参考博客:
https://blog.csdn.net/menghuannvxia/article/details/51333689
代码:
import requests
import re
from urllib.parse import quote
from lxml import etree
import sys
def get_jd_data(keyword):
keyword = quote(keyword) #解码中文
url = "https://search.jd.com/Search?keyword={}&enc=utf-8&qrst=1&rt=1&stop=1&vt=2&bs=1&wq={}&stock=1&psort=3&click=0".format(keyword,keyword)
# print(url)
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:65.0) Gecko/20100101 Firefox/65.0',
'Cookie':'__jda=122270672.1551510490895255034850.1551510491.1551510491.1551510491.1; __jdb=122270672.12.1551510490895255034850|1.1551510491; __jdc=12227