import requests
from lxml import etree
url='http://www.cargoyellowpages.com/en/jordan/amman/page_01.html'
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}
names=[]
tels=[]
list=[]
page_text=requests.get(url=url,headers=headers).text#得到网页信息
tree=etree.HTML(page_text)
companys = tree.xpath('//*[@id="content_style"]/div[2]/div[7]/div')#找到当前页面公司所在div
for company in companys:#遍历公司
try:
name = company.xpath('./div/div[1]/h2/span/a/text()')[0]#找到公司名称
names.append(name)#添加到公司名称列表
tel = company.xpath('./div/div[5]/text()')[0]#找到公司电话
tels.append(tel)#添加到电话列表
list.append([name,tel])
except:
pass
print(len(names))
print(len(tels))
print(len(list))