# -*- coding: utf-8 -*-
import os
import re
import time
from urllib.parse import urlencode
import requests
from lxml import etree
import pymysql
from time import strftime, gmtime
# 方法二,从本地文件夹获取
def get_html(keywords, page):
he = {
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'cookie': ,
'referer': ,
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'x-requested-with': 'XMLHttpRequest',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36'
}
url = 'https://search.jd.com/Search?keyword=' + keywords + \
'&qrst=1&stock=1&page=' + str(page) +
python 爬取京东商品信息
最新推荐文章于 2024-05-13 00:44:01 发布