自己更改cookie的值
from tuozhan_all import get
# 0. url
# 1. 构造headers
# 2. 调用get函数
# 3. 保存页面
url = 'http://www.renren.com/966927992'
headers = {
#'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
#'Accept-Encoding': 'gzip, deflate',
#'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
#'Cache-Control': 'max-age=0',
#'Connection': 'keep-alive',
'Cookie': 'anonymid=jkt0b8ab-q2jf6z; depovince=GW; _r01_=1; JSESSIONID=abcGJgLjV4-TIaBij_1uw; ick_login=9064892c-3ad2-43ae-b884-ed4ebbab6249; jebecookies=868d7d34-c453-40ee-93e8-197b43bdc86a|||||; _de=B996A2060AAF2DDA74DFAFD510163D3F; p=c48fa2c085eb307ad984daa9625fe72b2; first_login_flag=1; ln_uact=18510556963; ln_hurl=http://head.xiaonei.com/photos/0/0/men_main.gif; t=41d3adf9f7f90cd5b1d7bcfd4e3daf3b2; societyguester=41d3adf9f7f90cd5b1d7bcfd4e3daf3b2; id=966927992; xnsid=c97d475f; ver=7.0; loginfrom=null; jebe_key=a34f3f96-cded-4ab0-b18b-def8f814944a%7C65e0c5286f0503e29e3484234097e54d%7C1534217862022%7C1%7C1534217873290; wp_fold=0',
#'Host': 'www.renren.com',
#'Referer': 'http://renren.com/',
#'Upgrade-Insecure-Requests': '1',
#'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
}
html_bytes = get(url, headers=headers)
with open('renren.html', 'wb') as f:
f.write(html_bytes)
自动获取cookie
from tuozhan_all import post, get
import json
from urllib import request, parse
# 保存cookie
from http import cookiejar
# 通过对象保存cookie
cookie_object = cookiejar.CookieJar()
# handler 对应着一个操作
handler = request.HTTPCookieProcessor(cookie_object)
# opener 遇到有cookie的response的时候,调用handler内部的一个函数, 存储到cookie object
opener = request.build_opener(handler)
# def store(cookie):
# cookie_object.append(cookie)
#
# def check_response(response):
# if 'cookie' in response:
# handler.store(response['cookie'])
# url
url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2018721441132'
# form
form = {
'email': '18510556963',
'icode': '',
'origURL': 'http://www.renren.com/home',
'domain': 'renren.com',
'key_id': '1',
'captcha_type': 'web_login',
'password': '95cb2a1d59b918e0d16ab5d3535fb40103e4b546e651a3e3c99b91876927c78a',
'rkey': 'a7bccfbafd7ee702247450942dff5611',
'f': 'http%3A%2F%2Fwww.renren.com%2F966927992',
}
# post
form_bytes = parse.urlencode(form).encode('utf-8')
# response = request.urlopen(url, form_bytes)
# opener = request.build_opener()
# opener.open()
response = opener.open(url, form_bytes)
html_bytes = response.read()
#html_bytes = post(url, form=form)
# 打印结果
#print(html_bytes)
# 通过json获取一个字典类型
res_dict = json.loads(html_bytes.decode('utf-8'))
home_url = res_dict['homeUrl']
# 访问页面
response = opener.open(home_url)
html_bytes = response.read()
print(html_bytes.decode('utf-8'))