首页 > 代码库 > 爬虫实现模拟登陆豆瓣

爬虫实现模拟登陆豆瓣

一:

# -*- encoding:utf-8 -*- 

import requests 
from bs4 import BeautifulSoup 
import urllib 
import re 

loginUrl = http://accounts.douban.com/login 
formData={ 
"redir":"http://movie.douban.com/mine?status=collect", 
"form_email":"ewew2150@126.com", 
"form_password":2150306, 
"login":u登录 
} 
headers = {"User-Agent":Mozilla/5.0 (Windows NT 6.1)\AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36} 
r = requests.post(loginUrl,data=http://www.mamicode.com/formData,headers=headers) 
page = r.text 
#print r.url 

‘‘‘‘‘获取验证码图片‘‘‘ 
#利用bs4获取captcha地址 
soup = BeautifulSoup(page,"html.parser") 
captchaAddr = soup.find(img,id=captcha_image)[src]
print captchaAddr
#利用正则表达式获取captcha的ID 
reCaptchaID = r<input type="hidden" name="captcha-id" value="http://www.mamicode.com/(.*?)"/ 
captchaID = re.findall(reCaptchaID,page) 
print captchaID 
#保存到本地
urllib.urlretrieve(captchaAddr,"D:\captcha.jpg") 
captcha = raw_input(please input the captcha:) 

formData[captcha-solution] = captcha 
formData[captcha-id] = captchaID 
print "test"
r = requests.post(loginUrl,data=http://www.mamicode.com/formData,headers=headers) 
page = r.text 
if r.url==http://movie.douban.com/mine?status=collect: 
print Login successfully!!! 
print 我看过的电影,-*60 
#获取看过的电影 
soup = BeautifulSoup(page,"html.parser") 
result = soup.findAll(li,attrs={"class":"title"}) 
#print result 
for item in result: 
print item.find(a).get_text() 
else: 
print "failed!"

 

二:比较好的写法

# -*- encoding:utf-8 -*-  
  
import requests  
from bs4 import BeautifulSoup  
import urllib  
import re  
  
loginUrl = http://accounts.douban.com/login  
formData={  
    "redir":"http://movie.douban.com/mine?status=collect",  
    "form_email":"ewew2150@126.com",  
    "form_password":2150306,  
    "login":u登录  
}  
headers = {"User-Agent":Mozilla/5.0 (Windows NT 6.1)\AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36}  
r = requests.post(loginUrl,data=http://www.mamicode.com/formData,headers=headers)  
page = r.text  
#print r.url  
  
‘‘‘‘‘获取验证码图片‘‘‘  
#利用bs4获取captcha地址  
soup = BeautifulSoup(page,"html.parser")  
captchaAddr = soup.find(img,id=captcha_image)[src]
print captchaAddr
#利用正则表达式获取captcha的ID  
reCaptchaID = r<input type="hidden" name="captcha-id" value="http://www.mamicode.com/(.*?)"/  
captchaID = re.findall(reCaptchaID,page)  
print captchaID  
#保存到本地
urllib.urlretrieve(captchaAddr,"D:\captcha.jpg") 
captcha = raw_input(please input the captcha:)  
  
formData[captcha-solution] = captcha  
formData[captcha-id] = captchaID  
print "test"
r = requests.post(loginUrl,data=http://www.mamicode.com/formData,headers=headers)  
page = r.text  
if r.url==http://movie.douban.com/mine?status=collect:  
    print Login successfully!!!  
    print 我看过的电影,-*60  
    #获取看过的电影  
    soup = BeautifulSoup(page,"html.parser")  
    result = soup.findAll(li,attrs={"class":"title"})  
    #print result  
    for item in result:  
        print item.find(a).get_text()  
else:  
    print "failed!"  

 

爬虫实现模拟登陆豆瓣