爬虫三部曲

标签：发送请求   dex   href   index   时间   glin   item   保护   lis   

import time
import requests
# 爬虫三部曲
# 1.发送请求
def get_page(url):
    response = requests.get(url)
    return response
# 2.解析数据
import re
def parse_index(html):
    # findall匹配所有
    # re.findall(‘正则匹配规则‘，‘匹配文本‘，‘匹配模式‘)
    # re.S:对全部文本进行搜索匹配
    detail_urls = re.findall(
        ‘<div class="items"><a class="imglink" href="(.*?)"‘,
        html,re.S
    )
    #
    # for detail_url in detail_urls:
    #       print(detail_url)
    return detail_urls
#解析详情页
def parse_detail(html):
    movie_url = re.findall(‘<source src="(.*?)">‘,html,re.S)
    #print(movie_url)
    if movie_url:
        return movie_url[0]
#3.保护数据
import uuid
#uuid.uuid4()根据时间戳生成一段世界上唯一的字符串
def save_video(content):
    with open(f‘{uuid.uuid4()}.mp4‘,‘wb‘)as f:
        f.write(content)
        print(‘lllllll‘)
# main + 回车键
# 测试用例:
if __name__== ‘__main__‘:
    for line in range(6):
        url = f‘http://www.xiaohuar.com/list-3-{line}.html‘
        #发送请求
        response = requests.get(url)
        #print(response)
        #返回响应状态码
        # print(response.status_code)
        #print(response.text)
        #解析主页面
        detail_urls = parse_index(response.text)

        #循环遍历详情页url
        for detail_url in detail_urls:
            # peint(detail_url)
            #往每一个详情页发送请求
            detail_res = get_page(detail_url)
            # print(response.text)
            #解析详情页获取视频uel
            movie_url = parse_detail(detail_res.text)
            #判断视频url存在则打印
            if movie_url:
                print(movie_url)
                #往视频url发送请求获取视频二进制流
                movie_res = get_page(movie_url)
                save_video(movie_res.content)

爬虫三部曲

标签：发送请求   dex   href   index   时间   glin   item   保护   lis   

原文地址：https://www.cnblogs.com/yijingjing/p/11116311.html