Python 超级简单的小视频爬虫工具

import requests
from bs4 import BeautifulSoup
import re

url = 'https://ibaotu.com/shipin/7-0-0-0-3-1.html'
resource = requests.get(url)
html = resource.text

soup = BeautifulSoup(html, 'xml')
net_url = soup.find_all('video')

video_url = []

for x in net_url:
    if x.get('src'):
        video_url.append('https:'+x.get('src'))
# print(video_url)

titles = re.findall(r'<span class="video-title">(.*?)</span>', html)

for x,y in zip(titles, video_url):
    try:
        mp4_url = requests.get(y, timeout=10)
    except requests.exceptions.ConnectionError:
        print('出错啦')
        continue
    fn = open('F:\Python\PythonData/'+x+'.mp4', 'wb')
    fn.write(mp4_url.content)
    fn.close()