Last active
July 11, 2018 06:06
-
-
Save umihico/279c87001046928811f0341b06203e4d to your computer and use it in GitHub Desktop.
大量のテキストから住所を抜き出す
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
import re | |
def get_address_regex_lxmltree(lxmltree): | |
address_list = [] | |
for text in lxmltree.itertext(): | |
address_list.extend(get_address_regex_text(text)) | |
return address_list | |
def get_address_regex_text(text): | |
return re.findall("(...??[都道府県].+?市.+?区|.+?[市区町村].+)", text) | |
if __name__ == '__main__': | |
from requests import get | |
from lxml import html | |
from umihico_commons.functools import save_as_txt | |
url = "https://www.mhlw.go.jp/kouseiroudoushou/shikaku_shiken/h25_kaijou.html" | |
lxmltree = html.fromstring(get(url).text) | |
result = get_address_regex_lxmltree(lxmltree) | |
save_as_txt("result.txt", result) | |
# urls = re.findall( | |
# "https?://[\w/:%#\$&\?\(\)~\.=\+\-]+", get(url_list).text) | |
# print(urls) |
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
['札幌市白石区東札幌6条1丁目1-1', | |
'札幌市北区北7条西2丁目9', | |
'札幌市北区北7条西2丁目5', | |
'札幌市中央区南22条西7丁目', | |
'札幌市中央区大通西17丁目1-22', | |
'弘前市文京町1', | |
'産業見本市会館サンフェスタ・卸町会館', | |
'仙台市若林区卸町2-15-2', | |
'仙台市宮城野区港3-1-7', | |
'仙台市青葉区国見1-19-1', | |
'仙台市太白区八木山香澄町35-1', | |
'新潟市中央区浜浦町1-8', | |
'千代田区神田須田町1-5-10', | |
'中央区八重洲1-2-16', | |
'江東区有明3-5-7', | |
'豊島区西巣鴨3-20-1', | |
'港区白金台1-2-37', | |
'府中市朝日町3-11-1', | |
'八王子市片倉町1404-1', | |
'世田谷区太子堂1-7-57', | |
'大田区西蒲田5-23-22', | |
'豊島区西池袋3-34-1', | |
'愛知県日進市岩崎町阿良池12', | |
'金沢市常盤町212-1', | |
'河北郡内灘町大学1-1', | |
'金沢市太陽が丘1-1', | |
'寝屋川市早子町12-16', | |
'和泉市まなび野1-1', | |
'東大阪市御厨栄町4-1-10', | |
'大東市中垣内3-1-1', | |
'東大阪市小若江3-4-1', | |
'寝屋川市初町18-8', | |
'吹田市片山町2-5-1', | |
'広島市南区霞1-2-3', | |
'広島市安佐南区安東6-13-1', | |
'広島市中小企業会館', | |
'広島市西区商工センター1-14-1', | |
'広島市西区福島町2-1-1', | |
'高松市林町2217-1', | |
'高松市総合体育館', | |
'高松市福岡町4-36-1', | |
'高松市春日町960\u3000', | |
'高松市幸町1-1', | |
'高松市寿町2-4-20', | |
'高松市亀岡町1-10', | |
'福岡市南区玉川町22-1', | |
'福岡市中央区福浜1-3-1', | |
'福岡市博多区博多駅南4-2-10', | |
'福岡市南区筑紫丘1-1-1', | |
'福岡市城南区七隈8-19-1', | |
'北九州市小倉北区浅野3-8-1', | |
'福岡市早良区西新6-2-92\xa0', | |
'福岡市東区和白東3-30-1', | |
'熊本市北区和泉町325', | |
'宜野湾市野嵩736', | |
'中頭郡西原町字翁長777', | |
'中頭郡西原町字千原1', | |
'那覇市久米2-15-23', | |
'那覇市字国場555', | |
'〒100-8916 東京都千代田区霞が関1-2-2 電話:03-5253-1111(代表)'] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment