咳咳直接上代碼

#!/usr/bin/env python # -*- coding: utf-8 -*- # @Time : 2021/01/04 18:10 # @Author : 志偉 # @File : 圖庫大全1000.py # @Software: PyCharm import requests from lxml import etree import osif __name__ == '__main__':headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36'}m_path = './1000圖庫'if not os.path.exists(m_path):os.mkdir(m_path)for i in range(1, 2):url = f'https://www.1000tuku.com/guoneimeinv/list_5_{i}.html'resp = requests.get(url=url, headers=headers).texttree = etree.HTML(resp)href_list = tree.xpath('/html/body/div[4]/ul//@href')for href in href_list:resp1 = requests.get(url=href, headers=headers)# 處理中文亂碼問題resp1_text = resp1.text.encode('ISO-8859-1').decode('GB18030')tree1 = etree.HTML(resp1_text)page_num = int(tree1.xpath('//*[@id="content"]/div[1]/div[2]/ul/li[1]/a/text()')[0][1:3])title = tree1.xpath('/html/head/title/text()')[0]title_path = m_path + f'/{title}'if not os.path.exists(title_path):os.mkdir(title_path)for j in range(1, page_num + 1):if j == 1:every_herf = hrefelse:every_herf = href.replace('.html', f'_{j}.html')resp2 = requests.get(url=every_herf, headers=headers).texttree2 = etree.HTML(resp2)src_list = tree2.xpath('//*[@id="content"]/div[1]/div[1]//@src')for src in src_list:jpg_data = requests.get(url=src, headers=headers).contentjpg_name = src.split('/')[-1]jpg_path = title_path + f'/{jpg_name}'with open(jpg_path, 'wb') as fp:fp.write(jpg_data)print(jpg_name, '下載完成')

咳咳,看看效果

放學(xué)啦,回家吃飯去吧

總結(jié)

以上是生活随笔為你收集整理的Python爬虫_宅男福利?妹纸勿点__一蓑烟雨任平生的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。