master

分支 (1)

管理

管理

master

machine-study
/
电影天堂.py

import requests
import re

f = open('电影天堂.scv', 'a+', encoding='utf-8')
href = ""
url = "https://www.dy2018.com/"+href
headers = {

}
result = requests.get(url)
result.encoding = 'gb2312'
date = result.text

compiles = re.compile(r'2023必看热片.*?<ul>(?P<html>.*?)</ul>', re.S)
href = re.compile(r"<li><a href='(?P<aurl>.*?)' title=", re.S)

# 详情页的正则表达式
dateils_compile = re.compile(r'<td colspan="2" align="center" valign="top"><div id="Zoom">.*?片　　名'
                             r'(?P<moviename>.*?)<br />.*?<td style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(?P<download>.*?)">', re.S)

movie = compiles.search(date)

# print(movie.group("html"))


aurl = href.finditer(movie.group("html"))

for item in aurl:
    herf = item.group("aurl")
    url = url.strip("/")+herf
    dateils = requests.get(url)
    dateils.encoding = "gb2312"
    scvstr = dateils_compile.search(dateils.text)
    print(scvstr.group("moviename"), scvstr.group("download"))
    break