案例-亚洲大学排行：xpath

网址： https://www.webometrics.info/en/Asia

 

xpath代码：

import requests
import json
from lxml import etree
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}

def get_ranking(url):
    resp = requests.get(url, headers=headers)
    resp.encoding = 'UTF-8'
    html_tree = etree.HTML(resp.text)
    data = html_tree.xpath('//div[@id="block-system-main"]/div/table//tbody/tr')
    for item in data:
        print("University==>", item.xpath('./td[3]/a/text()')[0])
        print("ranking==>",item.xpath('./td[1]/center/text()')[0])
        print("World Rank==>",item.xpath('./td[2]/center/text()')[0])
# 分页
url  = 'https://www.webometrics.info/en/asia'

for item in range(0,160):
    if item == 0:
        get_ranking(url)
    else:
        full_url = "{}?page={}".format(url,item)
        get_ranking(full_url)