I took rviscomi’s query from Use of deprecated HTML features on the web? - #2 by rviscomi and included also the elements from the HTML standard’s element index.
#standardSQL
SELECT
LOWER(tag) AS tag,
COUNT(0) AS frequency,
COUNT(DISTINCT url) AS urls
FROM (
SELECT
url,
REGEXP_EXTRACT_ALL(body,
r'(?i)<(a|abbr|address|area|article|aside|audio|b|base|bdi|bdo|blockquote|body|br|button|canvas|caption|cite|code|col|colgroup|data|datalist|dd|del|details|dfn|dialog|div|dl|dt|em|embed|fieldset|figcaption|figure|footer|form|h1|h2|h3|h4|h5|h6|head|header|hgroup|hr|html|i|iframe|img|input|ins|kbd|label|legend|li|link|main|map|mark|math|menu|meta|meter|nav|noscript|object|ol|optgroup|option|output|p|param|picture|pre|progress|q|rp|rt|ruby|s|samp|script|section|select|slot|small|source|span|strong|style|sub|summary|sup|svg|table|tbody|td|template|textarea|tfoot|th|thead|time|title|tr|track|u|ul|var|video|wbr|applet|acronym|bgsound|dir|noframes|isindex|keygen|listing|menuitem|nextid|noembed|plaintext|rb|rtc|strike|xmp|basefont|big|blink|center|font|multicol|nobr|spacer|tt|marquee)(?:\s|/?>)') AS tags
FROM
`httparchive.response_bodies.2018_08_01_desktop`
WHERE
page = url),
UNNEST(tags) AS tag
GROUP BY
tag
ORDER BY
frequency DESC
result
| tag | frequency | urls |
|---|---|---|
| div | 220195805 | 1211109 |
| a | 199458214 | 1200656 |
| span | 114503663 | 1112859 |
| li | 103969319 | 1058955 |
| img | 43772141 | 1159543 |
| br | 37696955 | 919076 |
| p | 34059594 | 1049666 |
| script | 28445225 | 1219710 |
| td | 21821910 | 379919 |
| ul | 20357473 | 1058381 |
| option | 19794469 | 225487 |
| meta | 17181194 | 1243561 |
| link | 15729968 | 1203501 |
| i | 14679869 | 507695 |
| input | 11293319 | 963068 |
| tr | 9006510 | 381240 |
| strong | 8277464 | 533532 |
| h2 | 7810122 | 824400 |
| h3 | 7713738 | 687682 |
| b | 6416492 | 365688 |
| h4 | 3979458 | 391438 |
| label | 3559358 | 465348 |
| table | 3239199 | 383133 |
| button | 2943780 | 528577 |
| font | 2824141 | 114445 |
| svg | 2781271 | 174392 |
| style | 2744027 | 771295 |
| section | 2735708 | 355809 |
| article | 2655492 | 239268 |
| dd | 2460003 | 128956 |
| em | 2363419 | 181172 |
| form | 2173133 | 913408 |
| h1 | 2141903 | 792153 |
| noscript | 2059937 | 657878 |
| html | 1801751 | 1254018 |
| header | 1778951 | 594533 |
| time | 1639966 | 100274 |
| dt | 1628304 | 137094 |
| title | 1546053 | 1243039 |
| body | 1340941 | 1251391 |
| figure | 1313226 | 90936 |
| head | 1310642 | 1258649 |
| dl | 1262478 | 144319 |
| h5 | 1187033 | 139380 |
| iframe | 1168314 | 480719 |
| hr | 1130165 | 213642 |
| footer | 1129654 | 589297 |
| nav | 1116152 | 522793 |
| th | 1103263 | 94127 |
| small | 1081972 | 126187 |
| source | 728478 | 43378 |
| aside | 699185 | 220425 |
| select | 682147 | 243226 |
| tbody | 677575 | 169824 |
| center | 647241 | 126940 |
| h6 | 554572 | 72875 |
| abbr | 512469 | 67101 |
| sup | 499779 | 45797 |
| ins | 488111 | 145038 |
| u | 470117 | 71011 |
| ol | 427367 | 122008 |
| blockquote | 333552 | 80347 |
| picture | 286900 | 22599 |
| figcaption | 284306 | 28687 |
| fieldset | 272000 | 108874 |
| area | 260413 | 22924 |
| code | 213435 | 9862 |
| textarea | 188809 | 108455 |
| video | 169210 | 58101 |
| cite | 167805 | 16468 |
| dfn | 160542 | 3198 |
| main | 157028 | 146292 |
| pre | 152872 | 24701 |
| param | 147404 | 19957 |
| nobr | 125292 | 10118 |
| base | 117838 | 114609 |
| del | 111279 | 8155 |
| thead | 102634 | 45434 |
| address | 85313 | 49030 |
| s | 74612 | 9097 |
| optgroup | 71642 | 10139 |
| wbr | 71276 | 3749 |
| legend | 70593 | 31788 |
| col | 70233 | 7857 |
| sub | 61539 | 6689 |
| big | 58883 | 8717 |
| strike | 57023 | 5489 |
| kbd | 55335 | 26240 |
| object | 50800 | 25941 |
| map | 49969 | 25427 |
| hgroup | 35623 | 15428 |
| var | 33507 | 1307 |
| embed | 33089 | 18822 |
| caption | 32155 | 24192 |
| summary | 26044 | 5249 |
| marquee | 25276 | 15068 |
| menu | 22740 | 6459 |
| canvas | 21707 | 8300 |
| colgroup | 19611 | 8885 |
| template | 19535 | 3054 |
| bdi | 19211 | 563 |
| q | 18785 | 3234 |
| audio | 18748 | 5507 |
| tt | 16842 | 1652 |
| tfoot | 13625 | 10410 |
| mark | 11541 | 2277 |
| details | 8623 | 3585 |
| samp | 7889 | 450 |
| acronym | 7810 | 1588 |
| blink | 5461 | 1554 |
| rp | 5388 | 161 |
| spacer | 4158 | 255 |
| rt | 3731 | 254 |
| ruby | 3726 | 264 |
| noframes | 3481 | 3052 |
| bdo | 3025 | 267 |
| rb | 1987 | 146 |
| data | 1958 | 286 |
| meter | 1422 | 85 |
| menuitem | 1334 | 52 |
| output | 1284 | 380 |
| xmp | 1181 | 176 |
| slot | 1090 | 210 |
| plaintext | 1075 | 960 |
| progress | 1029 | 557 |
| dialog | 831 | 611 |
| applet | 812 | 710 |
| math | 758 | 41 |
| datalist | 689 | 503 |
| track | 583 | 322 |
| basefont | 561 | 233 |
| dir | 546 | 122 |
| bgsound | 349 | 325 |
| noembed | 270 | 199 |
| nextid | 8 | 1 |
| multicol | 5 | 2 |
| listing | 2 | 2 |
Number of pages is
SELECT COUNT(0) AS num FROM [httparchive:response_bodies.2018_08_01_desktop] WHERE page = url
→ 1294654
Ordering by urls and adding a percentage col:
| tag | frequency | urls | percent |
|---|---|---|---|
| head | 1310642 | 1258649 | 97.22 |
| html | 1801751 | 1254018 | 96.86 |
| body | 1340941 | 1251391 | 96.66 |
| meta | 17181194 | 1243561 | 96.05 |
| title | 1546053 | 1243039 | 96.01 |
| script | 28445225 | 1219710 | 94.21 |
| div | 220195805 | 1211109 | 93.55 |
| link | 15729968 | 1203501 | 92.96 |
| a | 199458214 | 1200656 | 92.74 |
| img | 43772141 | 1159543 | 89.56 |
| span | 114503663 | 1112859 | 85.96 |
| li | 103969319 | 1058955 | 81.79 |
| ul | 20357473 | 1058381 | 81.75 |
| p | 34059594 | 1049666 | 81.08 |
| input | 11293319 | 963068 | 74.39 |
| br | 37696955 | 919076 | 70.99 |
| form | 2173133 | 913408 | 70.55 |
| h2 | 7810122 | 824400 | 63.68 |
| h1 | 2141903 | 792153 | 61.19 |
| style | 2744027 | 771295 | 59.58 |
| h3 | 7713738 | 687682 | 53.12 |
| noscript | 2059937 | 657878 | 50.81 |
| header | 1778951 | 594533 | 45.92 |
| footer | 1129654 | 589297 | 45.52 |
| strong | 8277464 | 533532 | 41.21 |
| button | 2943780 | 528577 | 40.83 |
| nav | 1116152 | 522793 | 40.38 |
| i | 14679869 | 507695 | 39.21 |
| iframe | 1168314 | 480719 | 37.13 |
| label | 3559358 | 465348 | 35.94 |
| h4 | 3979458 | 391438 | 30.23 |
| table | 3239199 | 383133 | 29.59 |
| tr | 9006510 | 381240 | 29.45 |
| td | 21821910 | 379919 | 29.35 |
| b | 6416492 | 365688 | 28.25 |
| section | 2735708 | 355809 | 27.48 |
| select | 682147 | 243226 | 18.79 |
| article | 2655492 | 239268 | 18.48 |
| option | 19794469 | 225487 | 17.42 |
| aside | 699185 | 220425 | 17.03 |
| hr | 1130165 | 213642 | 16.5 |
| em | 2363419 | 181172 | 13.99 |
| svg | 2781271 | 174392 | 13.47 |
| tbody | 677575 | 169824 | 13.12 |
| main | 157028 | 146292 | 11.3 |
| ins | 488111 | 145038 | 11.2 |
| dl | 1262478 | 144319 | 11.15 |
| h5 | 1187033 | 139380 | 10.77 |
| dt | 1628304 | 137094 | 10.59 |
| dd | 2460003 | 128956 | 9.96 |
| center | 647241 | 126940 | 9.8 |
| small | 1081972 | 126187 | 9.75 |
| ol | 427367 | 122008 | 9.42 |
| base | 117838 | 114609 | 8.85 |
| font | 2824141 | 114445 | 8.84 |
| fieldset | 272000 | 108874 | 8.41 |
| textarea | 188809 | 108455 | 8.38 |
| time | 1639966 | 100274 | 7.75 |
| th | 1103263 | 94127 | 7.27 |
| figure | 1313226 | 90936 | 7.02 |
| blockquote | 333552 | 80347 | 6.21 |
| h6 | 554572 | 72875 | 5.63 |
| u | 470117 | 71011 | 5.48 |
| abbr | 512469 | 67101 | 5.18 |
| video | 169210 | 58101 | 4.49 |
| address | 85313 | 49030 | 3.79 |
| sup | 499779 | 45797 | 3.54 |
| thead | 102634 | 45434 | 3.51 |
| source | 728478 | 43378 | 3.35 |
| legend | 70593 | 31788 | 2.46 |
| figcaption | 284306 | 28687 | 2.22 |
| kbd | 55335 | 26240 | 2.03 |
| object | 50800 | 25941 | 2.0 |
| map | 49969 | 25427 | 1.96 |
| pre | 152872 | 24701 | 1.91 |
| caption | 32155 | 24192 | 1.87 |
| area | 260413 | 22924 | 1.77 |
| picture | 286900 | 22599 | 1.75 |
| param | 147404 | 19957 | 1.54 |
| embed | 33089 | 18822 | 1.45 |
| cite | 167805 | 16468 | 1.27 |
| hgroup | 35623 | 15428 | 1.19 |
| marquee | 25276 | 15068 | 1.16 |
| tfoot | 13625 | 10410 | 0.8 |
| optgroup | 71642 | 10139 | 0.78 |
| nobr | 125292 | 10118 | 0.78 |
| code | 213435 | 9862 | 0.76 |
| s | 74612 | 9097 | 0.7 |
| colgroup | 19611 | 8885 | 0.69 |
| big | 58883 | 8717 | 0.67 |
| canvas | 21707 | 8300 | 0.64 |
| del | 111279 | 8155 | 0.63 |
| col | 70233 | 7857 | 0.61 |
| sub | 61539 | 6689 | 0.52 |
| menu | 22740 | 6459 | 0.5 |
| audio | 18748 | 5507 | 0.43 |
| strike | 57023 | 5489 | 0.42 |
| summary | 26044 | 5249 | 0.41 |
| wbr | 71276 | 3749 | 0.29 |
| details | 8623 | 3585 | 0.28 |
| q | 18785 | 3234 | 0.25 |
| dfn | 160542 | 3198 | 0.25 |
| template | 19535 | 3054 | 0.24 |
| noframes | 3481 | 3052 | 0.24 |
| mark | 11541 | 2277 | 0.18 |
| tt | 16842 | 1652 | 0.13 |
| acronym | 7810 | 1588 | 0.12 |
| blink | 5461 | 1554 | 0.12 |
| var | 33507 | 1307 | 0.1 |
| plaintext | 1075 | 960 | 0.07 |
| applet | 812 | 710 | 0.05 |
| dialog | 831 | 611 | 0.05 |
| bdi | 19211 | 563 | 0.04 |
| progress | 1029 | 557 | 0.04 |
| datalist | 689 | 503 | 0.04 |
| samp | 7889 | 450 | 0.03 |
| output | 1284 | 380 | 0.03 |
| bgsound | 349 | 325 | 0.03 |
| track | 583 | 322 | 0.02 |
| data | 1958 | 286 | 0.02 |
| bdo | 3025 | 267 | 0.02 |
| ruby | 3726 | 264 | 0.02 |
| spacer | 4158 | 255 | 0.02 |
| rt | 3731 | 254 | 0.02 |
| basefont | 561 | 233 | 0.02 |
| slot | 1090 | 210 | 0.02 |
| noembed | 270 | 199 | 0.02 |
| xmp | 1181 | 176 | 0.01 |
| rp | 5388 | 161 | 0.01 |
| rb | 1987 | 146 | 0.01 |
| dir | 546 | 122 | 0.01 |
| meter | 1422 | 85 | 0.01 |
| menuitem | 1334 | 52 | 0.0 |
| math | 758 | 41 | 0.0 |
| multicol | 5 | 2 | 0.0 |
| listing | 2 | 2 | 0.0 |
| nextid | 8 | 1 | 0.0 |