基于selenium微博个人主页视频下载

# -*- coding: utf-8 -*-
import selenium
from selenium import webdriver
import time
import urllib.request
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
import re


class WeiBoVdeioDown(object):
    def __init__(self, url, fileName):
        # 设置下载某一个人相册中的视频地址
        self.url = url
        # 设置下载文件本地地址
        self.fileName = fileName

    def __get_fileName_and_down_url(self):
        """
        获得下载视频名称与视频地址
        :return:
        """
        self.driver = webdriver.Firefox()
        self.driver.get(self.url)
        WebDriverWait(self.driver, 200, 0.5).until(
            EC.presence_of_element_located((By.CLASS_NAME, ‘photo_module‘)))
        # 指定像素  var c = document.getElementsByClassName(‘WB_frame‘)[0].scrollHeight=1000
        # js_code = "document.getElementsByClassName(‘WB_frame‘)[0].scrollHeight=8000"
        # self.driver.execute_script(js_code)
        # print("拖动滑动条到底部...")
        # time.sleep(60)
        self.li = self.driver.find_elements_by_class_name(‘photo_module‘)
        # 遍历li得到视频说明与视频连接,并保存
        video_inf = {}
        # 得到第一个窗口的句柄值
        self.fu_handle = self.driver.current_window_handle
        for i in self.li:
            file_name = i.find_element_by_xpath(‘./a/div‘).text
            video_url = i.find_element_by_xpath(‘./a‘).get_attribute(‘href‘)
            print("视频名称：", file_name, "视频连接地址：", video_url)
            # 此处的视频连接地址不是最终的需要在此请求爬取
            if video_url.find("http://video.weibo.com") != -1:
                new_url = self.__get_final_video_url(video_url)
                video_inf[file_name] = new_url
        return video_inf

    def __get_final_video_url(self, url):
        """
        得到最终的视频地址
        :param url:
        :return:
        """
        # 根据url打开新的窗口
        js = "window.open(‘{}‘)".format(url)
        self.driver.execute_script(js)

        # 输出当前窗口的句柄
        # print("当前窗口的句柄：", self.driver.current_window_handle, "ddd:", self.fu_handle)
        # 获取当前窗口句柄集合（列表类型）

        # 得到新的窗口的句柄
        child_handle = None
        handles = self.driver.window_handles
        for handle in handles:
            if handle != self.fu_handle:
                child_handle = handle
        # print("子窗口句柄值：", child_handle)
        # print(handles)  # 输出句柄集合
        # 切换窗口
        self.driver.switch_to.window(child_handle)
        try:
            WebDriverWait(self.driver, 200, 0.5).until(
                EC.presence_of_element_located((By.ID, ‘playerRoom‘)))
            time.sleep(3)
            temp = re.findall(r‘<video src="(.*)"‘, self.driver.page_source)
            if len(temp) > 0:
                final_url = temp[0].replace("amp;", "")
                print("新的地址：ee", "html:" + final_url)
            else:
                final_url = ""
                print("无地址")
            time.sleep(3)
            self.driver.close()
            # 切换回主窗口
            self.driver.switch_to.window(self.fu_handle)
        except:
            final_url = ""

        return "http:" + final_url

    def download(self, url):
        """
        视频下载
        :return:
        """
        msg = self.__get_fileName_and_down_url()
        for file_name, url in msg.items():
            print("fileName:", file_name, "url:", url)
            if len(url) > 0:
                print("正在下载视频{}".format(file_name))
                print("路径：", ‘{}{}.mp4‘.format(self.fileName, file_name))
                urllib.request.urlretrieve(url, ‘{}{}.mp4‘.format(self.fileName, file_name))
        # //f.us.sinaimg.cn/001S2GEdlx07rpeAv93O01041200q03A0E010.mp4?label=mp4_hd&template=844x480.25.0&Expires=1550404650&ssig=kTARYMkU1Y&KID=unistore,video



if __name__ == ‘__main__‘:
    url = "https://weibo.com/p/1005052420864952/photos?type=video#place"  # 个人主页相册中的视频地址（自己可以更改，也可以添加程序来自动爬取）
    aa = WeiBoVdeioDown(url, ‘E:\玉面小嫣然‘) # 创建对象，输入下载地址和本地保存地址，默认保存文件名是微博上面名称
    url1 = "//f.us.sinaimg.cn/001S2GEdlx07rpeAv93O01041200q03A0E010.mp4?label=mp4_hd&template=844x480.25.0&Expires=1550404650&ssig=kTARYMkU1Y&KID=unistore,video"
    # aa.down_url(url)
    aa.download(url)


出现问题： 1、可能会出现异常，这里程序对异常处理不是很合适，可以通过后期对函数中的url地址进行判断，
　　　　　　2、滑动条自动加载，向下滑动，自动加载内容，查看网上解释可以通过以下实现

　　　　　　# js_code = "document.getElementsByClassName(‘WB_frame‘)[0].scrollHeight=8000"
          # self.driver.execute_script(js_code)
其中js_code 是要执行的代码，scrollHeight=10000是滑动到底部，这里测试没有成功，其他页面有些可以成功，似乎是元素找错了，需要找到这个滚动条的真正属于的容器才可以，有兴趣的可以自己去试试

第一次实现，不喜勿

#  下载视频，音乐和图片还可以通过如下实现
import re
url= ‘https://m10.music.126.net/20190218085252/d95768f7ab127a67ba24c1f6cba652e3/ymusic/015f/0f52/0f0b/65259539178803971cd18a5de46cfb76.mp3‘
import requests
r = requests.get(url, stream=True)
with open(‘E:\\a.mp3‘, ‘wb‘) as f:
    for i in r.iter_content(1024):
        f.write(i)

url = ‘http://f.us.sinaimg.cn/001R971olx07re2bg08g01041203HWqe0E020.mp4?label=mp4_720p&template=1268x720.20.0&Expires=1550453293&ssig=CZ7K3Algxi&KID=unistore,video‘
r = requests.get(url, stream=True)
with open(‘E:\\a.mp4‘, ‘wb‘) as f:
    for i in r.iter_content(1024):
        f.write(i)


对于小文件还可以是使用如下下载
with open(‘E:\\a.mp4‘, ‘wb‘) as f: 
　　f.write(r.raw.read()