SELECT * FROM (
SELECT page, url, REGEXP_EXTRACT(LOWER(content), r'(<link\s(?:[^>]+\s)?disabled(?:(?:\s|[=\/])[^>]*>|>))') as match FROM (
SELECT
page,
url,
JSON_EXTRACT(payload, '$._body') AS hasBody,
JSON_EXTRACT(payload, '$.response.content.text') AS content,
JSON_EXTRACT(payload, '$._contentType') AS type
FROM [httparchive:har.chrome_feb_1_2016_requests]
Simon Pieters zcorpan
zcorpan
/ gist:2c2b3114ddd636515b95
Created
August 26, 2015 14:49
httparchive results for 'content' without :before/:after
This file contains 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
| SELECT page, url | |
| FROM [httparchive:runs.2014_08_15_requests_body] | |
| WHERE mimeType CONTAINS "text/css" | |
| AND REGEXP_MATCH(LOWER(body), r"([;\{]|\s)content\s*:\s*[\"']") | |
| AND NOT LOWER(body) CONTAINS ":before" | |
| AND NOT LOWER(body) CONTAINS ":after" | |
| page,url | |
| http://www.orcsweb.com/,http://www.orcsweb.com/wp-content/plugins/wordpress-post-tabs/css/styles/default/style.css?ver=1.4 | |
| http://www.kabelbw.de/,http://www.kabelbw.de/content/www-kabelbw-de/templated/utilities/footnotes/footnotes-content/_jcr_content/template.a233dd4b6908ca42d0bd29dc31ccb0d9.css |
zcorpan
/ urls-with-showModalDialog
Created
February 25, 2014 07:59
URLs using showModalDialog, from https://gist.github.com/miketaylr/9190295
This file contains 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
| uaua.info | |
| descargasnsn.com | |
| evgenyfireform.com | |
| migente.com | |
| tumejortv.com | |
| medya73.com | |
| propertyroom.com | |
| reverb.com | |
| kosmetista.ru | |
| rayfile.com |
zcorpan
/ foster-parent.txt
Created
May 6, 2014 23:14
Rough search for foster parentings in http://webdevdata.org/ data set 2013-09-01 102,000 pages
This file has been truncated, but you can view the full file.
This file contains 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
| ./00/aawsat.com_001b36ab685661428c656f1098c6dba3.html.txt: <td><INPUT type=image src='/01common/pix/go.gif' name=I4 ></td><INPUT type=hidden name='cache' value='0'></form> | |
| ./00/penoestribo.com.br_00bc19cab0dae2549442afc6d59c5e37.html.txt:</td><br> | |
| ./01/erotema.ru_0164e896c185b678118ddf0b033a4482.html.txt: <tr><noindex> | |
| ./01/erotema.ru_0164e896c185b678118ddf0b033a4482.html.txt: <td> </td><noindex> | |
| ./01/erotema.ru_0164e896c185b678118ddf0b033a4482.html.txt: <td> </td><noindex> | |
| ./02/kingsex.eu_02edff6fbbd667807153b0d5f534ebe5.html.txt:</tr> <div class="clear"></div> | |
| ./02/mybabyclothes.com_028919e368cd0a19e815e4a2ef80ef2b.html.txt: <tr><td></td></tr><div class="titleMain">featured items</div><tr><td class="main"><!-- D featured_products_mainpage updated vinod //--> | |
| ./02/supplementwarehouse.com_023afe2df21244ed4d10152504abe976.html.txt: </DIV></TD><div id="autocomplete_choices" class="autocomplete"></div> | |
| ./03/laserpointerforums.com_03b35d25fa9b3e46e202e466d76d58e4.html |
This file contains 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
| import re | |
| from HTMLParser import HTMLParser | |
| from urlparse import urljoin | |
| import os | |
| src = '' | |
| width = False | |
| height = False | |
| class MyHTMLParser(HTMLParser): |
zcorpan
/ gist:5f0e36efdd35b800a6be
Created
September 2, 2015 08:19
WHATWG HTML svn revision to git commit hash
This file contains 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
| revs = { | |
| '8891': '80ff74291cf0f97e98e00298e4f463ac63ac2139', | |
| '8890': 'b67efcb6068b71915a37896300987e903be0e632', | |
| '8889': '4fb1fd704451cf9ca4008ded53b080c3b85e99ce', | |
| '8888': '6dd7f19415c2f04388b57073f2617556b446a3d9', | |
| '8887': '91799e2e56aa82d40de08ac5aece4d844e5c5447', | |
| '8886': 'e2f88d6709a85741c4c57c8f65b119df9530f819', | |
| '8885': '07084548449afb4a3a867cc2782f91095bae1e89', | |
| '8884': 'ddbab10c90ab369e6c23e750315b02a5edc48cc2', | |
| '8883': '61777f9d2457eead549bce1a16448d194041d3a9', |
zcorpan
/ parseMetaRefresh.html
Created
October 20, 2015 08:31
This file contains 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
| <!doctype html> | |
| <meta charset=utf-8> | |
| <script src=https://w3c-test.org/resources/testharness.js></script> | |
| <script> | |
| function collectCharacters(input, pos, chars) { | |
| var startPos = pos; | |
| while (chars.indexOf(input[pos]) != -1) { | |
| pos++; | |
| if (input[pos] === undefined) { | |
| break; |
zcorpan
/ bliss-perf-delete.html
Created
December 7, 2015 13:42
This file contains 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
| <!doctype html> | |
| <script src=bliss.js></script> | |
| <script> | |
| onload = function() { | |
| var start = performance.now(); | |
| var rows = []; | |
| for (var i = 0; i <= 50000; ++i) { | |
| rows.push($.create({ |
zcorpan
/ invalid-coords-webdevdata.txt
Created
January 13, 2016 22:56
This file contains 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
| ./aa/wetter.com_aa72bc7f58f52a956aefd7930808f787.html.txt:<area class="ForecastCityOverlay" alt="Berlin" title="Berlin" shape="poly" coords="264.788457758,119.230041959,296.788457758,119.230041959,296.788457758,105.230041959,264.788457758,105.230041959,264.788457758,119.230041959" href="/deutschland/berlin/DE0001020.html" > | |
| ./aa/wetter.com_aa72bc7f58f52a956aefd7930808f787.html.txt:<area class="ForecastCityOverlay" alt="Hamburg" title="Hamburg" shape="poly" coords="129.189202721,75.7755327482,181.189202721,75.7755327482,181.189202721,61.7755327482,129.189202721,61.7755327482,129.189202721,75.7755327482" href="/deutschland/hamburg/DE0004130.html" > | |
| ./aa/wetter.com_aa72bc7f58f52a956aefd7930808f787.html.txt:<area class="ForecastCityOverlay" alt="München" title="München" shape="poly" coords="220.179682511,307.487537772,280.179682511,307.487537772,280.179682511,293.487537772,220.179682511,293.487537772,220.179682511,307.487537772" href="/deutschland/muenchen/DE0006515.html" > | |
| ./aa/wetter.com_aa72bc7f58f52a956aefd79 |
zcorpan
/ parse-coords.html
Last active
January 14, 2016 13:46
This file contains 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
| <!doctype html> | |
| <meta charset=utf-8> | |
| <title>coords</title> | |
| <style> | |
| table { table-layout:fixed; width:100%; border-collapse:collapse } | |
| td { max-width:25%; overflow:hidden; border:2px solid gray; padding:0.5em; font-family:monospace } | |
| </style> | |
| <table> | |
| <tr><th>test<th>old parser<th>new parser (POC)<th>new parser (new-spec-compliant) | |
| <script> |
zcorpan
/ link-disabled.md
Created
May 2, 2016 09:01
httparchive research for https://github.com/whatwg/html/issues/1081
OlderNewer