Created
January 9, 2012 10:32
-
-
Save PyYoshi/1582365 to your computer and use it in GitHub Desktop.
Wikipediaにある企業一覧から企業リンクを抽出するコード
This file contains hidden or 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
| #!/usr/bin/env python | |
| # -*- coding: utf-8 -*- | |
| from lxml.html import fromstring | |
| import urllib,urllib2 | |
| import re | |
| result_links = [] | |
| urls = [ | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E6%B0%B4%E7%94%A3%E3%83%BB%E8%BE%B2%E6%9E%97)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%89%B1%E6%A5%AD)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E5%BB%BA%E8%A8%AD)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%A3%9F%E6%96%99%E5%93%81)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E7%B9%8A%E7%B6%AD%E8%A3%BD%E5%93%81)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E3%83%91%E3%83%AB%E3%83%97%E3%83%BB%E7%B4%99)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E5%8C%96%E5%AD%A6)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E5%8C%BB%E8%96%AC%E5%93%81)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E7%9F%B3%E6%B2%B9%E3%83%BB%E7%9F%B3%E7%82%AD%E8%A3%BD%E5%93%81)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E3%82%B4%E3%83%A0%E8%A3%BD%E5%93%81)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E3%82%AC%E3%83%A9%E3%82%B9%E3%83%BB%E5%9C%9F%E7%9F%B3%E8%A3%BD%E5%93%81)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%89%84%E9%8B%BC)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%9D%9E%E9%89%84%E9%87%91%E5%B1%9E)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%87%91%E5%B1%9E%E8%A3%BD%E5%93%81)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E6%A9%9F%E6%A2%B0)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%9B%BB%E6%B0%97%E6%A9%9F%E5%99%A8)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E8%BC%B8%E9%80%81%E7%94%A8%E6%A9%9F%E5%99%A8)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E7%B2%BE%E5%AF%86%E6%A9%9F%E5%99%A8)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E5%8D%B8%E5%A3%B2%E6%A5%AD)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E5%B0%8F%E5%A3%B2%E6%A5%AD)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E9%8A%80%E8%A1%8C%E4%B8%80%E8%A6%A7', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E8%A8%BC%E5%88%B8%E3%83%BB%E5%95%86%E5%93%81%E5%85%88%E7%89%A9%E5%8F%96%E5%BC%95)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E4%BF%9D%E9%99%BA)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E3%81%9D%E3%81%AE%E4%BB%96%E9%87%91%E8%9E%8D)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E4%B8%8D%E5%8B%95%E7%94%A3)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%99%B8%E9%81%8B)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E6%B5%B7%E9%81%8B)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E7%A9%BA%E9%81%8B)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E5%80%89%E5%BA%AB%E3%83%BB%E9%81%8B%E8%BC%B8%E9%96%A2%E9%80%A3)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E6%83%85%E5%A0%B1%E3%83%BB%E9%80%9A%E4%BF%A1)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E9%9B%BB%E6%B0%97%E3%83%BB%E3%82%AC%E3%82%B9)', | |
| 'http://ja.wikipedia.org/wiki/%E6%97%A5%E6%9C%AC%E3%81%AE%E4%BC%81%E6%A5%AD%E4%B8%80%E8%A6%A7_(%E3%82%B5%E3%83%BC%E3%83%93%E3%82%B9)', | |
| ] | |
| preWiki = re.compile(r'^http://ja.wikipedia.org/wiki/') | |
| def build_opener(): | |
| opener = urllib2.build_opener() | |
| opener.addheaders = [('User-agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:9.0.1) Gecko/20100101 Firefox/9.0.1')] | |
| return opener | |
| def parent_scraper(urls): | |
| results = [] | |
| for url in urls: | |
| html = build_opener().open(url).read() | |
| et = fromstring(html) | |
| xpath = r'/html/body/div[3]/div[3]/div[4]/ul/li/a' | |
| for r in et.xpath(xpath): | |
| ret = 'http://ja.wikipedia.org' + r.attrib['href'] | |
| m = preWiki.search(ret) | |
| if m: | |
| #print ret | |
| results.append(ret) | |
| return results | |
| def child_scraper(urls): | |
| results = [] | |
| for url in urls: | |
| html = build_opener().open(url).read() | |
| et = fromstring(html) | |
| xpath = '/html/body/div[3]/div[3]/div[4]/ul/li/a[@class="external text"]' | |
| for r in et.xpath(xpath): | |
| link = r.attrib['href'] | |
| if len(link) < 40: | |
| results.append(link) | |
| return results | |
| def main(): | |
| ret1 = parent_scraper(urls) | |
| results = child_scraper(ret1) | |
| for result in results: | |
| print result | |
| if __name__ in '__main__': | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment