不可描述片子爬虫案例

import re
import requests
from bs4 import BeautifulSoup


def (url):
    #请求头
    headers = {
        "accept-encoding":"gzip, deflate, br",
        "accept-language":"zh-CN,zh;q=0.9",
        "referer":"https://www.553ca.com/html/1/",
        "user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"
    }
    html = session.get(url=url,headers=headers).text.encode('latin1').decode('utf-8')
    soup = BeautifulSoup(html,"html.parser")
    content = soup.find('div',class_='box-video-list')
    con_list = content.find_all('li','col-md-2 col-sm-3 col-xs-4')
    data = []
    for list in con_list:
        lists = {}
        lists["video_pic"] = list.find('a').get('data-original')   #影片图片
        lists["video_href"] = "https://www.553ca.com"+list.find('a').get('href')  #视频跳转链接
        lists["title"]= list.find('a').get('title')     #影片名称
        data.append(lists)
    return data


#爬取到视频的真实链接
def devio_url(data):
    devio_data =[]
    for i in range(len(data)):
        list = {}
        devio_url = data[i]["video_href"]
        session = requests.session()
        html = session.get(devio_url).text.encode('latin1').decode('utf-8').strip()
        soup = BeautifulSoup(html, "html.parser")
        desc = soup.find_all("script")[18]
        pattern = re.search(' download="(.*)"', str(desc), re.S)[0]
        pat = re.compile('download="(.*)" target="_blank"', re.S)
        devio_url = pat.findall(pattern)[0]
        list["devio_name"] = data[i]["title"]
        list["devio_url"] = devio_url
        devio_data.append(list)
    return devio_data


#把电影下载到本地
def dewnload(devio_data):
    url = devio_data["devio_url"]
    r = requests.get(url, stream=True)
    try:
        with open('D:/爬取视频/%s.mp4'%devio_data["devio_name"], "wb") as mp4:
            for chunk in r.iter_content(chunk_size=1024 * 1024):
                if chunk:
                    mp4.write(chunk)
        return "%s下载完成"%devio_data["devio_name"]
    except:
        return "%s下载失败" % devio_data["devio_name"]

if __name__ == '__main__':
    url = "https://www.553ca.com/html/65/"
    session = requests.session()
    
    data = devio_desc(url)
    # 爬取到视频的真实链接(影片名、影片链接)
    devio_data=devio_url(data)
    #将电影下载到本地
    for i in range(len(devio_data)):
        result=dewnload(devio_data[i])
        print(result)