python爬虫入门练习——爬酷6网视频

'''
    爬虫爬酷6网视频练习
    version：01
    author：jasn
    Date:2020-02-18
'''

import requests
import re

filepath = r'C:\Users\Administrator\Desktop\Day\Jasn--70--Days\爬虫\Day 01\res\酷6视频' # 视频保存地址
i = 0  # 计数器

# 发送请求,获取相应内容
def get_page(index_url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"
    }
    request = requests.get(index_url, headers=headers)
    if request.status_code == 200:
        return request.text


# 解析视频列表页面数据，拿到视频内页url
def get_content(res):
    detail_urls = re.findall('class="video-image-warp".*?href="(.*?)">', res)
    for url in detail_urls:
        if url.startswith('/video'):
            url = r'https://www.ku6.com' + url
            yield url


# 解析视频内页数据，获取视频下载url
def parse_videos(detail_url):
    l = re.findall('type: "video/mp4", src: "(.*?)"', detail_url)
    if l:
        new_videos = l[0]
        yield new_videos


# 下载视频保存到本地
def get_videos(url, i):
    try:
        print('下载视频链接：%s' % url)
        request = requests.get(url)
        if request.status_code == 200:
            print('开始下载')
            name = 'ku6_'+str(i)
            with open(r'%s/%s.mp4' % (filepath, name), 'wb')as f:
                f.write(request.content)
                print('下载 %s.mp4 成功' % name)
    except Exception:
        print('链接超时！')



if __name__ == '__main__':
    res = get_page('https://www.ku6.com/index')
    videos_url = get_content(res)
    for video_url in videos_url:
        detail_url = get_page(video_url)
        movie_url = parse_videos(detail_url)
        for url in movie_url:
            i = i+1
            get_videos(url, i)

See you next time!