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

Update source javdb

Browse Source
This commit is contained in:
yoshiko2
2021-07-05 21:51:56 +08:00
parent 1a365457cd
commit 99832367a2
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
WebCrawler/javdb.py
View File

@@ -207,19 +207,19 @@ def getSeries(a):
result2 = str(html.xpath('//strong[contains(text(),"系列")]/../span/a/text()')).strip(" ['']") result2 = str(html.xpath('//strong[contains(text(),"系列")]/../span/a/text()')).strip(" ['']")
return str(result1 + result2).strip('+').replace("', '", '').replace('"', '') return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
javdb_site = "javdb9"
def main(number): def main(number):
javdb_site = ["javdb9", "javdb30"]
try: try:
# if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number).group(): # if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number).group():
# pass # pass
# else: # else:
# number = number.upper() # number = number.upper()
number = number.upper() number = number.upper()
cookie_json = './' + javdb_site + '.json' cookie_json = './javdb.json'
javdb_cookies = None javdb_cookies = None
# 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)
javdb_site = random.choice(javdb_site)
if cdays < 7: if cdays < 7:
javdb_cookies = load_cookies(cookie_json) javdb_cookies = load_cookies(cookie_json)
elif cdays != 9999: elif cdays != 9999:
@@ -230,7 +230,7 @@ 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://javdb9.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