Itmens/lib.itmens
Itmens/lib.itmens
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

support more google book urls

Browse source
This commit is contained in:
Your Name 2022-07-22 21:30:37 -04:00
parent 5fd6c696d4
commit 03fe53cec9
1 changed files with 8 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
common/scrapers/google.py
View file

@ -28,10 +28,16 @@ class GoogleBooksScraper(AbstractScraper):
@classmethod
def get_effective_url(cls, raw_url):
u = re.match(r"https://books\.google\.com/books\?id=[^&#]+", raw_url)
return u[0] if u else None
# https://books.google.com/books?id=wUHxzgEACAAJ
# https://books.google.com/books/about/%E7%8F%BE%E5%A0%B4%E6%AD%B7%E5%8F%B2.html?id=nvNoAAAAIAAJ
# https://www.google.com/books/edition/_/nvNoAAAAIAAJ?hl=en&gbpv=1
u = re.match(r"https://books\.google\.com/books.*id=([^&#]+)", raw_url)
if not u:
u = re.match(r"https://www\.google\.com/books/edition/[^/]+/([^&#?]+)", raw_url)
return 'https://books.google.com/books?id=' + u[1] if u else None
def scrape(self, url, response=None):
url = self.get_effective_url(url)
m = self.regex.match(url)
if m:
api_url = f'https://www.googleapis.com/books/v1/volumes/{m[1]}'