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

typo

Browse Source
This commit is contained in:
jnozsc 2020-02-17 21:51:09 -08:00
parent 8dc9be12cc
commit 06de0232a1
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
javdb.py
View File

@ -61,7 +61,7 @@ def getTag(a):
return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',') return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
def getCover_small(a, index=0): def getCover_small(a, index=0):
# same issue mentioned below, # same issue mentioned below,
# javdb sometime returns multiple result # 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
html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() html = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text()
result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index] result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
@ -86,7 +86,7 @@ def main(number):
number = number.upper() number = number.upper()
query_result = get_html('https://javdb.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 result, # 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('//*[@id="videos"]/div/div/a/@href') urls = html.xpath('//*[@id="videos"]/div/div/a/@href')