{"id":72,"date":"2023-11-06T16:09:22","date_gmt":"2023-11-06T16:09:22","guid":{"rendered":"https:\/\/blog.dataplatform.lt\/?p=72"},"modified":"2023-11-06T16:09:50","modified_gmt":"2023-11-06T16:09:50","slug":"schema","status":"publish","type":"post","link":"https:\/\/blog.dataplatform.lt\/?p=72","title":{"rendered":"Schema &#8220;Flats&#8221;"},"content":{"rendered":"\n<p>Example end to end:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import requests\nimport json\nimport re\nfrom pprint import pprint\nfrom dphelper import DPHelper\nhelper = DPHelper(is_verbose=True)\nheaders = helper.create_headers(authority=\"https:\/\/berzunamai.lt\/butai\/\")\n \ncontent = helper.from_url('https:\/\/berzunamai.lt\/butai\/', headers=headers)\n# content of table\nrg = re.compile('&lt;tr class=\".*?\">&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;td class=\".*?\">&lt;a href=\"(.*?)\".*?>&lt;\/a>.*?&lt;\/td>&lt;td class=\".*?\">(.*?)&lt;\/td>&lt;\/tr>')\nresults = rg.findall(content)\n# columns to get\napts = helper.parse_rows(\n  &#91;'id','floor_romanian','area','rooms','orientation','price','status','empty_column','www','floor'],\nresults,\nverbose=True,    \n)\n# add flat link in to 'www' column\nfor row in apts:\n    row&#91;'www'] = f\"https:\/\/berzunamai.lt\/butai\/{row&#91;'floor']}-aukstas\/{row&#91;'id']}-butas\/\"\n \n# export to JSON\nprint(json.dumps(apts))<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>Example end to end:<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[12],"tags":[],"class_list":["post-72","post","type-post","status-publish","format-standard","hentry","category-code-examples"],"_links":{"self":[{"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=\/wp\/v2\/posts\/72","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=72"}],"version-history":[{"count":2,"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=\/wp\/v2\/posts\/72\/revisions"}],"predecessor-version":[{"id":74,"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=\/wp\/v2\/posts\/72\/revisions\/74"}],"wp:attachment":[{"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=72"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=72"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.dataplatform.lt\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=72"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}