爬和卓照片

#!/usr/bin/env python
#coding:utf-8
import urllib.request
import urllib.parse
import http.cookiejar
import re
import random
import time
import os

rex = '"url":"http:.*?jpg"'
rex2 = "'albumName':'.*?',"
page = 1
isLoadEnd = False
albumIds = ["225325744"]

def login():
    #这个地址是在network中监控的真实提交表单的地址
    url = "http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=20171011315479"
    postdata = urllib.parse.urlencode({
        "email":"[email protected]",
        "password":"wangxun0902"
    }).encode('utf-8')
    req = urllib.request.Request(url, postdata)

    # randdom_header = random.choice(my_headers)
    # req.add_header("User-Agent",randdom_header)
    #使用http.cookiejar.CookieJar()创建CookieJar对象
    cjar = http.cookiejar.CookieJar()
    #使用HTTPCookieProcessor创建cookie处理器，并以其为参数构造opener
    opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cjar))
    #安装为全局opener
    urllib.request.install_opener(opener)
    file = opener.open(req)
    # data = file.read()
    # file = open("/Users/xunwang/Desktop/python/Demo1.5.html", "wb")
    # file.write(data)
    # file.close()

def pachong(albumId,upage,picFileDir):
    # url2 = "http://photo.renren.com/photo/240205043/album-267052848/v7"
    url2 = "http://photo.renren.com/photo/235602297/album-" + albumId + "/bypage/ajax/v7?page=" + str(upage) + "&pageSize=100&requestToken=2078225833&_rtk=47a03403;"
    data2 = urllib.request.urlopen(url2).read()
    data2 = data2.decode('utf-8')
    print(url2) 

    global isLoadEnd
    global page
    imgre = re.compile(rex)
    imglist = re.findall(imgre,data2)
    size = len(imglist)
    print(size)
    print(page)
    if size != 100:
        isLoadEnd = True
    else:
        page = page + 1
    print(isLoadEnd)
    # exit()

    y = 0

    opener=urllib.request.build_opener()
    opener.addheaders=[('User-Agent','Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36')]#'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
    urllib.request.install_opener(opener)

    for imgurl in imglist:
        #time.sleep(5)
        # new_header = random.choice(my_headers)
        #print("new_header --> " + new_header)

        # opener=urllib.request.build_opener()
        # opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
        # urllib.request.install_opener(opener)
        
        rimageurl = imgurl[7:-1].replace('\\','')
        z = rimageurl[-20:-4]
        y = y + 1
        print("rimageurl --> " + rimageurl + " y --> " + str(y) + " z --> " + str(z) + " page --> " + str(page))
        urllib.request.urlretrieve(rimageurl, picFileDir + '/s_%s_%s_%s.jpg' % (str(page),str(y),str(z)))

    # print(imglist)

def makePicFileDir(albumId):
    url3 = "http://photo.renren.com/photo/235602297/album-" + albumId + "/v7"
    data3 = urllib.request.urlopen(url3).read()
    data3 = data3.decode('utf-8')
    imgre3 = re.compile(rex2)
    print("imgre3:" + str(imgre3) + "  data3:" + data3)
    imglist3 = re.findall(imgre3,data3)
    print(imglist3[0])
    albumName = imglist3[0][13:-2]
    print(albumName)
    albumPicPath = "/Users/wangxun/Desktop/python/imgs/" + albumName
    os.makedirs(albumPicPath)
    return albumPicPath
    # exit()

if __name__=='__main__':
    # login()
    for albumId in albumIds:
        isLoadEnd = False
        page = 1
        login()
        picFileDir = makePicFileDir(albumId)
        while(isLoadEnd == False):
            login()
            pachong(albumId,page,picFileDir)