utllib-cookie + utllib-error

utllib-cookie

from os.path import exists
from os import makedirs
from fake_useragent import UserAgent
from urllib import request
from urllib import parse
from http import cookiejar
from hashlib import md5


class UrllibCookie():
    def __init__(self, saveCookieDirPath, url):
        self.saveCookieDirPath = saveCookieDirPath
        self.url = url
        
        self.save()
    
    def getCookieFilePath(self):
        SplitResult = parse.urlsplit(self.url)
        SplitString = ''.join([SplitResult.scheme, '://', SplitResult.hostname])
        
        return self.saveCookieDirPath + '/' + md5(bytes(SplitString, encoding='utf-8')).hexdigest() + '.cookie'
    
    def save(self):
        cookie = cookiejar.MozillaCookieJar()
        handle = request.HTTPCookieProcessor(cookie)
        opener = request.build_opener(handle)
        
        opener.open(self.url)
        cookie.save(self.getCookieFilePath())
    
    def get(self):
        cookie = cookiejar.MozillaCookieJar()
        cookie.load(self.getCookieFilePath())
        
        return cookie


if __name__ == '__main__':
    cookieDirPath = '.cookie'
    
    if not exists(cookieDirPath):
        makedirs(cookieDirPath)
    
    o = UrllibCookie(cookieDirPath, 'https://tieba.baidu.com/index.html?traceid=')
    g = o.get()
    
    print(g)  # <Cookie BAIDUID=558E8D5FE58F96E5A78E9A63E1AE731B:FG=1 for .baidu.com/>

utllib-error

# CY3761 | 2021-11-27 10:30

from urllib import request
from urllib import error

urlItems = [
    'https://www.google.com',  # 国内无法直接访问
    'https://www.google.cn',  # 国内能访问
    'https://movie.douban.com',  # 需要头信息才能正确访问
]

for url in urlItems:
    print(url)
    
    try:
        res = request.urlopen(url)
    except error.HTTPError as e:  # 说明服务器是有能力响应, 只是某种原因拒绝了你的请求
        print(e)
    except error.URLError as e:  # 地址无法访问可能会触发
        print(e)
    else:
        print(res.code, len(res.read()))

utllib一般好用，很多处理需要封装