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

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2024-03-02 09:51:18 +05:30
commit a874ee037d
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
3 changed files with 21 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
recipes/new_york_review_of_books.recipe
View File

@ -62,7 +62,7 @@ class NewYorkReviewOfBooks(BasicNewsRecipe):
# Find cover
cover = soup.find('img', attrs={'class':'border-light-gray'})
if cover is not None:
self.cover_url = absurl(cover['src'])
self.cover_url = absurl(cover['data-lazy-src'])
self.log('Found cover at:', self.cover_url)
# Find date
@ -91,3 +91,8 @@ class NewYorkReviewOfBooks(BasicNewsRecipe):
'description': desc})
return [('Current Issue', articles)]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-lazy-src':True}):
img['src'] = img['data-lazy-src']
return soup

7
recipes/new_york_review_of_books_no_sub.recipe
View File

@ -52,7 +52,7 @@ class NewYorkReviewOfBooks(BasicNewsRecipe):
# Find cover
cover = soup.find('img', attrs={'class':'border-light-gray'})
if cover is not None:
self.cover_url = absurl(cover['src'])
self.cover_url = absurl(cover['data-lazy-src'])
self.log('Found cover at:', self.cover_url)
# Find date
@ -81,3 +81,8 @@ class NewYorkReviewOfBooks(BasicNewsRecipe):
'description': desc})
return [('Current Issue', articles)]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-lazy-src':True}):
img['src'] = img['data-lazy-src']
return soup

16
recipes/scientific_american.recipe
View File

@ -67,22 +67,24 @@ class ScientificAmerican(BasicNewsRecipe):
if not curr_issue_link:
self.abort_recipe_processing("Unable to find issue link")
issue_url = 'https://www.scientificamerican.com' + curr_issue_link.a["href"]
# for past editions https://www.scientificamerican.com/archive/issues/
# issue_url = 'https://www.scientificamerican.com/issue/sa/2024/01-01/'
soup = self.index_to_soup(issue_url)
script = soup.find("script", id="__NEXT_DATA__")
script = soup.find("script", id="__DATA__")
if not script:
self.abort_recipe_processing("Unable to find script")
JSON = script.contents[0].split('JSON.parse(`')[1].replace("\\\\", "\\")
data = json.JSONDecoder().raw_decode(JSON)[0]
issue_info = (
json.loads(script.contents[0])
.get("props", {})
.get("pageProps", {})
.get("issue", {})
data
.get("initialData", {})
.get("issueData", {})
)
if not issue_info:
self.abort_recipe_processing("Unable to find issue info")
image_id, ext = splitext(issue_info["image"])
self.cover_url = f"https://static.scientificamerican.com/sciam/cache/file/{image_id}_source{ext}?w=800"
self.cover_url = issue_info["image_url"] + "?w=800"
edition_date = datetime.strptime(issue_info["issue_date"], "%Y-%m-%d")
self.timefmt = f" [{edition_date:%B %Y}]"