Merge branch 'main' of github.com:HTTPArchive/almanac.httparchive.org…

… into production
HTTPArchive · Dec 2, 2024 · a58c704 · a58c704
2 parents f79361b + 91885c1
commit a58c704
Show file tree

Hide file tree

Showing 96 changed files with 1,498 additions and 250 deletions.
diff --git a/sql/2024/seo/robots-txt-size-2024.sql b/sql/2024/seo/robots-txt-size-2024.sql
@@ -1,37 +1,31 @@
 #standardSQL
 # Robots.txt size
-CREATE TEMPORARY FUNCTION getRobotsSize(payload STRING)
-RETURNS FLOAT64 LANGUAGE js AS '''
-try {
-  var $ = JSON.parse(payload);
-  var robots = JSON.parse($._robots_txt);
-  return robots['size']/1024;
-} catch (e) {
-  return 0;
-}
-''';
-
 SELECT
   client,
   COUNT(DISTINCT(site)) AS sites,
+  SAFE_DIVIDE(COUNTIF(robots_size = 0), COUNT(DISTINCT(site))) AS pct_0,
   SAFE_DIVIDE(COUNTIF(robots_size > 0 AND robots_size <= 100), COUNT(DISTINCT(site))) AS pct_0_100,
   SAFE_DIVIDE(COUNTIF(robots_size > 100 AND robots_size <= 200), COUNT(DISTINCT(site))) AS pct_100_200,
   SAFE_DIVIDE(COUNTIF(robots_size > 200 AND robots_size <= 300), COUNT(DISTINCT(site))) AS pct_200_300,
   SAFE_DIVIDE(COUNTIF(robots_size > 300 AND robots_size <= 400), COUNT(DISTINCT(site))) AS pct_300_400,
   SAFE_DIVIDE(COUNTIF(robots_size > 400 AND robots_size <= 500), COUNT(DISTINCT(site))) AS pct_400_500,
   SAFE_DIVIDE(COUNTIF(robots_size > 500), COUNT(DISTINCT(site))) AS pct_gt500,
-  SAFE_DIVIDE(COUNTIF(robots_size = 0), COUNT(DISTINCT(site))) AS pct_missing,
+  SAFE_DIVIDE(COUNTIF(robots_size IS NULL), COUNT(DISTINCT(site))) AS pct_missing,
   COUNTIF(robots_size > 500) AS count_gt500,
-  COUNTIF(robots_size = 0) AS count_missing
+  COUNTIF(robots_size IS NULL) AS count_missing
 FROM (
   SELECT
     client,
-    page AS site,
-    getRobotsSize(payload) AS robots_size
+    root_page AS site,
+    custom_metrics.robots_txt,
+    FLOAT64(custom_metrics.robots_txt.size_kib) AS robots_size
   FROM
-    `httparchive.all.pages`
-  WHERE date = '2024-06-01'
-) -- noqa: L062
+    `httparchive.crawl.pages`
+  WHERE
+    date = '2024-06-01' AND
+    is_root_page AND -- no need to crawl inner pages for this one
+    custom_metrics.robots_txt.status IS NOT NULL
+)
 GROUP BY
   client
 ORDER BY

diff --git a/src/config/2024.json b/src/config/2024.json
@@ -75,8 +75,7 @@
           "part": "II",
           "chapter_number": "9",
           "title": "SEO",
-          "slug": "seo",
-          "todo": true
+          "slug": "seo"
         },
         {
           "part": "II",

diff --git a/src/config/contributors.json b/src/config/contributors.json
@@ -1191,7 +1191,10 @@
   },
   "dwsmart": {
     "avatar_url": "11179452",
+    "bluesky": "tamethebots.com",
     "github": "dwsmart",
+    "linkedin": "davewsmart",
+    "mastodon": "https://seocommunity.social/@dwsmart",
     "name": "Dave Smart",
     "teams": {
       "2020": [
@@ -1203,9 +1206,11 @@
       "2022": [
         "authors",
         "reviewers"
+      ],
+      "2024": [
+        "authors"
       ]
     },
-    "twitter": "davewsmart",
     "website": "https://tamethebots.com"
   },
   "dsottimano": {
@@ -2044,7 +2049,9 @@
   },
   "fellowhuman1101": {
     "avatar_url": "52051775",
+    "bluesky": "not-a-robot.com",
     "github": "fellowhuman1101",
+    "linkedin": "jamie-indigo",
     "name": "Jamie Indigo",
     "teams": {
       "2020": [
@@ -2056,6 +2063,10 @@
       ],
       "2022": [
         "authors"
+      ],
+      "2024": [
+        "authors",
+        "leads"
       ]
     },
     "twitter": "Jammer_Volts",
@@ -3023,13 +3034,22 @@
   },
   "MichaelLewittes": {
     "avatar_url": "96250205",
+    "bluesky": "michaellewittes.bsky.social",
     "github": "MichaelLewittes",
+    "linkedin": "michael-lewittes-a22b831",
+    "mastodon": "https://seocommunity.social/@MichaelLewittes",
     "name": "Michael Lewittes",
     "teams": {
       "2022": [
         "editors"
+      ],
+      "2024": [
+        "authors",
+        "editors"
       ]
-    }
+    },
+    "twitter": "MichaelLewittes",
+    "website": "https://www.ranktify.com/team"
   },
   "MichaelSolati": {
     "avatar_url": "11811422",
@@ -4871,5 +4891,42 @@
         "reviewers"
       ]
     }
+  },
+  "mikaelaraujo": {
+    "avatar_url": "4764075",
+    "bluesky": "mikaelaraujo.bsky.social",
+    "github": "mikaelaraujo",
+    "linkedin": "mikael-araujo",
+    "name": "Mikael Araújo",
+    "teams": {
+      "2024": [
+        "authors"
+      ]
+    },
+    "threads": "@mikaelaraujo",
+    "twitter": "miknaraujo",
+    "website": "https://www.mikaelaraujo.com"
+  },
+  "henryp25": {
+    "avatar_url": "62102954",
+    "github": "henryp25",
+    "linkedin": "henry-price-9ab362b4",
+    "name": "Henry Price",
+    "teams": {
+      "2024": [
+        "analysts"
+      ]
+    }
+  },
+  "cnichols013" :{
+    "avatar_url": "73146375",
+    "github": "cnichols013",
+    "linkedin": "chris-nichols",
+    "name": "Chris Nichols",
+    "teams": {
+      "2024": [
+        "analysts"
+      ]
+    }
   }
 }