{"id":715,"date":"2009-08-18T18:34:49","date_gmt":"2009-08-18T10:34:49","guid":{"rendered":"http:\/\/www.impjq.net\/blog\/2009\/08\/18\/pythonhtmlparser%e8%a7%a3%e6%9e%90html\/"},"modified":"2018-12-07T23:25:59","modified_gmt":"2018-12-07T15:25:59","slug":"pythonhtmlparser%e8%a7%a3%e6%9e%90html","status":"publish","type":"post","link":"https:\/\/pjq.me\/?p=715","title":{"rendered":"Python:HTMLParser,\u89e3\u6790html"},"content":{"rendered":"<p>\u8bb0\u5f55\u4e00\u6bb5\u7528HTMLParser\u89e3\u6790html\u7684python\u4ee3\u7801:<\/p>\n<pre lang=\"python\" line=\"1\">\ndata = urllib.urlopen('http:\/\/10.85.40.153').read()\n\n#data = response.read()\nprint data\n\nclass parseHtml(HTMLParser.HTMLParser):\n    def handle_starttag(self, tag, attrs):\n        print tag\n        if 'input'.__contains__(tag):\n            for name, value in attrs:\n                print 'name=%s,value=%s' % (name, value)\n                if value.__contains__('Home'):\n                    print value\n                    print self.get_starttag_text()\n\n\n\nparse = parseHtml()\nparse.feed(data)\n\n<\/pre>\n<div class=\"zemanta-pixie\"><img decoding=\"async\" class=\"zemanta-pixie-img\" alt=\"\" src=\"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70\" \/><\/div>\n","protected":false},"excerpt":{"rendered":"<p>\u8bb0\u5f55\u4e00\u6bb5\u7528HTMLParser\u89e3\u6790html\u7684python\u4ee3\u7801: data = urllib.urlopen(&#8216;http:\/\/10.85.40.153&#8217;).read() #data = response.read() print data class parseHtml(HTMLParser.HTMLParser): def handle_starttag(self, tag, attrs): print tag if &#8216;input&#8217;.__contains__(tag): for name, value in attrs: print &#8216;name=%s,value=%s&#8217; % (name, value) if value.__contains__(&#8216;Home&#8217;): print value print self.get_starttag_text() parse = parseHtml() parse.feed(data)<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[169],"tags":[],"class_list":["post-715","post","type-post","status-publish","format-standard","hentry","category-tech"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.0 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Python:HTMLParser,\u89e3\u6790html - Jianqing&#039;s Blog<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/pjq.me\/?p=715\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Python:HTMLParser,\u89e3\u6790html - Jianqing&#039;s Blog\" \/>\n<meta property=\"og:description\" content=\"\u8bb0\u5f55\u4e00\u6bb5\u7528HTMLParser\u89e3\u6790html\u7684python\u4ee3\u7801: data = urllib.urlopen(&#039;http:\/\/10.85.40.153&#039;).read() #data = response.read() print data class parseHtml(HTMLParser.HTMLParser): def handle_starttag(self, tag, attrs): print tag if &#039;input&#039;.__contains__(tag): for name, value in attrs: print &#039;name=%s,value=%s&#039; % (name, value) if value.__contains__(&#039;Home&#039;): print value print self.get_starttag_text() parse = parseHtml() parse.feed(data)\" \/>\n<meta property=\"og:url\" content=\"https:\/\/pjq.me\/?p=715\" \/>\n<meta property=\"og:site_name\" content=\"Jianqing&#039;s Blog\" \/>\n<meta property=\"article:published_time\" content=\"2009-08-18T10:34:49+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2018-12-07T15:25:59+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70\" \/>\n<meta name=\"author\" content=\"pengjianqing\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"pengjianqing\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/pjq.me\/?p=715#article\",\"isPartOf\":{\"@id\":\"https:\/\/pjq.me\/?p=715\"},\"author\":{\"name\":\"pengjianqing\",\"@id\":\"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60\"},\"headline\":\"Python:HTMLParser,\u89e3\u6790html\",\"datePublished\":\"2009-08-18T10:34:49+00:00\",\"dateModified\":\"2018-12-07T15:25:59+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/pjq.me\/?p=715\"},\"wordCount\":6,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60\"},\"image\":{\"@id\":\"https:\/\/pjq.me\/?p=715#primaryimage\"},\"thumbnailUrl\":\"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70\",\"articleSection\":[\"Tech\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/pjq.me\/?p=715#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/pjq.me\/?p=715\",\"url\":\"https:\/\/pjq.me\/?p=715\",\"name\":\"Python:HTMLParser,\u89e3\u6790html - Jianqing&#039;s Blog\",\"isPartOf\":{\"@id\":\"https:\/\/pjq.me\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/pjq.me\/?p=715#primaryimage\"},\"image\":{\"@id\":\"https:\/\/pjq.me\/?p=715#primaryimage\"},\"thumbnailUrl\":\"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70\",\"datePublished\":\"2009-08-18T10:34:49+00:00\",\"dateModified\":\"2018-12-07T15:25:59+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/pjq.me\/?p=715#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/pjq.me\/?p=715\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/pjq.me\/?p=715#primaryimage\",\"url\":\"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70\",\"contentUrl\":\"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/pjq.me\/?p=715#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/pjq.me\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Python:HTMLParser,\u89e3\u6790html\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/pjq.me\/#website\",\"url\":\"https:\/\/pjq.me\/\",\"name\":\"Jianqing&#039;s Blog\",\"description\":\"Thoughts and Future\",\"publisher\":{\"@id\":\"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/pjq.me\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60\",\"name\":\"pengjianqing\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/pjq.me\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/pjq.me\/wp-content\/uploads\/2021\/12\/Screen-Shot-2021-12-02-at-6.10.58-PM.png\",\"contentUrl\":\"https:\/\/pjq.me\/wp-content\/uploads\/2021\/12\/Screen-Shot-2021-12-02-at-6.10.58-PM.png\",\"width\":460,\"height\":752,\"caption\":\"pengjianqing\"},\"logo\":{\"@id\":\"https:\/\/pjq.me\/#\/schema\/person\/image\/\"},\"url\":\"https:\/\/pjq.me\/?author=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Python:HTMLParser,\u89e3\u6790html - Jianqing&#039;s Blog","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/pjq.me\/?p=715","og_locale":"en_US","og_type":"article","og_title":"Python:HTMLParser,\u89e3\u6790html - Jianqing&#039;s Blog","og_description":"\u8bb0\u5f55\u4e00\u6bb5\u7528HTMLParser\u89e3\u6790html\u7684python\u4ee3\u7801: data = urllib.urlopen('http:\/\/10.85.40.153').read() #data = response.read() print data class parseHtml(HTMLParser.HTMLParser): def handle_starttag(self, tag, attrs): print tag if 'input'.__contains__(tag): for name, value in attrs: print 'name=%s,value=%s' % (name, value) if value.__contains__('Home'): print value print self.get_starttag_text() parse = parseHtml() parse.feed(data)","og_url":"https:\/\/pjq.me\/?p=715","og_site_name":"Jianqing&#039;s Blog","article_published_time":"2009-08-18T10:34:49+00:00","article_modified_time":"2018-12-07T15:25:59+00:00","og_image":[{"url":"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70","type":"","width":"","height":""}],"author":"pengjianqing","twitter_card":"summary_large_image","twitter_misc":{"Written by":"pengjianqing"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/pjq.me\/?p=715#article","isPartOf":{"@id":"https:\/\/pjq.me\/?p=715"},"author":{"name":"pengjianqing","@id":"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60"},"headline":"Python:HTMLParser,\u89e3\u6790html","datePublished":"2009-08-18T10:34:49+00:00","dateModified":"2018-12-07T15:25:59+00:00","mainEntityOfPage":{"@id":"https:\/\/pjq.me\/?p=715"},"wordCount":6,"commentCount":0,"publisher":{"@id":"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60"},"image":{"@id":"https:\/\/pjq.me\/?p=715#primaryimage"},"thumbnailUrl":"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70","articleSection":["Tech"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/pjq.me\/?p=715#respond"]}]},{"@type":"WebPage","@id":"https:\/\/pjq.me\/?p=715","url":"https:\/\/pjq.me\/?p=715","name":"Python:HTMLParser,\u89e3\u6790html - Jianqing&#039;s Blog","isPartOf":{"@id":"https:\/\/pjq.me\/#website"},"primaryImageOfPage":{"@id":"https:\/\/pjq.me\/?p=715#primaryimage"},"image":{"@id":"https:\/\/pjq.me\/?p=715#primaryimage"},"thumbnailUrl":"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70","datePublished":"2009-08-18T10:34:49+00:00","dateModified":"2018-12-07T15:25:59+00:00","breadcrumb":{"@id":"https:\/\/pjq.me\/?p=715#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/pjq.me\/?p=715"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/pjq.me\/?p=715#primaryimage","url":"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70","contentUrl":"http:\/\/img.zemanta.com\/pixy.gif?x-id=57946abf-ee5f-8805-90f7-b1e55e7d4d70"},{"@type":"BreadcrumbList","@id":"https:\/\/pjq.me\/?p=715#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/pjq.me\/"},{"@type":"ListItem","position":2,"name":"Python:HTMLParser,\u89e3\u6790html"}]},{"@type":"WebSite","@id":"https:\/\/pjq.me\/#website","url":"https:\/\/pjq.me\/","name":"Jianqing&#039;s Blog","description":"Thoughts and Future","publisher":{"@id":"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/pjq.me\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/pjq.me\/#\/schema\/person\/0eb1e72d1e69fbbd9b5c0bfd8e2aae60","name":"pengjianqing","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/pjq.me\/#\/schema\/person\/image\/","url":"https:\/\/pjq.me\/wp-content\/uploads\/2021\/12\/Screen-Shot-2021-12-02-at-6.10.58-PM.png","contentUrl":"https:\/\/pjq.me\/wp-content\/uploads\/2021\/12\/Screen-Shot-2021-12-02-at-6.10.58-PM.png","width":460,"height":752,"caption":"pengjianqing"},"logo":{"@id":"https:\/\/pjq.me\/#\/schema\/person\/image\/"},"url":"https:\/\/pjq.me\/?author=1"}]}},"views":2623,"_links":{"self":[{"href":"https:\/\/pjq.me\/index.php?rest_route=\/wp\/v2\/posts\/715","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pjq.me\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/pjq.me\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/pjq.me\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/pjq.me\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=715"}],"version-history":[{"count":0,"href":"https:\/\/pjq.me\/index.php?rest_route=\/wp\/v2\/posts\/715\/revisions"}],"wp:attachment":[{"href":"https:\/\/pjq.me\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=715"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/pjq.me\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=715"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/pjq.me\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=715"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}