Python爬蟲帶用戶名密碼登錄

# -*- coding: utf-8 -*-
"""
Created on Wed Jun  6 13:18:58 2018

@author: Lenovo
"""

# -*- coding: utf-8 -*-

import requests
import urllib
import random
from datetime import datetime
# python2 和 python3的兼容代碼
try:
    # python2 中
    import cookielib
    print(f"user cookielib in python2.")
except:
    # python3 中
    import http.cookiejar as cookielib
    print(f"user cookielib in python3.")

# session代表某一次連接
huihuSession = requests.session()
# 因為原始的session.cookies 沒有save()方法，所以需要用到cookielib中的方法LWPCookieJar，這個類實例化的cookie對象，就可以直接調用save方法。
huihuSession.cookies = cookielib.LWPCookieJar(filename = "huihuCookies.txt")

userAgent = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36"
header = {
    # "origin": "https://passport.huihu.cn",
    "Referer": "http://hh.haiper.com.cn/w/wander/user/login/",
    'User-Agent': userAgent,
}

def huihuLogin(account, password):
    # 
    print ("開始模擬登錄嘻嘻嘻")

    postUrl = "http://hh.haiper.com.cn/w/wander/user/login/"
    postData = {
        "username": account,
        "password": password,
    }
    
    # 使用session直接post請求
    responseRes = huihuSession.post(postUrl, data = postData, headers = header)
    # 無論是否登錄成功，狀態碼一般都是 statusCode = 200    
    #responseRes = requests.post(postUrl, data = postData, headers = header)
    # 無論是否登錄成功，狀態碼一般都是 statusCode = 200
    print(f"statusCode = {responseRes.status_code}")
    #print(f"text = {responseRes.text}")
    huihuSession.cookies.save()
def isLoginStatus():
    # 通過訪問個人中心頁面的返回狀態碼來判斷是否為登錄狀態
    for i in range(2131,2134):
        routeUrl = "http://hh.haiper.com.cn/w/bench/extend/health/trade/all?nickname=&type=&gender=&level=&range%5Bstart%5D=2014-11-11+14%3A57&range%5Bend%5D=2018-06-06+14%3A57&page="+str(i)
        
    # 下面有兩個關鍵點
        # 第一個是header，如果不設置，會返回500的錯誤
        # 第二個是allow_redirects，如果不設置，session訪問時，服務器返回302，
        # 然后session會自動重定向到登錄頁面，獲取到登錄頁面之后，變成200的狀態碼
        # allow_redirects = False  就是不允許重定向
        try:
            responseRes = huihuSession.get(routeUrl, headers = header, allow_redirects = False)
            result = responseRes.text
        except:
            continue
        start = result.find('<div class="form-control-static form-control-static-list">')
        result = result[start:]
        #print (result)
        for j in range(1,16):
            start = result.find('擦擦擦圖片')
            if start==-1:
                break
            else:
                result = result[start:]
                start = result.find('src="')
                result = result[start+5:]
                end = result.find('" class="img-rounded"')
                imgpath = result[:end]
                print (imgpath)
                if imgpath=='/attachment/':
                    continue
                randomname = datetime.now().strftime("%Y%m%d_%H%M%S") + str(random.randint(1,100))+'.jpg'
                try:
                    urllib.request.urlretrieve(imgpath,'./擦擦擦/'+randomname)
                except:
                    continue
        print (i)
    print(f"isLoginStatus = {responseRes.status_code}")
        #print(f"text = {responseRes.text}")
    if responseRes.status_code != 200:
        return False
    else:
        return True
if __name__ == "__main__":
    # 從返回結果來看，有登錄成功
    huihuLogin("xxxx", "xxxx")
    isLogin1 = isLoginStatus()
    print(f"is login huihu = {isLogin1}")