bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #794 from 553531284/master

Browse Source 
fix javdb xpath
This commit is contained in:
Yoshiko2
2022-05-08 02:49:43 +08:00
committed by GitHub
parent 664e3feedb 47a3560132
commit bdf7f69390
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
WebCrawler/javdb.py
View File

@@ -124,7 +124,7 @@ def getCover_small(html, index=0):
# javdb sometime returns multiple results # javdb sometime returns multiple results
# DO NOT just get the firt one, get the one with correct index number # DO NOT just get the firt one, get the one with correct index number
try: try:
result = html.xpath("//*[@class='movie-list h cols-4']/div/a/div[contains(@class, 'cover')]/img/@src")[index] result = html.xpath("//*[contains(@class,'movie-list')]/div/a/div[contains(@class, 'cover')]/img/@src")[index]
if not 'https' in result: if not 'https' in result:
result = 'https:' + result result = 'https:' + result
return result return result
@@ -242,12 +242,12 @@ def main(number):
# javdb sometime returns multiple results, # javdb sometime returns multiple results,
# and the first elememt maybe not the one we are looking for # and the first elememt maybe not the one we are looking for
# iterate all candidates and find the match one # iterate all candidates and find the match one
urls = html.xpath('//*[@class="movie-list h cols-4"]/div/a/@href') urls = html.xpath('//*[contains(@class,"movie-list")]/div/a/@href')
# 记录一下欧美的ids ['Blacked','Blacked'] # 记录一下欧美的ids ['Blacked','Blacked']
if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number): if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number):
correct_url = urls[0] correct_url = urls[0]
else: else:
ids = html.xpath('//*[@class="movie-list h cols-4"]/div/a/div[contains(@class, "video-title")]/strong/text()') ids = html.xpath('//*[contains(@class,"movie-list")]/div/a/div[contains(@class, "video-title")]/strong/text()')
try: try:
correct_url = urls[ids.index(number)] correct_url = urls[ids.index(number)]
except: except: