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

Merge pull request #547 from lededev/cookies-over18

Browse Source 
javdb:always include over18 cookies
This commit is contained in:
Yoshiko2
2021-07-16 17:47:34 +08:00
committed by GitHub
parent 4b6da439e7 f51d91b227
commit e83be4736a
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

@@ -216,7 +216,7 @@ def main(number):
# number = number.upper() # number = number.upper()
number = number.upper() number = number.upper()
cookie_json = './' + javdb_site + '.json' cookie_json = './' + javdb_site + '.json'
javdb_cookies = None javdb_cookies = {'over18':'1', 'theme':'auto', 'locale':'zh'}
# 不加载过期的cookie，javdb登录界面显示为7天免登录，故假定cookie有效期为7天 # 不加载过期的cookie，javdb登录界面显示为7天免登录，故假定cookie有效期为7天
cdays = file_modification_days(cookie_json) cdays = file_modification_days(cookie_json)
if cdays < 7: if cdays < 7:
@@ -229,7 +229,7 @@ def main(number):
javdb_url = 'https://' + javdb_site + '.com/search?q=' + number + '&f=all' javdb_url = 'https://' + javdb_site + '.com/search?q=' + number + '&f=all'
query_result = get_html(javdb_url, cookies=javdb_cookies) query_result = get_html(javdb_url, cookies=javdb_cookies)
except: except:
query_result = get_html('https://javdb.com/search?q=' + number + '&f=all') query_result = get_html('https://javdb.com/search?q=' + number + '&f=all', cookies=javdb_cookies)
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
@@ -251,7 +251,7 @@ def main(number):
javdb_detail_url = 'https://' + javdb_site + '.com' + correct_url javdb_detail_url = 'https://' + javdb_site + '.com' + correct_url
detail_page = get_html(javdb_detail_url, cookies=javdb_cookies) detail_page = get_html(javdb_detail_url, cookies=javdb_cookies)
except: except:
detail_page = get_html('https://' + javdb_site + '.com' + correct_url) detail_page = get_html('https://javdb.com' + correct_url, cookies=javdb_cookies)
# no cut image by default # no cut image by default
imagecut = 3 imagecut = 3