下厨房网站图片爬虫

# -*- coding:utf-8 -*-
import os
import requests
import urllib
from pyquery import PyQuery
import uuid

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome"
                  "/75.0.3770.142 Safari/537.36"
}


def href_url_download():
    # 1.填写要爬取关键词的list.txt
    keyword_list = open("list.txt", 'r', encoding='utf-8')
    lines = keyword_list.readlines()
    keyword_list.close()
    for keyword in lines:
        keyword = keyword.strip()
        print(keyword)
        # 2.修改爬取的页数(1,14),默认爬取13页
        for pages in range(1, 14):
            page = str(pages)
            # https://www.xiachufang.com/search/?keyword=华夫饼&cat=1001&page=2
            url = "https://www.xiachufang.com/search/?keyword=" + keyword + "&cat=1001&page= " + page
            # print(url)
            try:
                txt = requests.get(url, headers=headers).text
                doc = PyQuery(txt)
                # print(d

标签：keyword,下厨房,网站,list,爬虫,url,import,txt,page
来源： https://blog.csdn.net/weixin_38185649/article/details/100746880