漫客栈数据采集学习

import requests

import re

from urllib.parse import urlparse, urlunparse

url = "https://www.mkzhan.com/category/?is_free=1&page=1"

# 发送HTTPS请求

response = requests.get(url)

content = response.text

# 使用正则表达式匹配目标地址和名称

pattern = r'<p class="comic__title"><a href="([^"]+)"[^>]*>(.*?)<\/a><\/p>'

matches = re.findall(pattern, content)

# 打印匹配的地址和名称

for match in matches:

    address = "https://www.mkzhan.com" + match[0]

    name = match[1]

    print("地址:", address)

    print("名称:", name)

    # 发送章节的GET请求

    chapter_response = requests.get(address)

    chapter_content = chapter_response.text

    # 使用正则表达式匹配章节地址和id

    chapter_pattern