导入内置模块
urllib.request
urllib.parse
http.cookiejar
ssl
socket
gzip
random
uas.py模块
"""
@reated: 2022/3/25 Fri.
@by: MR.N
@blog: https://blog.csdn.net/qq_21264377
@version: 1.0
"""
user_agent_list = [
'Mozilla/5.0 (Linux; Android 7.0; SM-G892A Build/NRD90M; wv) '
'AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/67.0.3396.87 Mobile Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1',
'Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) '
'Chrome/20.0.1132.57 Safari/536.11',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) '
'Chrome/19.0.1063.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3',
'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3',
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24',
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) '
'Chrome/19.0.1055.1 Safari/535.24'
]
httpkit.py模块
常量
SOCKET_TIMEOUT
SOCKET_TIMEOUT = 30
HTTPS_TIMEOUT
HTTPS_TIMEOUT = 7
函数
valid_https
def valid_https(url=None):
if url is None:
return False
if '/' not in url:
return False
paths = url.split('/')
if paths[0] not in ['http:', 'https:']:
return False
if paths[1] != '':
return False
if paths[2] is None:
return False
if '.' not in paths[2]:
return False
host_paths = paths[2].split('.')
if len(host_paths) < 2:
return False
return True
split_path
def split_path(url, separator='/'):
return url.split(separator)
get_host
def get_host(paths):
host = '/'.join