python - 爬蟲模擬登錄后，爬取csdn后臺文章列表遇到的問題
問題描述
爬蟲確實(shí)已經(jīng)登錄進(jìn)去了，因?yàn)槲遗廊€(gè)人信息是可以抓出來的，但是下圖的這個(gè)網(wǎng)址抓不出來：
網(wǎng)址是：http://write.blog.csdn.net/postlist，就是你的csdn后臺。
我貼下代碼吧，py2.7的
#!/usr/bin/env python# -*- coding: utf-8 -*-from bs4 import BeautifulSoupimport requestsclass CSDN(object): def __init__(self, headers):self.session = requests.Session()self.headers = headers def get_webflow(self):url = ’http://passport.csdn.net/account/login’response = self.session.get(url=url, headers=self.headers)soup = BeautifulSoup(response.text, ’html.parser’)lt = soup.find(’input’, {’name’: ’lt’})[’value’]execution = soup.find(’input’, {’name’: ’execution’})[’value’]soup.clear()return (lt, execution) def login(self, account, password):self.username = accountself.password = passwordlt, execution = self.get_webflow()data = { ’username’: account, ’password’: password, ’lt’: lt, ’execution’: execution, ’_eventId’: ’submit’}url = ’http://passport.csdn.net/account/login’response = self.session.post(url=url, headers=self.headers, data=data)if (response.status_code == 200): print(’正?！?else: print(’異常’) def func(self):headers1={ ’Host’:’write.blog.csdn.net’, ’Upgrade-Insecure-Requests’:’1’, ’User-Agent’:’Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36’}response=self.session.get(url=’http://write.blog.csdn.net/postlist’,headers=headers1,allow_redirects=False)print response.textif __name__ == ’__main__’: headers = {’Host’: ’passport.csdn.net’,’Origin’: ’http://passport.csdn.net’,’Referer’:’http://passport.csdn.net/account/login’,’Upgrade-Insecure-Requests’:’1’,’User-Agent’: ’Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36’, } csdn = CSDN(headers=headers) account = ’’ password = ’’ csdn.login(account=account, password=password) csdn.func()
上面的代碼輸出是
正常<html><head><title>Object moved</title></head><body><h2>Object moved to <a >here</a>.</h2></body></html>
問題解答
回答1：因?yàn)檫@個(gè)地址返回的是一個(gè)302跳轉(zhuǎn)，你要根據(jù)返回header的Location繼續(xù)請求，再分析返回的內(nèi)容繼續(xù)處理，瀏覽器幫你做了這些302跳轉(zhuǎn)和執(zhí)行返回的js等內(nèi)容，手工抓取就需要自己處理．
回答2：直接用cookie即可
網(wǎng)公網(wǎng)安備