微信文本的爬取

 

 

import requests
from lxml import etree


def body():
    url = "https://mp.weixin.qq.com/s/6XYNToX51bWX7ij5MiTWFA"
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'}
    respones = requests.get(url,headers=header)
    respones.encoding = "utf_8"
    html = respones.text
    obj = etree.HTML(html)
    obj_body = obj.xpath('//div[@class="rich_media_content "]/p//text() ')
    obj_titer = obj.xpath('//div[@id="img-content"]/h2/text()')
    y = []
    for i in obj_titer:
        s = i.strip()
        y.append(s)
    obj = y + obj_body
    print(obj)
    v = []
    for i in obj:       
        v.append("\u3000"+"\u3000" + i+"\n")
    with open(r"F:\day08\人民日报\微信文章\%s.text"%y,"w",encoding="utf-8") as f:
        for i in v:
            f.write(i)

body()

　　

转载于:https://www.cnblogs.com/heluobing/p/10829305.html