用python requests库写一个人人网相册爬虫

# -*- coding: utf-8 -*-
import requests
import json
import os

def mkdir(path):
    path=path.strip()
    path=path.rstrip("\\")
    isExists=os.path.exists(path)
    if not isExists:
        print path+u‘ 创建成功‘
        os.makedirs(path)
    else:
        print path+u‘ 目录已存在‘

#执行该文件的主过程
if __name__ == ‘__main__‘:
    #创建requests会话
    s = requests.Session()
    #hyg初始url-登录hyg
    origin_url = ‘http://www.renren.com‘
    login_data = {
        ‘email‘:‘账号‘,
        ‘domain‘:‘renren.com‘,
        ‘origURL‘:‘http://www.renren.com/home‘,
        ‘key_id‘:‘1‘,
        ‘captcha_type‘:‘web_login‘,
        ‘password‘:‘通过抓包获取‘,
        ‘rkey‘:‘通过抓包获取‘
    }
    r = s.post("http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2016742045262", data = login_data)
    if ‘true‘ in r.content:
        print u‘登录人人网成功‘
    #访问相册
    albums = [‘album-987919974‘]
    album_url = ‘http://photo.renren.com/photo/278382090/‘+albums[0]+‘/v7‘
    r = s.get(album_url)
    if "photoId" in r.content:
        print u‘进入相册成功‘
        #print r.content
        content = r.content
        index1 = content.find(‘nx.data.photo = ‘)
        print index1
        index2 = content.find(‘; define.config‘)
        print index2
        target_json = content[index1+16:index2].strip()
        target_json = target_json[13:len(target_json)-2]
        print target_json
        data = json.loads(target_json.replace("\‘", ‘"‘));
        photos = data[‘photoList‘]
        album_name = data[‘albumName‘]
        # 定义并创建目录
        album_path = ‘d:\\‘+album_name
        print album_path
        mkdir(album_path)
        for photo in photos:
            #print photo[‘url‘]
            image_name = photo[‘photoId‘]
            photo_url = photo[‘url‘]
            r = requests.get(photo_url)
            image_path = album_path+‘/‘+image_name+‘.jpg‘
            f = open(image_path, ‘wb‘)
            f.write(r.content)
            f.close()