川菜

import redis
import requests
from lxml import etree
def get_xpath_by_requests(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',

    }
    response = requests.get(url,headers=headers)
    if response.status_code==200:
        # print(response.text)
        return etree.HTML(response.text)
def get_text(text):
    if text:
        return text[0]
    return ''
def parse_caixi(url):
    re = redis.Redis()
    html = get_xpath_by_requests(url)
    infos = get_text(html.xpath('//span[@class="gopage"]/form/text()'))
    # print(infos,url)
    info = infos[1:-5]
    # print(max_page)
    if info:
        max_page = info
    else:
        max_page = 1
    # print(max_page)
    for i in range(1,int(max_page)+1):
        page_url = url+'?&page={}'.format(i)
        print(page_url)
        re.lpush('picture_caixi:start_urls',page_url)
def main():
    base_url = 'https://www.meishij.net/china-food/caixi/'
    html = get_xpath_by_requests(base_url)
    caixi_list = html.xpath('//dl[@class="listnav_dl_style1 w990 clearfix"]/dd//a/@href')
    # print(caixi_list)
    for url in caixi_list:
        parse_caixi(url)
if __name__ == '__main__':
    main()

运行结果报错