xpath来爬取诗词

# 爬取中国古诗词网的诗词

import requests
from lxml import etree

url = "http://86gsc.com/"
headers={'User-Agent': 'BaiduSpider'}
res = requests.get(url = url,headers = headers).text
# 访问成功
# print(res.status_code)
# print(res)
tree = etree.HTML(res)   #?什么意思

# xpath返回的值都是以列表的形式来返回的
title = tree.xpath("//p/a/b/text()")      #xpath返回的结果以列表的形式存储
print(title)
authors = tree.xpath("//div/p/a[2]/text()")
print(authors)
concent = tree.xpath('//div[@class="contson"]/text()')       #注意双冒号和单冒号
print(concent)

for t,a,c in zip(title,authors,concent):
    print(t,a,c)
# for i in zip(title,authors,concent):
#     print(i)