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

Fix javdb source

Browse Source
This commit is contained in:
yoshiko2
2021-04-25 20:26:42 +08:00
parent 746602f6d6
commit ca198ff8be
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

@@ -197,9 +197,9 @@ def main(number):
# number = number.upper() # number = number.upper()
number = number.upper() number = number.upper()
try: try:
query_result = get_html('https://javdb.com/search?q=' + number + '&f=all') query_result = get_html('https://javdb8.com/search?q=' + number + '&f=all')
except: except:
query_result = get_html('https://javdb4.com/search?q=' + number + '&f=all') query_result = get_html('https://javdb.com/search?q=' + number + '&f=all')
html = etree.fromstring(query_result, etree.HTMLParser()) # //table/tr[1]/td[1]/text() html = etree.fromstring(query_result, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
# 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
@@ -211,7 +211,7 @@ def main(number):
else: else:
ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()') ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
correct_url = urls[ids.index(number)] correct_url = urls[ids.index(number)]
detail_page = get_html('https://javdb.com' + correct_url) detail_page = get_html('https://javdb8.com' + correct_url)
# no cut image by default # no cut image by default
imagecut = 3 imagecut = 3