svg矢量图批量下载翻页物品爬虫程序代码QZQ1

import requests import json import os import re import time # 新增用于控制请求延迟 from lxml import etree # 1. 关键从浏览器复制完整的 Cookie 和 Headers headers { User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36 Edg/150.0.0.0, Referer: https://freesvglab.com/zh/svg/line-art-rooster-farm, # 关键完整的Cookie字符串从浏览器F12复制 Cookie: cf_clearance4HDa3sVuwMymqY0Jo9YUBFmSKT8qa4w7eXaBJveQUB8-1785585211-1.2.1.1-HNzZBo.2P6oXd.AcezEbmv63.DaYC4YWvsA0iX_PrVu5MiyoAkPcuDmtkyXwWXb49EvP5QbvhJo3sFzpxRDvNOez2dZlVnkwOjI_I4TatyPHqHWGSCpVc.ENcwzHFd115j1Sn4XXEWRqYbmrv3lGQfS4khPbynrWle3GFPtGL9IV_SDZjMWyN1xTpYoDM97q9elLpyeFlMFJqY5uK7060rpjEyfnYAQ62JNTgLxOxo0hu5vxM0nqdrZk9edLV9MayTRPzxAByKxw0yPmIdM0CMaxm9y4jxfkiq0VTSJH2njvrefkwcdqYj7I3XrDvYc49vT5._KCMRx3ln9ZxX.Zx0k8VNc7bRO.Qatu3pVlqCk; _gaGA1.1.1678275870.1785585329; _ga_P3K7XNCWBJGS2.1.s1785585329$o1$g1$t1785585461$j35$l0$h0 } # 创建一个文件夹用于存放视频片段取名为物品 if not os.path.exists(物品): os.mkdir(物品) for page in range(1,6): print(f--------- 正在爬取第{page}页的内容 ----------) # if page1: # url https://freesvglab.com/zh/category/objects/page/1/ # 请求地址 # else: # url fhttps://freesvglab.com/zh/category/objects/page/{page}.html # 请求地址 # 第36行修正 - 统一使用 /page/{page}/ if page 1: url https://freesvglab.com/zh/category/objects/ # 第1页 else: url fhttps://freesvglab.com/zh/category/objects/page/{page}/ # 第2页开始 #https://freesvglab.com/zh/category/objects/page/2 # url fhttps://freesvglab.com/zh/category/objects response requests.get(urlurl, headersheaders).text # print(response.text) # html_datare.findall(url:(.*?)},response.text) # print(html_data) # 使用XPath解析页面 page_html etree.HTML(response) # 提取歌曲列表信息 # id_list page_html.xpath(//html/body/main/div[2]/a[*]) # id_list page_html.xpath(//html/body/main/div[2]/a[*]/href) id_list page_html.xpath(//html/body/main/div[2]/a/href) # print(id_list) # 解析歌曲列表信息并逐个提交下载任务到线程池 for n in id_list: i https://freesvglab.com n # print(i) # /html/body/main/div[2]/a[2] # https://freesvglab.com/zh/svg/logo-lantern res requests.get(url i, headersheaders).text # print(res) # 使用XPath解析页面 page_html etree.HTML(res) # # 提取歌曲列表信息 # # id_list page_html.xpath(//html/body/main/div[2]/a[*]) # d page_html.xpath(//html/body/main/article/div[2]/div[2]/a[2]/href)[0] # print(d) n page_html.xpath(//html/body/main/article/div[2]/div[1]/h1/text())[0] # print(n) # break u https://freesvglab.com d # //html/body/main/article/div[2]/div[2]/a[1] # //html/body/main/article/div[2]/div[2]/a[2]/href # https://freesvglab.com/images/vectors/logo/lantern.svg # 判断文件是否已经存在 # break # file_path os.path.join(物品, n .svg) file_path os.path.join(物品, f{n}_{int(time.time())}.svg) response requests.get(urlu, headersheaders).content with open(file_path, wb) as f: f.write(response) print(n, 下载完成) # //html/body/main/article/div[2]/div[1]/h1/text()