diff --git a/getdata.py b/getdata.py index e69de29..d75e155 100644 --- a/getdata.py +++ b/getdata.py @@ -0,0 +1,13 @@ +import csv +import requests +import re, os +from bs4 import BeautifulSoup + +url = ' https://mp.weixin.qq.com/s/K0u_qPFQtWuH4hk5K2xWfQ' +response = requests.get(url) +response.encoding = response.apparent_encoding +response.encoding = 'utf-8' +html = response.text +soup = BeautifulSoup(html, 'html.parser') +ans = soup.select('div.rich_media > div.rich_media_inner ') +ans1 = ans[0].text.encode() \ No newline at end of file