我用xpath匹配不出来数字
from lxml import etree
from bs4 import BeautifulSoup
import requests
import time
url='http://glidedsky.com/level/web/crawler-basic-1'
def main(url1):
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Safari/537.36 Edg/88.0.705.56','Cookie': 'acw_tc=2760820316125972250506308e6ec5bbbfb0ee4f05cd6654aa87c9ff316107; xq_a_token=176b14b3953a7c8a2ae4e4fae4c848decc03a883; xqat=176b14b3953a7c8a2ae4e4fae4c848decc03a883; xq_r_token=2c9b0faa98159f39fa3f96606a9498edb9ddac60; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTYxMzQ0MzE3MSwiY3RtIjoxNjEyNTk3MjIxMzA2LCJjaWQiOiJkOWQwbjRBWnVwIn0.lN8zzdiJLPwJHb0PXSKWs-HcgwiNYPFt4O2IsiSHEhPC_6GpsWYaql2MGgtaI0M0v--HY2KHIIunB5q6ZygzWACEzk8gpYqWcIG3zEzJBAeP89GpTxFxD8oyWXDm_DWLcYdI77LmihrwgR2DYO58CoFzy-PE2s3SBf6_zoul0gV5vfEhfWsek1xEORe6fC5hq93p9Xx55tpQA_h1E1t0ir_PPa_5Y1EqZXKW8baSoVfHVWLgc-INRDkKSG5A8oQUT2D2rsW4M8i9Qb1u1FWqF2hvoG82XazkiqZyr1edqnKoeKkAcKEz6bvjOMZZA7cdl_1MRF97jMx7pS5hsQrUQA; u=651612597225055; Hm_lvt_1db88642e346389874251b5a1eded6e3=1612597226; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1612597226; device_id=24700f9f1986800ab4fcc880530dd0ed'}#进行UA伪装
r=requests.get(url1,headers=headers).text
# r1=etree.HTML(r.content,etree.HTMLParser(encoding='UTF-8'))
soup=BeautifulSoup(r,'lxml')
# a=r1.xpath('//div[@class＝"col-md-1"]//text()')
data=soup.findAll('div',class_='col-md-1')
print(data)
if __name__ == '__main__':
main(url)
