add new spider regex definitions and associated tests

regexes.yaml

@@ -1235,6 +1235,6 @@ device_parsers:
   ##########
   # Spiders (this is hack...)
   ##########
-  - regex: '(bingbot|bot|borg|google(^tv)|yahoo|slurp|msnbot|msrbot|openbot|archiver|netresearch|lycos|scooter|altavista|teoma|gigabot|baiduspider|blitzbot|oegp|charlotte|furlbot|http%20client|polybot|htdig|ichiro|mogimogi|larbin|pompos|scrubby|searchsight|seekbot|semanticdiscovery|silk|snappy|speedy|spider|voila|vortex|voyager|zao|zeal|fast\-webcrawler|converacrawler|dataparksearch|findlinks|crawler|Netvibes|Sogou Pic Spider|ICC\-Crawler|Innovazion Crawler)'
+  - regex: '(bingbot|bot|borg|google(^tv)|yahoo|slurp|msnbot|msrbot|openbot|archiver|netresearch|lycos|scooter|altavista|teoma|gigabot|baiduspider|blitzbot|oegp|charlotte|furlbot|http%20client|polybot|htdig|ichiro|mogimogi|larbin|pompos|scrubby|searchsight|seekbot|semanticdiscovery|silk|snappy|speedy|spider|voila|vortex|voyager|zao|zeal|fast\-webcrawler|converacrawler|dataparksearch|findlinks|crawler|Netvibes|Sogou Pic Spider|ICC\-Crawler|Innovazion Crawler|Daumoa|EtaoSpider|A6\-Indexer|YisouSpider)'
     device_replacement: 'Spider'
 

test_resources/test_device.yaml

@@ -353,3 +353,15 @@ test_cases:
 
   - user_agent_string: 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534+ (KHTML, like Gecko) MsnBot-Media /1.0b'
     family: 'Spider'
+
+  - user_agent_string: 'Mozilla/5.0 (compatible; MSIE or Firefox mutant; not on Windows server; + http://tab.search.daum.net/aboutWebSearch.html) Daumoa/3.0'
+    family: 'Spider'
+
+  - user_agent_string: 'Mozilla/5.0 (compatible; EtaoSpider/1.0; http://open.etao.com/dev/EtaoSpider)'
+    family: 'Spider'
+
+  - user_agent_string: 'A6-Indexer/1.0 (http://www.a6corp.com/a6-web-scraping-policy/)'
+    family: 'Spider'
+
+  - user_agent_string: 'YisouSpider'
+    family: 'Spider'