Python XPath抓取小说《三国演义》

 

from lxml import etree
import requests

"""
获取章节列表和地址
"""
def  getContents():
    tagret = "https://www.kanunu8.com/files/old/2011/2447.html"
    req = requests.get(url=tagret)
    req.encoding = "gb2312"
    html = req.text
    bookdata = etree.HTML(html)

    table_list = bookdata.xpath('//table[9]//tr[1]//td[2]//table[4]//tr[1]//td[1]//table[1]//a//text()')

    table_url = bookdata.xpath('//table[9]//tr[1]//td[2]//table[4]//tr[1]//td[1]//table[1]//a//@href')

    for title in table_list:
        print(title)

    for u in table_url:
        print(u)

"""
获取小说内容
"""
def getContent():
    tagret = "https://www.kanunu8.com/files/old/2011/2447/71775.html"
    req  = requests.get(url=tagret)
    req.encoding = "gb2312"
    html = req.text

    bookdata = etree.HTML(html)
    table_list = bookdata.xpath('//table[5]//tr[1]//td[2]//text()')

    print(table_list)


if __name__ == '__main__':
    getContents()

 

 

来源：https://www.cnblogs.com/dangzhengtao/p/12215219.html