爬虫入门

功能：
知乎算是对爬虫比较友好的网站了，但是！
现在登陆验证码很恶心，需要点击图中倒立的文字！这让我们这种本来识字就不多的人情何以堪/(ㄒoㄒ)/~~。于是采用替换url参数的方法，换个登陆验证码登陆，验证码需要手动输入。

#coding=utf-8
import urllib2
import re
from bs4 import BeautifulSoup
import requests
import time

url = "https://www.zhihu.com/#signin"
requests.adapters.DEFAULT_RETRIES = 511
###
定义函数，输出验证码
###

def captcha(captcha_data):
    with open("captcha.jpg","wb")as f:
        f.write(captcha_data)
    text = raw_input("请输入验证码：")
    return text

###
通过抓包可以发现，验证码图片是由unix时间戳生成的，于是我们可以自己抓出登陆时的四位数字字母验证码
###
def zhihulogin():
    while True:
        try:
            sess = requests.Session()
            sess.keep_alive = False
            headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36"}

            html = sess.get(url,headers = headers).text
            bs = BeautifulSoup(html,"lxml")

            _xsrf = bs.find("input",attrs={"name":"_xsrf"}).get("value")

            captcha_url = "https://www.zhihu.com/captcha.gif?r=%d&type=login" %(time.time() * 1000)

            captcha_data = sess.get(captcha_url,headers =headers).content
            text = captcha(captcha_data)
            data = {
                "_xsrf":_xsrf,
                "email":email,
                "password":pwd,
                "captcha":text
            }

            response = sess.post("https://www.zhihu.com/login/email",data = data,headers = headers)
            print response.text
            print captcha_url

            print _xsrf
            break
        except:
###
这里不加sleep的话，好像会报ssl最大连接数的错误，具体的错误日志忘了(lll￢ω￢)
###
            time.sleep(5)


if __name__ == "__main__":
    zhihulogin()