Python爬虫：6_Movie

代码

import requests
import re

domain = 'https://dytt89.com/'

resp = requests.get(domain, verify=False)  # verify=False 去掉安全验证
resp.encoding = 'gb2312'  # 指定字符集,跟网页内的一致
# print(resp.text)

# 拿到li
obj = re.compile(r'2022必看热片.*?<ul>(?P<ul>.*?)</ul>', re.S)
obj1 = re.compile(r"<a href='(?P<href>.*?)'", re.S)
obj2 = re.compile(r'◎片　　名(?P<movie>.*?)<br />.*?<td style="WORD-WRAP: break-word" bgcolor="#fdfddf">'
                  r'<a href="(?P<download>.*?)">', re.S)

ret = obj.finditer(resp.text)
child_list = []
for it in ret:
    ul = it.group('ul')
    ret2 = obj1.finditer(ul)
    for it2 in ret2:
        child_href = domain + it2.group('href').strip('/')
        child_list.append(child_href)

# 请求子页面
for href in child_list:
    child_resp = requests.get(href, verify=False)
    child_resp.encoding = 'gb2312'
    # print(child_resp.text)
    ret3 = obj2.search(child_resp.text)
    print('电影名称：{0} - 下载地址：{1}'.format(ret3.group('movie'), ret3.group('download')))

resp.close()