From 31ac25b46c5c97fec9c11e45c645b188c072534e Mon Sep 17 00:00:00 2001 From: Andreas Krennmair Date: Tue, 19 Sep 2023 13:06:55 +0200 Subject: [PATCH 1/2] Add User-Agent detection for Google-Read-Aloud. --- regexes.yaml | 2 +- tests/test_ua.yaml | 12 ++++++++++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/regexes.yaml b/regexes.yaml index a8f8e097..dc42854b 100644 --- a/regexes.yaml +++ b/regexes.yaml @@ -148,7 +148,7 @@ user_agent_parsers: family_replacement: 'Pinterestbot' # Bots - - regex: '(CSimpleSpider|Cityreview Robot|CrawlDaddy|CrawlFire|Finderbots|Index crawler|Job Roboter|KiwiStatus Spider|Lijit Crawler|QuerySeekerSpider|ScollSpider|Trends Crawler|USyd-NLP-Spider|SiteCat Webbot|BotName\/\$BotVersion|123metaspider-Bot|1470\.net crawler|50\.nu|8bo Crawler Bot|Aboundex|Accoona-[A-z]{1,30}-Agent|AdsBot-Google(?:-[a-z]{1,30}|)|altavista|AppEngine-Google|archive.{0,30}\.org_bot|archiver|Ask Jeeves|[Bb]ai[Dd]u[Ss]pider(?:-[A-Za-z]{1,30})(?:-[A-Za-z]{1,30}|)|bingbot|BingPreview|blitzbot|BlogBridge|Bloglovin|BoardReader Blog Indexer|BoardReader Favicon Fetcher|boitho.com-dc|BotSeer|BUbiNG|\b\w{0,30}favicon\w{0,30}\b|\bYeti(?:-[a-z]{1,30}|)|Catchpoint(?: bot|)|[Cc]harlotte|Checklinks|clumboot|Comodo HTTP\(S\) Crawler|Comodo-Webinspector-Crawler|ConveraCrawler|CRAWL-E|CrawlConvera|Daumoa(?:-feedfetcher|)|Feed Seeker Bot|Feedbin|findlinks|Flamingo_SearchEngine|FollowSite Bot|furlbot|Genieo|gigabot|GomezAgent|gonzo1|(?:[a-zA-Z]{1,30}-|)Googlebot(?:-[a-zA-Z]{1,30}|)|Google SketchUp|grub-client|gsa-crawler|heritrix|HiddenMarket|holmes|HooWWWer|htdig|ia_archiver|ICC-Crawler|Icarus6j|ichiro(?:/mobile|)|IconSurf|IlTrovatore(?:-Setaccio|)|InfuzApp|Innovazion Crawler|InternetArchive|IP2[a-z]{1,30}Bot|jbot\b|KaloogaBot|Kraken|Kurzor|larbin|LEIA|LesnikBot|Linguee Bot|LinkAider|LinkedInBot|Lite Bot|Llaut|lycos|Mail\.RU_Bot|masscan|masidani_bot|Mediapartners-Google|Microsoft .{0,30} Bot|mogimogi|mozDex|MJ12bot|msnbot(?:-media {0,2}|)|msrbot|Mtps Feed Aggregation System|netresearch|Netvibes|NewsGator[^/]{0,30}|^NING|Nutch[^/]{0,30}|Nymesis|ObjectsSearch|OgScrper|Orbiter|OOZBOT|PagePeeker|PagesInventory|PaxleFramework|Peeplo Screenshot Bot|PHPCrawl|PlantyNet_WebRobot|Pompos|Qwantify|Read%20Later|Reaper|RedCarpet|Retreiver|Riddler|Rival IQ|scooter|Scrapy|Scrubby|searchsight|seekbot|semanticdiscovery|SemrushBot|Simpy|SimplePie|SEOstats|SimpleRSS|SiteCon|Slackbot-LinkExpanding|Slack-ImgProxy|Slurp|snappy|Speedy Spider|Squrl Java|Stringer|TheUsefulbot|ThumbShotsBot|Thumbshots\.ru|Tiny Tiny RSS|Twitterbot|WhatsApp|URL2PNG|Vagabondo|VoilaBot|^vortex|Votay bot|^voyager|WASALive.Bot|Web-sniffer|WebThumb|WeSEE:[A-z]{1,30}|WhatWeb|WIRE|WordPress|Wotbox|www\.almaden\.ibm\.com|Xenu(?:.s|) Link Sleuth|Xerka [A-z]{1,30}Bot|yacy(?:bot|)|YahooSeeker|Yahoo! Slurp|Yandex\w{1,30}|YodaoBot(?:-[A-z]{1,30}|)|YottaaMonitor|Yowedo|^Zao|^Zao-Crawler|ZeBot_www\.ze\.bz|ZooShot|ZyBorg|ArcGIS Hub Indexer)(?:[ /]v?(\d+)(?:\.(\d+)(?:\.(\d+)|)|)|)' + - regex: '(CSimpleSpider|Cityreview Robot|CrawlDaddy|CrawlFire|Finderbots|Index crawler|Job Roboter|KiwiStatus Spider|Lijit Crawler|QuerySeekerSpider|ScollSpider|Trends Crawler|USyd-NLP-Spider|SiteCat Webbot|BotName\/\$BotVersion|123metaspider-Bot|1470\.net crawler|50\.nu|8bo Crawler Bot|Aboundex|Accoona-[A-z]{1,30}-Agent|Google-Read-Aloud|AdsBot-Google(?:-[a-z]{1,30}|)|altavista|AppEngine-Google|archive.{0,30}\.org_bot|archiver|Ask Jeeves|[Bb]ai[Dd]u[Ss]pider(?:-[A-Za-z]{1,30})(?:-[A-Za-z]{1,30}|)|bingbot|BingPreview|blitzbot|BlogBridge|Bloglovin|BoardReader Blog Indexer|BoardReader Favicon Fetcher|boitho.com-dc|BotSeer|BUbiNG|\b\w{0,30}favicon\w{0,30}\b|\bYeti(?:-[a-z]{1,30}|)|Catchpoint(?: bot|)|[Cc]harlotte|Checklinks|clumboot|Comodo HTTP\(S\) Crawler|Comodo-Webinspector-Crawler|ConveraCrawler|CRAWL-E|CrawlConvera|Daumoa(?:-feedfetcher|)|Feed Seeker Bot|Feedbin|findlinks|Flamingo_SearchEngine|FollowSite Bot|furlbot|Genieo|gigabot|GomezAgent|gonzo1|(?:[a-zA-Z]{1,30}-|)Googlebot(?:-[a-zA-Z]{1,30}|)|Google SketchUp|grub-client|gsa-crawler|heritrix|HiddenMarket|holmes|HooWWWer|htdig|ia_archiver|ICC-Crawler|Icarus6j|ichiro(?:/mobile|)|IconSurf|IlTrovatore(?:-Setaccio|)|InfuzApp|Innovazion Crawler|InternetArchive|IP2[a-z]{1,30}Bot|jbot\b|KaloogaBot|Kraken|Kurzor|larbin|LEIA|LesnikBot|Linguee Bot|LinkAider|LinkedInBot|Lite Bot|Llaut|lycos|Mail\.RU_Bot|masscan|masidani_bot|Mediapartners-Google|Microsoft .{0,30} Bot|mogimogi|mozDex|MJ12bot|msnbot(?:-media {0,2}|)|msrbot|Mtps Feed Aggregation System|netresearch|Netvibes|NewsGator[^/]{0,30}|^NING|Nutch[^/]{0,30}|Nymesis|ObjectsSearch|OgScrper|Orbiter|OOZBOT|PagePeeker|PagesInventory|PaxleFramework|Peeplo Screenshot Bot|PHPCrawl|PlantyNet_WebRobot|Pompos|Qwantify|Read%20Later|Reaper|RedCarpet|Retreiver|Riddler|Rival IQ|scooter|Scrapy|Scrubby|searchsight|seekbot|semanticdiscovery|SemrushBot|Simpy|SimplePie|SEOstats|SimpleRSS|SiteCon|Slackbot-LinkExpanding|Slack-ImgProxy|Slurp|snappy|Speedy Spider|Squrl Java|Stringer|TheUsefulbot|ThumbShotsBot|Thumbshots\.ru|Tiny Tiny RSS|Twitterbot|WhatsApp|URL2PNG|Vagabondo|VoilaBot|^vortex|Votay bot|^voyager|WASALive.Bot|Web-sniffer|WebThumb|WeSEE:[A-z]{1,30}|WhatWeb|WIRE|WordPress|Wotbox|www\.almaden\.ibm\.com|Xenu(?:.s|) Link Sleuth|Xerka [A-z]{1,30}Bot|yacy(?:bot|)|YahooSeeker|Yahoo! Slurp|Yandex\w{1,30}|YodaoBot(?:-[A-z]{1,30}|)|YottaaMonitor|Yowedo|^Zao|^Zao-Crawler|ZeBot_www\.ze\.bz|ZooShot|ZyBorg|ArcGIS Hub Indexer)(?:[ /]v?(\d+)(?:\.(\d+)(?:\.(\d+)|)|)|)' # AWS S3 Clients # must come before "Bots General matcher" to catch "boto"/"boto3" before "bot" diff --git a/tests/test_ua.yaml b/tests/test_ua.yaml index 2b2bee8c..ec6261f1 100644 --- a/tests/test_ua.yaml +++ b/tests/test_ua.yaml @@ -8681,3 +8681,15 @@ test_cases: major: '3' minor: '2' patch: '1' + + - user_agent_string: 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 Safari/537.36 (compatible; Google-Read-Aloud; +https://support.google.com/webmasters/answer/1061943)' + family: 'Google-Read-Aloud' + major: + minor: + patch: + + - user_agent_string: 'Mozilla/5.0 (Linux; Android 7.0; SM-G930V Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.125 Mobile Safari/537.36 (compatible; Google-Read-Aloud; +https://support.google.com/webmasters/answer/1061943)' + family: 'Google-Read-Aloud' + major: + minor: + patch: \ No newline at end of file From 6f26316127ccf5615f58132d532d3154f57c2c92 Mon Sep 17 00:00:00 2001 From: Andreas Krennmair Date: Tue, 19 Sep 2023 13:24:18 +0200 Subject: [PATCH 2/2] Add device detection for Google-Read-Aloud. --- regexes.yaml | 10 ++++++++++ tests/test_device.yaml | 9 ++++++++- 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/regexes.yaml b/regexes.yaml index dc42854b..db962640 100644 --- a/regexes.yaml +++ b/regexes.yaml @@ -1870,6 +1870,16 @@ device_parsers: brand_replacement: 'Spider' model_replacement: 'Desktop' + # Google-Read-Aloud + - regex: 'Mozilla/.{0,200}Mobile.{1,100}Google-Read-Aloud' + device_replacement: 'Spider' + brand_replacement: 'Spider' + model_replacement: 'Smartphone' + - regex: 'Mozilla/.{0,200}Google-Read-Aloud' + device_replacement: 'Spider' + brand_replacement: 'Spider' + model_replacement: 'Desktop' + ######### # WebBrowser for SmartWatch # @ref: https://play.google.com/store/apps/details?id=se.vaggan.webbrowser&hl=en diff --git a/tests/test_device.yaml b/tests/test_device.yaml index 990c2208..acaadcca 100644 --- a/tests/test_device.yaml +++ b/tests/test_device.yaml @@ -80579,5 +80579,12 @@ test_cases: brand: 'Motorola' model: 'motorola moto g play (2021)' + - user_agent_string: 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 Safari/537.36 (compatible; Google-Read-Aloud; +https://support.google.com/webmasters/answer/1061943)' + family: 'Spider' + brand: 'Spider' + model: 'Desktop' - \ No newline at end of file + - user_agent_string: 'Mozilla/5.0 (Linux; Android 7.0; SM-G930V Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.125 Mobile Safari/537.36 (compatible; Google-Read-Aloud; +https://support.google.com/webmasters/answer/1061943)' + family: 'Spider' + brand: 'Spider' + model: 'Smartphone' \ No newline at end of file