#!/usr/bin/env python
# -*- coding:utf-8 -*-
from selenium import webdriver
import urllib
import urllib.request
import time
# 普通爬蟲,使用Charles抓包獲取網址url,但是西瓜視頻url只能使用一次
# url加密,只能使用selenium獲取數據,瀏覽器
url = 'https://www.ixigua.com/'
driver = webdriver.Chrome()
driver.get(url=url)
time.sleep(2)
video_lists = driver.find_elements_by_xpath('//div[@class="feed-infinite-wrapper"]/ul/li')
print(len(video_lists))
hrefs = []
for video_info in video_lists:
hrefs.append(video_info.find_element_by_xpath('.//a').get_attribute('href'))
def download_video(title, video_url):
urllib.request.urlretrieve(video_url,'./videos/%s.mp4'%(title))
print('視頻:%s下載成功'%(title))
for href in hrefs:
driver.get(href)
time.sleep(2)
video_url = driver.find_element_by_class_name('vjs-tech').get_attribute('src')
title = driver.find_element_by_xpath('//h2[@class="title"]').text
download_video(title,video_url)
input('輸入任意字符,點擊回車退出程序')
driver.quit()