用python requests库写一个人人网相册爬虫

担心人人网会黄掉，写个爬虫，把我的相册照片都下载下来。代码如下：

# -*- 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)

        return "yes"

    else:

        print path+u' 目录已存在'

        return "no"

def login_renren(s):

    origin_url = 'http://www.renren.com'

    login_data = {

        'email':'用户名',

        'domain':'renren.com',

        'origURL':'http://www.renren.com/home',

        'key_id':'',

        'captcha_type':'web_login',

        'password':'密码抓包获得',

        'rkey':'rkey抓包获得'

    }

    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'

    return s

def get_albums(s):

    r = s.get('http://photo.renren.com/photo/278382090/albumlist/v7?showAll=1#')

    #print r.content

    content = r.content

    index1 = content.find('nx.data.photo = ')

    #print index1

    index2 = content.find('nx.data.hasHiddenAlbum =')

    #print index2

    target_json = content[index1+16:index2].strip()

    target_json = target_json[0:len(target_json)-1]

    #print target_json

    data = json.loads(target_json.replace("\'", '"'));

    album_list = data['albumList']

    album_count = album_list['albumCount']

    tip = u'一共有'+str(album_count)+u'个相册'

    print tip

    album_ids = []

    for album in album_list['albumList']:

        #print album['albumName']

        album_ids.append(album['albumId'])

    return album_ids,s

def download_albums(album_ids,s):

    #访问相册

    for album_id in album_ids:

        album_url = 'http://photo.renren.com/photo/278382090/album-'+album_id+'/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

            if mkdir(album_path)=='yes':

                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()

                    tip = u'相片'+image_name+u'下载成功'

                    print tip

            else:

                print u'相册已经下载'

#执行该文件的主过程

if __name__ == '__main__':

    #创建requests会话

    s = requests.Session()

    #登录人人网

    s = login_renren(s)

    #获取相册列表

    album_ids,s = get_albums(s)

    #下载相册

    download_albums(album_ids,s) 

搞定！运行效果如下：