Google\u691c\u7d22\uff06\u7d50\u679c\u8868\u793a\u3092Python\u7d4c\u7531\u3067\u884c\u3046\u3002
\n\u30a6\u30a7\u30d6\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0\u306e\u57fa\u790e\u306b\u306a\u308b\u306e\u304b\u3082(\uff1f)<\/p>\n
\u5b9f\u884c\u30b5\u30f3\u30d7\u30eb\u306f\u3053\u3061\u3089\u3002 1\u30da\u30fc\u30b8\u76ee\u3057\u304b\u8868\u793a\u3067\u304d\u3066\u3044\u306a\u3044… \u5f37\u5f15\u306a\u3068\u3053\u308d\u3082\u3042\u308b\u306e\u3067\u3001\u5f8c\u3067\u52c9\u5f37\u3057\u76f4\u3057\u3066\u4fee\u6b63\u3059\u308b\u304b\u3082… Google\u691c\u7d22\uff06\u7d50\u679c\u8868\u793a\u3092Python\u7d4c\u7531\u3067\u884c\u3046\u3002 \u30a6\u30a7\u30d6\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0\u306e\u57fa\u790e\u306b\u306a\u308b\u306e\u304b\u3082(\uff1f) \u5b9f\u884c\u30b5\u30f3\u30d7\u30eb\u306f\u3053\u3061\u3089\u3002 https:\/\/www.dogrow.net\/python\/sample\/0078\/ (1\/2)\u2026 \u7d9a\u304d\u3092\u8aad\u3080 »<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[26],"tags":[],"class_list":["post-632","post","type-post","status-publish","format-standard","hentry","category-web"],"views":3488,"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/posts\/632","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/comments?post=632"}],"version-history":[{"count":40,"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/posts\/632\/revisions"}],"predecessor-version":[{"id":2711,"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/posts\/632\/revisions\/2711"}],"wp:attachment":[{"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/media?parent=632"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/categories?post=632"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dogrow.net\/python\/wp-json\/wp\/v2\/tags?post=632"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\nhttps:\/\/www.dogrow.net\/python\/sample\/0078\/<\/a><\/p>\n(1\/2) index.cgi<\/h3>\n
\n\u5185\u90e8\u3067 start=10,20,30 \u306a\u3069\u3068\u5207\u308a\u66ff\u3048\u3066\u60c5\u5831\u53ce\u96c6\u3092\u7e70\u308a\u8fd4\u305b\u3070\u8907\u6570\u30da\u30fc\u30b8\u5206\u3092\u8868\u793a\u3067\u304d\u308b\u3051\u3069\u3001\u307e\u305a\u306f\u57fa\u672c\u5f62\u306e\u307f\u3092\u4f5c\u3063\u3066\u307f\u308b\u3002<\/p>\n\r\n#!\/usr\/local\/bin\/python\r\n# -*- coding: utf-8 -*-\r\n\r\nprint 'Content-type: text\/html'\r\n\r\nimport cgi\r\nimport myparser\r\nimport re\r\n\r\nprint """\r\n<!DOCTYPE html>\r\n<html>\r\n<head>\r\n<meta http-equiv="Content-Type" content="text\/html; charset=utf-8" \/>\r\n<title>\u30b5\u30f3\u30d7\u30eb<\/title>\r\n<\/head>\r\n<body>\r\n"""\r\n\r\nform = cgi.FieldStorage()\r\nif form.has_key('word'):\r\n\tword = re.sub("[ |\u3000]+","+",form['word'].value)\r\n\turl = 'https:\/\/www.google.co.jp\/search?q=' + word\r\n\tlinkItem = myparser.parse(url)\r\n\tfor item in linkItem:\r\n\t\ttitle = item.get_title()\r\n\t\tsite = item.get_ref()\r\n\t\tif len(title) <= 0:\r\n\t\t\ttitle = '***'\r\n\t\tif re.match('http', site):\r\n\t\t\thref = site\r\n\t\telse:\r\n\t\t\thref = 'https:\/\/www.google.com' + site\r\n\t\tprint '<a href=\\"%s\\">%s<\/a><hr \/>' % (href, title)\r\n\r\nprint """\r\n<form enctype="multipart\/form-data" action=".\/" method=post>\r\nGoogle\u691c\u7d22\uff1a<input type=text name=word style="width:400px">\r\n<input type=submit value="\u5b9f\u884c">\r\n<\/form>\r\n<\/body>\r\n<\/html>\r\n"""\r\n<\/pre>\n(2\/2) myparser.py<\/h3>\n
\n\u6307\u5b9aWEB\u30da\u30fc\u30b8\u306e\u30c7\u30fc\u30bf\u53d6\u5f97\u306b\u306f urllib2<\/span> \u30e2\u30b8\u30e5\u30fc\u30eb\u306eHTTP\u30e9\u30c3\u30d1\u30fc\u6a5f\u80fd\u3092\u4f7f\u7528\u3059\u308b\u3002
\nHTML\u306e\u69cb\u6587\u89e3\u6790\u306b\u306f HTMLParser<\/span> \u30e2\u30b8\u30e5\u30fc\u30eb\u3092\u4f7f\u7528\u3059\u308b\u3002\uff08\u4eca\u56de\u306f\u697d\u3067\u304d\u308b lxml<\/span> \u3092\u4f7f\u308f\u306a\u3044\uff09
\nPython\u30d7\u30ed\u30b0\u30e9\u30e0\u3067\u6587\u5b57\u5217\u3092\u51e6\u7406\u3059\u308b\u9593\u306f unicode \u3067\u6271\u3046\u3002<\/p>\n\r\n#!~\/usr\/local\/bin\/python\r\n# -*- coding: utf-8 -*-\r\nimport chardet\r\nimport urllib2\r\nfrom HTMLParser import HTMLParser\r\n\r\nclass MyLinkItem:\r\n def __init__(self):\r\n self.m_ref = ''\r\n self.m_title = ''\r\n def set_ref(self, val):\r\n self.m_ref = val\r\n def set_title(self, val):\r\n self.m_title = val\r\n def get_ref(self):\r\n return self.m_ref.encode('utf-8')\r\n def get_title(self):\r\n return self.m_title.encode('utf-8')\r\n\r\nclass MyParser(HTMLParser):\r\n def __init__(self):\r\n HTMLParser.__init__(self)\r\n self.m_linkItem = []\r\n self.proc_atag = False\r\n self.title = ''\r\n def handle_starttag(self, tagname, attribute):\r\n if tagname.lower() == 'a':\r\n for i in attribute:\r\n if i[0].lower() == 'href':\r\n if re.match('\\\/url\\?q=http', i[1]):\r\n if not re.search('webcache\\.googleusercontent', i[1]):\r\n self.proc_atag = True\r\n self.title = ''\r\n linkItem = MyLinkItem()\r\n linkItem.set_ref(i[1])\r\n self.m_linkItem.append(linkItem)\r\n def handle_endtag(self, tagname):\r\n if tagname.lower() == 'a':\r\n if self.proc_atag == True:\r\n self.m_linkItem[-1].set_title(self.title)\r\n self.proc_atag = False\r\n def handle_data(self, data):\r\n if self.proc_atag == True:\r\n self.title = self.title + data\r\n def get_linkItem(self):\r\n return self.m_linkItem\r\n\r\ndef parse(url):\r\n # load html\r\n opener = urllib2.build_opener()\r\n opener.addheaders = [('User-agent', 'Mozilla\/5.0')]\r\n html = opener.open(url)\r\n data = html.read()\r\n html.close()\r\n rr = chardet.detect(data) # \u6587\u5b57\u30b3\u30fc\u30c9\u3092\u5224\u5b9a\r\n data = data.decode(rr['encoding']) # unicode\u306b\u5909\u63db\r\n # parse\r\n parser = MyParser()\r\n parser.feed(data)\r\n linkItem = parser.get_linkItem()\r\n parser.close()\r\n return linkItem\r\n<\/pre>\n
\n","protected":false},"excerpt":{"rendered":"