【爬虫完整版】学完可以接任何爬虫副业单！来者不拒！目前B站最完整的python学

P31 最新代码来了，大家可以用我的代码试试

目前只抓取1-10页的，如何有需要大家自己改，但是不是恶意抓取，仅供学习！谢谢！

import dic as dic
import requests
import re
from io import StringIO
import json
from bs4 import BeautifulSoup
import lxml

if __name__ == "__main__":
    for i in range(1, 11):
        url = 'https://www.umei.cc/bizhitupian/meinvbizhi/'
        if i > 1:
            url = 'https://www.umei.cc/bizhitupian/meinvbizhi/' + 'index_' + str(i) + '.htm'
        print(url)
        headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.'
        }
        dic = {
            'href': ''
        }
        response = requests.get(url=url, headers=headers, stream=True)
        response.encoding = 'utf-8'
        page_text = BeautifulSoup(response.text, 'html.parser')
        d_list = page_text.find('div', {'id': 'infinite_scroll'}).find_all('div', class_='title')
        for d in d_list:
            href = 'https://www.umei.cc/' + d.find('a').get('href')
            url1 = href
            headers1 = {
                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.'
            }
            response1 = requests.get(url=url1, headers=headers1, stream=True)
            response1.encoding = 'utf-8'
            page_text1 = BeautifulSoup(response1.text, 'html.parser')
            big = page_text1.find('div', class_='big-pic')
            big_src = big.find('img').get('src')
            print(big_src)