archive_url)
q = edition_date.replace('-', '')
q = '/print-covers/{}_'.format(q)
img = archive.find('img', srcset=lambda x: x and q in x)
else:
archive = self.index_to_soup("https://www.economist.com/weeklyedition/archive")
div = archive.find(attrs={'class': 'edition-teaser__image'})
if div is not None:
img = div.find('img', srcset=True)
if img:
self.cover_url = img['srcset'].split(',')[-1].split()[0]
if (tag := soup.select_one("script#__NEXT_DATA__")) is not None:
data = json.loads(tag.string)
self.cover_url = data['props']['pageProps']['content']['image']['main']['url']['canonical']
self.log('Got cover:', self.cover_url)
feeds = []
for section in soup.findAll(**classes('layout-weekly-edition-section')):