屠戮電影天堂（結(jié)合老師視頻代碼，又通過GPT優(yōu)化了代碼，jupyter notebook內(nèi)可以正常運(yùn)行）

import requests

import re

import csv

import pandas as pd

# 設(shè)置請求頭

headers = {

??"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.62"

}

# 發(fā)送請求獲取主頁內(nèi)容

url = "https://www.dytt89.com"

response = requests.get(url, headers=headers)

response.encoding = 'gb2312'

# 使用正則表達(dá)式提取子頁面鏈接和電影信息

obj1 = re.compile(r'2023必看熱片.*?<ul>(?P<ul>.*?)</ul>', re.S)

obj2 = re.compile(r'<a href=(?P<href>.*?) ', re.S)

obj3 = re.compile(r'◎片 名(?P<movie>.*?)<br />.*?<td '

?????????r'style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(?P<download>.*?)">', re.S)

result1 = obj1.finditer(response.text)

child_href_list = []

# 提取子頁面鏈接

for it in result1:

??ul = it.group('ul')

???

??result2 = obj2.finditer(ul)

??for itt in result2:

????child_href = url + itt.group('href').strip("/").strip("'")

????child_href_list.append(child_href)

movies = []

# 提取子頁面內(nèi)容并保存電影信息

for href in child_href_list:

??child_response = requests.get(href)

??child_response.encoding = 'gb2312'

???

??result3 = obj3.search(child_response.text)

??movie = result3.group('movie').strip()

??download_link = result3.group('download').strip()

???

??movies.append({'電影': movie, '下載鏈接': download_link})

# 將電影信息保存為DataFrame

df = pd.DataFrame(movies)

# 保存為CSV文件

filename = 'movies.csv'

df.to_csv(filename, index=False, encoding='utf-8-sig')

print(f"電影信息已成功保存到 {filename} 文件中。")