利用验证码登录豆瓣页面

程序已经过了好久都忘了，所以简单的整理了一下思路。

1.登录豆瓣页面时，带有的是具有图片验证码的登录方式。
首先要拿到登录页面的链接，点击（登录豆瓣）进入登录页面（首先要确保自己有一个豆瓣账号），datas里要写入自己的账号与密码才能登录
datas = {'source':'index_nav','redir':'https://www.douban.com/','form_email':'15532108480','form_password':'228yuhailong','captcha-solution':captcha,'captcha-id':captcha_id}
2.lxml爬取，F12检查找到验证码图片的位置，利用lxml提取，拿到验证码图片并写入（imgs）。
3.lxml取得验证码id---Value（YFhlJDpFopxc14NpzMJCrybn:en）
4.取得豆瓣登录页面链接，利用已有账号进行登录
url = 'https://accounts.douban.com/login'
datas ={'source':'index_nav','redir':'https://www.douban.com/','form_email':'15532108480','form_password':'228yuhailong','captcha-solution':captcha,'captcha-id':captcha_id}
data_encoded = urllib.parse.urlencode(datas).encode(encoding='utf-8')
response = oper.open(url, data_encoded)
content = response.read()
html = content.decode()
5.将html写入

spath = './douban.html'#豆瓣登陆成功后的html
f=open(spath,"w",encoding='utf-8')
f.write(html)
f.close()

6.getImg方法
def getImg(url,imgName):
try:
req_timeout = 5
req = Request(url=url,headers=headers)
f = urlopen(req,None,req_timeout)
pic = f.read()
#pic= Request.get(url, timeout=10)
imgPath = './imgs/%s.jpg'%(imgName)#图片路径存储位置
fp=open(imgPath,'wb')
fp.write(pic)
fp.close()
except Request.exceptions.ConnectionError:
print(u'链接失败')

代码时间

爬虫py文件

import urllib.request
import http.cookiejar
from lxml import etree
from spiderImg import getImg

#添加协议头
head = {
    'Connection': 'Keep-Alive',
    'Accept': 'text/html, application/xhtml+xml, */*',
    'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko'
}

def makeMyOpener(head):
    cj = http.cookiejar.CookieJar()
    opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
    header = []
    for key, value in head.items():
        elem = (key, value)
        header.append(elem)
    opener.addheaders = header
    return opener

oper = makeMyOpener(head)
uop = oper.open('https://accounts.douban.com/login', timeout = 1000)
data = uop.read()
html = data.decode()
'''
spath = './doubanLogin.html'
f=open(spath,"w",encoding='utf-8')
f.write(html)
f.close()
'''
#print(html)
#lxml提取
#得到验证码
selector = etree.HTML(html)
links = selector.xpath('//img[@id="captcha_image"]/@src')#验证码图片的链接
for link in links:
    print(link)
    getImg(link,'captcs')

#得到验证码id
captcha_ids = selector.xpath('//input[@name="captcha-id"]/@value')
captcha_id = 0
for cid in captcha_ids:
    captcha_id = cid
    print(captcha_id)


captcha=input("请输入验证码：")
print(captcha)

url = 'https://accounts.douban.com/login'
datas = {'source':'index_nav','redir':'https://www.douban.com/','form_email':'15532108480','form_password':'228yuhailong','captcha-solution':captcha,'captcha-id':captcha_id}
data_encoded = urllib.parse.urlencode(datas).encode(encoding='utf-8')
response = oper.open(url, data_encoded)
content = response.read()
html = content.decode()
#print(html)

spath = './douban.html'#豆瓣登陆成功后的html
f=open(spath,"w",encoding='utf-8')
f.write(html)
f.close()

方法py文件

# -*- coding: utf-8 -*-
from urllib.request import Request
from urllib.request import urlopen

#添加模拟浏览器协议头
headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}

#url = 'https://ss0.bdstatic.com/94oJfD_bAAcT8t7mm9GUKT-xh_/timg?image&quality=100&size=b4000_4000&sec=1510537362&di=3f1f93bb6bf35c7724e3b5c435528187&src=http://www.zhlzw.com/UploadFiles/Article_UploadFiles/201204/20120412123921838.jpg'

def getImg(url,imgName):
    try:
        req_timeout = 5
        req = Request(url=url,headers=headers)
        f = urlopen(req,None,req_timeout)
        pic = f.read()
        #pic= Request.get(url, timeout=10)
        imgPath = './imgs/%s.jpg'%(imgName)#图片路径存储位置
        fp=open(imgPath,'wb')
        fp.write(pic)
        fp.close()
    except Request.exceptions.ConnectionError:
        print(u'链接失败')
#
# getImg(url,'mm')

说一下方法py文件里注释的几行代码，

这个文件本身就可以拿下图片并存入文件#url是图片链接

getImg（url，‘mm’）链接和存图片时的名字

 

到此为止，利用验证码登录豆瓣完成（一定要注意有一个自己的账号，否则登录不成功）