Itmens/lib.itmens
Itmens/lib.itmens
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

fix imdb link parsing for DoubanMovie

Browse source
This commit is contained in:
doubaniux 2021-10-08 18:09:30 -04:00
parent 7a088d2a62
commit dfe0c3b4e2
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
common/scraper.py
View file

@ -450,6 +450,9 @@ class DoubanMovieScraper(DoubanScrapperMixin, AbstractScraper):
imdb_elem = content.xpath(
"//div[@id='info']//span[text()='IMDb链接:']/following-sibling::a[1]/text()")
if not imdb_elem:
imdb_elem = content.xpath(
"//div[@id='info']//span[text()='IMDb:']/following-sibling::text()[1]")
imdb_code = imdb_elem[0].strip() if imdb_elem else None
director_elem = content.xpath(