Last active
March 9, 2018 10:50
-
-
Save andy23512/4cbfb7a24a22a900c59e60abf3abe4c5 to your computer and use it in GitHub Desktop.
Use regex to search text in html via BeautifulSoup
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import re\n", | |
"import requests\n", | |
"from bs4 import BeautifulSoup\n", | |
"\n", | |
"res = requests.get(\"http://civil.csu.edu.tw/wSite/lp?ctNode=13264&mp=541613&idPath=8859_13263_13264\")\n", | |
"res.encoding = 'utf8'\n", | |
"soup = BeautifulSoup(res.text,'html.parser')\n", | |
"web_tag = 'div.article a'\n", | |
"articles = soup.select(web_tag)\n", | |
"email_set = set()\n", | |
"for art in articles:\n", | |
" res2 = requests.get(\"http://civil.csu.edu.tw/wSite/\"+art['href'])\n", | |
" res2.encoding = 'utf8'\n", | |
" soup2 = BeautifulSoup(res2.text,'html.parser')\n", | |
" pattern = re.compile(r'.*@.*')\n", | |
" email_set.add(soup2.find(text=pattern))\n", | |
"print(email_set)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.6.4" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment