crawler-user-agents 1.0.106 → 1.0.108
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/crawler-user-agents.json +110 -2
- package/main.php +1 -1
- package/package.json +1 -1
package/crawler-user-agents.json
CHANGED
|
@@ -101,6 +101,32 @@
|
|
|
101
101
|
]
|
|
102
102
|
}
|
|
103
103
|
,
|
|
104
|
+
{
|
|
105
|
+
"pattern": "Google-InspectionTool",
|
|
106
|
+
"url": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
|
|
107
|
+
"instances": [
|
|
108
|
+
"Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/W.X.Y.Z Mobile Safari/537.36 (compatible; Google-InspectionTool/1.0)",
|
|
109
|
+
"Mozilla/5.0 (compatible; Google-InspectionTool/1.0)"
|
|
110
|
+
]
|
|
111
|
+
}
|
|
112
|
+
,
|
|
113
|
+
{
|
|
114
|
+
"pattern": "Storebot-Google",
|
|
115
|
+
"url": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
|
|
116
|
+
"instances": [
|
|
117
|
+
"Mozilla/5.0 (X11; Linux x86_64; Storebot-Google/1.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36",
|
|
118
|
+
"Mozilla/5.0 (Linux; Android 8.0; Pixel 2 Build/OPD3.170816.012; Storebot-Google/1.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Mobile Safari/537.36"
|
|
119
|
+
]
|
|
120
|
+
}
|
|
121
|
+
,
|
|
122
|
+
{
|
|
123
|
+
"pattern": "GoogleOther",
|
|
124
|
+
"url": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers",
|
|
125
|
+
"instances": [
|
|
126
|
+
"GoogleOther"
|
|
127
|
+
]
|
|
128
|
+
}
|
|
129
|
+
,
|
|
104
130
|
{
|
|
105
131
|
"pattern": "bingbot",
|
|
106
132
|
"url": "http://www.bing.com/bingbot.htm",
|
|
@@ -198,7 +224,7 @@
|
|
|
198
224
|
"instances": [
|
|
199
225
|
"python-httpx/0.16.1",
|
|
200
226
|
"python-httpx/0.13.0.dev1"
|
|
201
|
-
|
|
227
|
+
|
|
202
228
|
],
|
|
203
229
|
"url": "https://www.python-httpx.org"
|
|
204
230
|
}
|
|
@@ -4829,7 +4855,7 @@
|
|
|
4829
4855
|
"instances": [
|
|
4830
4856
|
"Mozilla/5.0 (compatible; Go-http-client/1.1; +centurybot9@gmail.com)"
|
|
4831
4857
|
],
|
|
4832
|
-
"url": "unknown"
|
|
4858
|
+
"url": "unknown"
|
|
4833
4859
|
},
|
|
4834
4860
|
{
|
|
4835
4861
|
"pattern": "Viber",
|
|
@@ -4990,5 +5016,87 @@
|
|
|
4990
5016
|
"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://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)",
|
|
4991
5017
|
"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://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers)"
|
|
4992
5018
|
]
|
|
5019
|
+
},
|
|
5020
|
+
{
|
|
5021
|
+
"pattern": "Valve\\/Steam",
|
|
5022
|
+
"addition_date": "2023/05/24",
|
|
5023
|
+
"instances": [
|
|
5024
|
+
"Valve/Steam HTTP Client 1.0 (SteamChatURLLookup)"
|
|
5025
|
+
]
|
|
5026
|
+
},
|
|
5027
|
+
{
|
|
5028
|
+
"pattern": "OdklBot\\/",
|
|
5029
|
+
"addition_date": "2023/05/24",
|
|
5030
|
+
"instances": [
|
|
5031
|
+
"OdklBot/1.0 (share@odnoklassniki.ru)",
|
|
5032
|
+
"Mozilla/5.0 (compatible; OdklBot/1.0 like Linux; klass@odnoklassniki.ru)"
|
|
5033
|
+
],
|
|
5034
|
+
"url": "https://odnoklassniki.ru/"
|
|
5035
|
+
},
|
|
5036
|
+
{
|
|
5037
|
+
"pattern": "GPTBot",
|
|
5038
|
+
"addition_date": "2023/08/09",
|
|
5039
|
+
"instances": [
|
|
5040
|
+
"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; GPTBot/1.0; +https://openai.com/gptbot)"
|
|
5041
|
+
],
|
|
5042
|
+
"url": "https://platform.openai.com/docs/gptbot"
|
|
5043
|
+
},
|
|
5044
|
+
{
|
|
5045
|
+
"pattern": "YandexRenderResourcesBot\\/",
|
|
5046
|
+
"addition_date": "2023/08/16",
|
|
5047
|
+
"instances": [
|
|
5048
|
+
"Mozilla/5.0 (compatible; YandexRenderResourcesBot/1.0; +http://yandex.com/bots) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0"
|
|
5049
|
+
],
|
|
5050
|
+
"url": "http://yandex.com/bots"
|
|
5051
|
+
},
|
|
5052
|
+
{
|
|
5053
|
+
"pattern": "LightspeedSystemsCrawler",
|
|
5054
|
+
"addition_date": "2023/08/16",
|
|
5055
|
+
"instances": [
|
|
5056
|
+
"LightspeedSystemsCrawler Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US"
|
|
5057
|
+
]
|
|
5058
|
+
},
|
|
5059
|
+
{
|
|
5060
|
+
"pattern": "ev-crawler\\/",
|
|
5061
|
+
"addition_date": "2023/08/16",
|
|
5062
|
+
"instances": [
|
|
5063
|
+
"Mozilla/5.0 (compatible; ev-crawler/1.0; +https://headline.com/legal/crawler)"
|
|
5064
|
+
],
|
|
5065
|
+
"url": "https://headline.com/legal/crawler"
|
|
5066
|
+
},
|
|
5067
|
+
{
|
|
5068
|
+
"pattern": "BitSightBot\\/",
|
|
5069
|
+
"addition_date": "2023/08/16",
|
|
5070
|
+
"instances": [
|
|
5071
|
+
"Mozilla/5.0 (compatible; BitSightBot/1.0)"
|
|
5072
|
+
],
|
|
5073
|
+
"url": "https://www.bitsight.com"
|
|
5074
|
+
},
|
|
5075
|
+
{
|
|
5076
|
+
"pattern": "woorankreview\\/",
|
|
5077
|
+
"addition_date": "2023/08/16",
|
|
5078
|
+
"instances": [
|
|
5079
|
+
"Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1 (compatible; woorankreview/2.0; +https://www.woorank.com/)",
|
|
5080
|
+
"Mozilla/5.0 (compatible; woorankreview/2.0; +https://www.woorank.com/)"
|
|
5081
|
+
],
|
|
5082
|
+
"url": "https://www.woorank.com/"
|
|
5083
|
+
},
|
|
5084
|
+
{
|
|
5085
|
+
"pattern": "Google-Safety",
|
|
5086
|
+
"addition_date": "2023/08/17",
|
|
5087
|
+
"instances": [
|
|
5088
|
+
"Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.5735.179 Mobile Safari/537.36 (compatible; Google-Safety; +http://www.google.com/bot.html)",
|
|
5089
|
+
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.5735.179 Safari/537.36 (compatible; Google-Safety; +http://www.google.com/bot.html)",
|
|
5090
|
+
"Google-Safety"
|
|
5091
|
+
],
|
|
5092
|
+
"url": "https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers"
|
|
5093
|
+
},
|
|
5094
|
+
{
|
|
5095
|
+
"pattern": "AwarioBot",
|
|
5096
|
+
"addition_date": "2023/08/23",
|
|
5097
|
+
"instances": [
|
|
5098
|
+
"Mozilla/5.0 (compatible; AwarioBot/1.0; +https://awario.com/bots.html)"
|
|
5099
|
+
],
|
|
5100
|
+
"url": "https://awario.com/bots.html"
|
|
4993
5101
|
}
|
|
4994
5102
|
]
|
package/main.php
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
<?php
|
|
2
2
|
if (!function_exists('get_crawler_user_agents_list')) {
|
|
3
3
|
function get_crawler_user_agents_list() {
|
|
4
|
-
return json_decode(file_get_contents('crawler-user-agents.json'), true);
|
|
4
|
+
return json_decode(file_get_contents(__DIR__.'/crawler-user-agents.json'), true);
|
|
5
5
|
}
|
|
6
6
|
}
|