Python爬虫Xpath定位数据的两种方法

import requests
from lxml import etree
import time
import Socket
import csv
from selenium import WEBdriver
from configparser import ConfigParser
from selenium.webdriver import Chrome
from selenium.webdriver import ChromeOptions
#禁止图片和CSS加载
chrome_options = webdriver.ChromeOptions()
prefs = {"profile.managed_default_content_settings.images": 2}
chrome_options.add_experimental_option("prefs", prefs)
option = ChromeOptions()
option.add_experimental_option('excludeSwitches', ['enable-automation'])
# 如果想加载图片，就把下面第二句话改第一句话，删掉上面的“禁止图片和css加载”部分
# wb = Chrome(options=option)
wb=webdriver.Chrome(options=chrome_options)
#最大化窗口、输入网址、等待至网页加载完成（防止元素还没加载出来就开始爬了这样自然爬不到数据。如果一直加载不出就等10秒，加载好了就立刻结束等待）
wb.maximize_window()
wb.get("https://www.tianyancha.com/")
wb.implicitly_wait(5)

data = wb.page_source
time.sleep(3)
data = wb.page_source
time.sleep(3)
page_all.append(data)
html = etree.HTML(data)
company = html.xpath('/html/body/div/div/div[2]/div/div[1]/div[1]/div[3]/div[1]/div[1]/div[1]/h1/text()')
print(company )

"//div[@class='mainArea']/ul/li"