{"id":26908,"date":"2022-12-20T18:53:58","date_gmt":"2022-12-20T13:23:58","guid":{"rendered":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/"},"modified":"2022-12-20T18:53:58","modified_gmt":"2022-12-20T13:23:58","slug":"solved-extract-contact-information-from-html-with-python","status":"publish","type":"post","link":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/","title":{"rendered":"[Solved] extract contact information from html with python"},"content":{"rendered":"<p> [ad_1]<br \/>\n<\/p>\n<div id=\"answer-29653877\" class=\"answer js-answer accepted-answer js-accepted-answer\" data-answerid=\"29653877\" data-parentid=\"29638590\" data-score=\"0\" data-position-on-page=\"1\" data-highest-scored=\"1\" data-question-has-accepted-highest-score=\"1\" itemprop=\"acceptedAnswer\" itemscope itemtype=\"https:\/\/schema.org\/Answer\">\n<div class=\"post-layout\">\n<div class=\"votecell post-layout--left\"><\/div>\n<div class=\"answercell post-layout--right\">\n<div class=\"s-prose js-post-body\" itemprop=\"text\">\n<p>I use this code to extract information<\/p>\n<pre><code># _*_ coding:utf-8 _*_\nimport urllib2\nimport urllib\nimport re\nfrom bs4 import BeautifulSoup\nimport sys\nreload(sys)\nsys.setdefaultencoding('utf-8')\n\ndef grabHref(url,localfile):\n    html = urllib2.urlopen(url).read()\n    html = unicode(html,'gb2312','ignore').encode('utf-8','ignore')\n    soup = BeautifulSoup(html)\n    myfile = open(localfile,'wb')\n    for link in soup.select(\"div &gt;            a[href^=http:\/\/www.karmaloop.com\/kazbah\/browse]\"):\n        for item in BeautifulSoup(urllib2.urlopen(link['href']).read()).select(\"div &gt; a[href^=mailto]\"):\n            contactInfo = item.get_text()\n            print link['href']\n            print contactInfo\n\n        myfile.write(link['href'])\n        myfile.write('\\r\\n')\n        myfile.write(contactInfo)\n        myfile.write('\\r\\n')\n    myfile.close()\n\n\n\ndef main():\n    url = \"http:\/\/www.karmaloop.com\/brands\"\n    localfile=\"Contact.txt\"\n    grabHref(url,localfile)\nif __name__==\"__main__\":\n    main()\n<\/code><\/pre>\n<p>But I still can only get email address here, how can I get phone number and address? Thanks <\/p>\n<\/p><\/div>\n<div class=\"mt24\"><\/div>\n<\/div>\n<p>            <span class=\"d-none\" itemprop=\"commentCount\">3<\/span> <\/p><\/div>\n<\/div>\n<p>[ad_2]<\/p>\n<p>solved extract contact information from html with python <\/p>\n","protected":false},"excerpt":{"rendered":"<p>[ad_1] I use this code to extract information # _*_ coding:utf-8 _*_ import urllib2 import urllib import re from bs4 import BeautifulSoup import sys reload(sys) sys.setdefaultencoding(&#8216;utf-8&#8242;) def grabHref(url,localfile): html = urllib2.urlopen(url).read() html = unicode(html,&#8217;gb2312&#8242;,&#8217;ignore&#8217;).encode(&#8216;utf-8&#8242;,&#8217;ignore&#8217;) soup = BeautifulSoup(html) myfile = open(localfile,&#8217;wb&#8217;) for link in soup.select(&#8220;div &gt; a[href^=http:\/\/www.karmaloop.com\/kazbah\/browse]&#8221;): for item in BeautifulSoup(urllib2.urlopen(link[&#8216;href&#8217;]).read()).select(&#8220;div &gt; a[href^=mailto]&#8221;): contactInfo = item.get_text() &#8230; <a title=\"[Solved] extract contact information from html with python\" class=\"read-more\" href=\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\" aria-label=\"More on [Solved] extract contact information from html with python\">Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[320],"tags":[1684,349],"class_list":["post-26908","post","type-post","status-publish","format-standard","hentry","category-solved","tag-extract","tag-python"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.5 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>[Solved] extract contact information from html with python - JassWeb<\/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:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"[Solved] extract contact information from html with python - JassWeb\" \/>\n<meta property=\"og:description\" content=\"[ad_1] I use this code to extract information # _*_ coding:utf-8 _*_ import urllib2 import urllib import re from bs4 import BeautifulSoup import sys reload(sys) sys.setdefaultencoding(&#039;utf-8&#039;) def grabHref(url,localfile): html = urllib2.urlopen(url).read() html = unicode(html,&#039;gb2312&#039;,&#039;ignore&#039;).encode(&#039;utf-8&#039;,&#039;ignore&#039;) soup = BeautifulSoup(html) myfile = open(localfile,&#039;wb&#039;) for link in soup.select(&quot;div &gt; a[href^=http:\/\/www.karmaloop.com\/kazbah\/browse]&quot;): for item in BeautifulSoup(urllib2.urlopen(link[&#039;href&#039;]).read()).select(&quot;div &gt; a[href^=mailto]&quot;): contactInfo = item.get_text() ... Read more\" \/>\n<meta property=\"og:url\" content=\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\" \/>\n<meta property=\"og:site_name\" content=\"JassWeb\" \/>\n<meta property=\"article:published_time\" content=\"2022-12-20T13:23:58+00:00\" \/>\n<meta name=\"author\" content=\"Kirat\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Kirat\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\"},\"author\":{\"name\":\"Kirat\",\"@id\":\"https:\/\/jassweb.com\/solved\/#\/schema\/person\/65c9c7b7958150c0dc8371fa35dd7c31\"},\"headline\":\"[Solved] extract contact information from html with python\",\"datePublished\":\"2022-12-20T13:23:58+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\"},\"wordCount\":43,\"publisher\":{\"@id\":\"https:\/\/jassweb.com\/solved\/#organization\"},\"keywords\":[\"extract\",\"python\"],\"articleSection\":[\"Solved\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\",\"url\":\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\",\"name\":\"[Solved] extract contact information from html with python - JassWeb\",\"isPartOf\":{\"@id\":\"https:\/\/jassweb.com\/solved\/#website\"},\"datePublished\":\"2022-12-20T13:23:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/jassweb.com\/solved\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"[Solved] extract contact information from html with python\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/jassweb.com\/solved\/#website\",\"url\":\"https:\/\/jassweb.com\/solved\/\",\"name\":\"JassWeb\",\"description\":\"Build High-quality Websites\",\"publisher\":{\"@id\":\"https:\/\/jassweb.com\/solved\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/jassweb.com\/solved\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/jassweb.com\/solved\/#organization\",\"name\":\"Jass Web\",\"url\":\"https:\/\/jassweb.com\/solved\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/jassweb.com\/solved\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/jassweb.com\/wp-content\/uploads\/2021\/02\/jass-website-logo-1.png\",\"contentUrl\":\"https:\/\/jassweb.com\/wp-content\/uploads\/2021\/02\/jass-website-logo-1.png\",\"width\":693,\"height\":132,\"caption\":\"Jass Web\"},\"image\":{\"@id\":\"https:\/\/jassweb.com\/solved\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/jassweb.com\/solved\/#\/schema\/person\/65c9c7b7958150c0dc8371fa35dd7c31\",\"name\":\"Kirat\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/jassweb.com\/solved\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/jassweb.com\/solved\/wp-content\/litespeed\/avatar\/1261af3c9451399fa1336d28b98ea3bb.jpg?ver=1775798750\",\"contentUrl\":\"https:\/\/jassweb.com\/solved\/wp-content\/litespeed\/avatar\/1261af3c9451399fa1336d28b98ea3bb.jpg?ver=1775798750\",\"caption\":\"Kirat\"},\"sameAs\":[\"http:\/\/jassweb.com\"],\"url\":\"https:\/\/jassweb.com\/solved\/author\/jaspritsinghghumangmail-com\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"[Solved] extract contact information from html with python - JassWeb","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:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/","og_locale":"en_US","og_type":"article","og_title":"[Solved] extract contact information from html with python - JassWeb","og_description":"[ad_1] I use this code to extract information # _*_ coding:utf-8 _*_ import urllib2 import urllib import re from bs4 import BeautifulSoup import sys reload(sys) sys.setdefaultencoding('utf-8') def grabHref(url,localfile): html = urllib2.urlopen(url).read() html = unicode(html,'gb2312','ignore').encode('utf-8','ignore') soup = BeautifulSoup(html) myfile = open(localfile,'wb') for link in soup.select(\"div &gt; a[href^=http:\/\/www.karmaloop.com\/kazbah\/browse]\"): for item in BeautifulSoup(urllib2.urlopen(link['href']).read()).select(\"div &gt; a[href^=mailto]\"): contactInfo = item.get_text() ... Read more","og_url":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/","og_site_name":"JassWeb","article_published_time":"2022-12-20T13:23:58+00:00","author":"Kirat","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Kirat","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/#article","isPartOf":{"@id":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/"},"author":{"name":"Kirat","@id":"https:\/\/jassweb.com\/solved\/#\/schema\/person\/65c9c7b7958150c0dc8371fa35dd7c31"},"headline":"[Solved] extract contact information from html with python","datePublished":"2022-12-20T13:23:58+00:00","mainEntityOfPage":{"@id":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/"},"wordCount":43,"publisher":{"@id":"https:\/\/jassweb.com\/solved\/#organization"},"keywords":["extract","python"],"articleSection":["Solved"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/","url":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/","name":"[Solved] extract contact information from html with python - JassWeb","isPartOf":{"@id":"https:\/\/jassweb.com\/solved\/#website"},"datePublished":"2022-12-20T13:23:58+00:00","breadcrumb":{"@id":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/jassweb.com\/solved\/solved-extract-contact-information-from-html-with-python\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/jassweb.com\/solved\/"},{"@type":"ListItem","position":2,"name":"[Solved] extract contact information from html with python"}]},{"@type":"WebSite","@id":"https:\/\/jassweb.com\/solved\/#website","url":"https:\/\/jassweb.com\/solved\/","name":"JassWeb","description":"Build High-quality Websites","publisher":{"@id":"https:\/\/jassweb.com\/solved\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/jassweb.com\/solved\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/jassweb.com\/solved\/#organization","name":"Jass Web","url":"https:\/\/jassweb.com\/solved\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/jassweb.com\/solved\/#\/schema\/logo\/image\/","url":"https:\/\/jassweb.com\/wp-content\/uploads\/2021\/02\/jass-website-logo-1.png","contentUrl":"https:\/\/jassweb.com\/wp-content\/uploads\/2021\/02\/jass-website-logo-1.png","width":693,"height":132,"caption":"Jass Web"},"image":{"@id":"https:\/\/jassweb.com\/solved\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/jassweb.com\/solved\/#\/schema\/person\/65c9c7b7958150c0dc8371fa35dd7c31","name":"Kirat","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/jassweb.com\/solved\/#\/schema\/person\/image\/","url":"https:\/\/jassweb.com\/solved\/wp-content\/litespeed\/avatar\/1261af3c9451399fa1336d28b98ea3bb.jpg?ver=1775798750","contentUrl":"https:\/\/jassweb.com\/solved\/wp-content\/litespeed\/avatar\/1261af3c9451399fa1336d28b98ea3bb.jpg?ver=1775798750","caption":"Kirat"},"sameAs":["http:\/\/jassweb.com"],"url":"https:\/\/jassweb.com\/solved\/author\/jaspritsinghghumangmail-com\/"}]}},"_links":{"self":[{"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/posts\/26908","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/comments?post=26908"}],"version-history":[{"count":0,"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/posts\/26908\/revisions"}],"wp:attachment":[{"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/media?parent=26908"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/categories?post=26908"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jassweb.com\/solved\/wp-json\/wp\/v2\/tags?post=26908"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}