QQ相册下载

注意：只能下载允许访问的用户，设置权限的必须加好友的用户不能获取其私人信息

1.配置环境：

python2.7

selenium-2.40.0

beautifulsoup4-4.6.0

代码解析：

1.生成QQ号，对应的文件夹；

2.登录自己的QQ；

3.访问QQ用户相册，判断是否需要加好友；

4.无权限设置下载相册内容；

5.访问QQ用户说说，下载说说图片内容；

6.释放资源；

7.删除空文件夹。

小白一枚，有不足的地方请指教

#-*- coding:utf-8 -*-
from selenium import webdriver
from time import sleep
import requests
import os
from PIL import Image
from bs4 import BeautifulSoup
import sys
# 保存图片目录
save_file = 'E:/qq_friend/'
#获取相册图片
def login(driver):
    # driver = webdriver.Firefox()
    try:
        driver.find_element_by_id('login_div')
        a = True
    except:
        a = False
    if a == True:
        #浏览器可见登录
        driver.switch_to.frame('login_frame')
        driver.find_element_by_id('switcher_plogin').click()
        driver.find_element_by_id('u').clear()  # 选择用户名框3083567057
        driver.find_element_by_id('u').send_keys('x')
        driver.find_element_by_id('p').clear()
        driver.find_element_by_id('p').send_keys('x')
        driver.implicitly_wait(100)  # 在一个时间范围内智能的等待。
        # driver.execute_script('var button = document.getElementById("login_button")')
        driver.find_element_by_id('login_button').click()
    driver.implicitly_wait(60)
    try:
        driver.find_element_by_id('QM_OwnerInfo_Icon')
        print '允许访问空间'
        b = True
    except:
        b = False
        print '此QQ不允许访问空间'
        # driver.close()
        # driver.quit()
    # if b == True:
    #     loadPic(qq, driver)
    return b
#下载相册中的资源
def loadPic(qq,driver):
    print('====正在访问相册=====')
    try:
        driver.get('http://user.qzone.qq.com/{}/4'.format(qq))
    except:
        print '不予许访问相册'
    driver.implicitly_wait(60)
    driver.find_element_by_id('QM_OwnerInfo_Icon')
    iframe = driver.find_element_by_xpath("//iframe[@name='app_canvas_frame']")#phantomjs对xpath元素定位查找有较好的支持
    driver.switch_to.frame(iframe)
    allowaccess_ls = driver.find_elements_by_xpath("//div[@data-allowaccess='1' and @data-total>'1']")
    for i in range(0,len(allowaccess_ls)):
        driver.implicitly_wait(30)
        allowaccess_ls1 = driver.find_elements_by_xpath("//div[@data-allowaccess='1' and @data-total>'1']/div/a")
            #TODU 无界面不能使用click()
        driver.implicitly_wait(30)  # 在一个时间范围内智能的等待。
        allowaccess_ls1[i].click()
        print '点击可访问的第'+str(i+1)+'个相册'
        img_ls = driver.find_elements_by_css_selector(".j-pl-photoitem-img")
        for j in range(0,len(img_ls)):
                driver.implicitly_wait(30)
                img_ls1 = driver.find_elements_by_css_selector(".j-pl-photoitem-img")
                link = img_ls1[j].get_attribute('src')
                print 'link====',link
                try:
                    dowmloadPic(link, save_file+str(qq)+'/' + str(i) + '_' + str(j) + '_pic.jpg')
                except:
                    print 'picture url error'
                    continue
        driver.implicitly_wait(30)
        driver.back()
     driver.switch_to.default_content()

#下载说说里面的资源
def get_shuoshuo(qq,driver):
        print('====开始下载说说=====')
        try:
            driver.get('http://user.qzone.qq.com/{}/311'.format(qq))
        except:
            print '不予许访问说说'
        driver.switch_to.default_content()
        driver.switch_to.frame('app_canvas_frame')
        hp = driver.find_elements_by_class_name('img-attachments-inner')
        img_number=0
        for ho in hp:
            hq = ho.find_elements_by_tag_name('a')
            for tg in hq:
                try:
                    linkF = tg.get_attribute('href')
                    print('linkF====',linkF[0:-1])
                    # urllib.request.urlretrieve(linkF[0:-1], 'F:/qq_friend/myself/%s.jpg' % str(x))
                    dowmloadPic(linkF[0:-1], save_file+str(qq)+'/' + str(img_number) + '.jpg')
                    img_number += 1
                except:
                    pass

#下载图片
def dowmloadPic(url,save_file):
   try:
    pic = requests.get(url, timeout=20)
    fp = open(save_file.decode('utf-8').encode('cp936'),'wb')
    fp.write(pic.content)
    fp.close()
   except requests.exceptions.ConnectionError:
    pass
#新建文件目录
#参数path：目录文件名
#成功返回1
#失败返回0
def createfile(path):
    # 去除首位空格
    path = path.strip()
    # 去除尾部 \ 符号
    path = path.rstrip("\\")
    # 判断路径是否存在
    # 存在     True
    # 不存在   False
    isExists = os.path.exists(path)
    # 判断结果
    if not isExists:
        # 如果不存在则创建目录
        # 创建目录操作函数
        os.makedirs(path)
        print path + ' 创建成功'
        return True
    else:
        # 如果目录存在则不创建，并提示目录已存在
        print path + ' 目录已存在'
        return False
# 删除不能打开的文件和目录
def delcantopen(dir):
    for root, save_file, files in os.walk(dir):
        for file in files:
            try:
                im = Image.open(root + '//' + file)
            except:
                os.remove(root + '//' + file)
        try:
            os.rmdir(root)#删除不能打开的文件
        except:
            pass
#下载某个范围的QQ数据
def downQQPic(begin,end):
    # driver = webdriver.PhantomJS('E:\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe')
    driver = webdriver.PhantomJS('E:\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe')
    driver.get('http://qzone.qq.com')
    temp = login(driver)
    if temp == True:
      for qq in range(begin,end):
        # 获取qq
        filepath = save_file + str(qq)

        if createfile(filepath) == True:
            try:
                #获取QQ相册图片
                loadPic(qq, driver)
                # 获取qq说说的图片
                get_shuoshuo(qq,driver)
            except:
                continue
    driver.close()
    driver.quit()
if __name__ == '__main__':
    # 随机生成QQ号（1164867801----1164870024）1164869068 =====1223号，已经查看到1164870223 1164880025
    downQQPic(1164880465, 1164890025)
    # 删除空目录、删除不能打开的图片
    delcantopen(save_file)