python来一份情书采集备用python xpath

最新推荐文章于 2025-12-05 17:02:52 发布

原创

最新推荐文章于 2025-12-05 17:02:52 发布 · 117 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #xpath #json

import requests
from lxml import etree
import time
class Book():
def init(self):
self.url = “http://www.qingshu.so/lmqs.html”
self.headers = {
“User-Agent”: “Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36”
}

def get_data(self):
    response = requests.get(url=self.url, headers=self.headers)
    response.encoding = "utf-8"
    return response.text
def parse(self,data):
    tree = etree.HTML(data)
    mainlist = tree.xpath('//div[@class="item"]')
    fp = open("./烂漫情书.txt", "w", encoding='UTF-8')
    for main in mainlist:
        mainsrc="http://www.qingshu.so"+ str(main.xpath('.//div[@class="des"]//@href ')[0])

        # http://www.qingshu.so/aiqing/1669.html
        res=requests.get(mainsrc,headers=self.headers)
        res.encoding="utf-8"
        res_text=res.text
        tree1=etree.HTML(res_text)
        h1=tree1.xpath('//h1[@class="a_t