etree的应用

最新推荐文章于 2024-11-23 16:19:43 发布

原创最新推荐文章于 2024-11-23 16:19:43 发布 · 1.2k 阅读

0 ·

CC 4.0 BY-SA版权

script 专栏收录该内容

14 篇文章

订阅专栏


import urllib.request
import requests
import json
from lxml import etree

url = "http://www.qiushibaike.com/8hr/page/2/"
headers = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"}

request = urllib.request.Request(url,headers=headers)
html = urllib.request.urlopen(request).read().decode()

text = etree.HTML(html)
#contains()模糊查询方法，第一个参数是要匹配的标签，第二个参数是标签名部分内容
node_list = text.xpath('//div[contains(@id,"qiushi_tag")]')

items = {}
for node in node_list:
    username = node.xpath('.//h2')[0].text
    image = node.xpath('.//div[@class="thumb"]//@src')
    content = node.xpath('.//div[@class="content"]/span')[0].text
    items = {
        "username":username,
        "image":image,
        "content":content,
    }
    # 因为json.dumps 序列化时对中文默认使用的ascii编码.想输出真正的中文需要指定ensure_ascii=False
    f_str = json.dumps(items, ensure_ascii = False)
    with open("qiushi.josn","a+",encoding="utf-8") as f:
        f.write(f_str+"\n")