## [v8.12]() (2022-03-11)

**Updated**
- changed the logger. No longer printing out to console information about the host, etc
- removed two parameters from `EventRegistry` constructor:
	- `logging` - if you wish to log requests to file, please call now `EventRegistry.setLogging(True)`
	- `printHostInfo` - if you wish to see the host info, call `logging.getLogger("eventregistry").setLevel(logging.DEBUG)`
- `checkVersion()` is no longer automatically called in `EventRegistry` constructor. If you wish to see if there is an updated version of the module, please call the method manually.

Author: gregorleban

CHANGELOG.md

@@ -1,5 +1,15 @@
 # Change Log
 
+## [v8.12]() (2022-03-11)
+
+**Updated**
+- changed the logger. No longer printing out to console information about the host, etc
+- removed two parameters from `EventRegistry` constructor:
+	- `logging` - if you wish to log requests to file, please call now `EventRegistry.setLogging(True)`
+	- `printHostInfo` - if you wish to see the host info, call `logging.getLogger("eventregistry").setLevel(logging.DEBUG)`
+- `checkVersion()` is no longer automatically called in `EventRegistry` constructor. If you wish to see if there is an updated version of the module, please call the method manually.
+
+
 ## [v8.11]() (2022-01-05)
 
 **Updated**
@@ -271,7 +281,7 @@
 - Changed constructor parameters in `GetRecentEvents` and `GetRecentArticles`.
 
 **Removed**
-- removed `EventRegistry.login()` method to login the user. The user should authenticate using the API key that he can obtain on [his settings page](http://eventregistry.org/me?tab=settings).
+- removed `EventRegistry.login()` method to login the user. The user should authenticate using the API key that he can obtain on [his settings page](https://newsapi.ai/dashboard).
 
 
 

eventregistry/Base.py

@@ -3,7 +3,7 @@
 """
 
 import six, warnings, os, sys, re, datetime, time
-
+from eventregistry.Logger import logger
 
 mainLangs = ["eng", "deu", "zho", "slv", "spa"]
 allLangs = [ "eng", "deu", "spa", "cat", "por", "ita", "fra", "rus", "ara", "tur", "zho", "slv", "hrv", "srp" ]
@@ -226,7 +226,7 @@ def _setQueryArrVal(self, value, propName, propOperName, defaultOperName):
             if propOperName != None:
                 self.queryParams[propOperName] = defaultOperName
                 if len(value) > 1:
-                    print("Warning: The value of parameter '%s' was provided as a list and '%s' operator was used implicitly between the items. We suggest specifying the list using the QueryItems.AND() or QueryItems.OR() to ensure the appropriate operator is used." % (propName, defaultOperName))
+                    logger.warning("Warning: The value of parameter '%s' was provided as a list and '%s' operator was used implicitly between the items. We suggest specifying the list using the QueryItems.AND() or QueryItems.OR() to ensure the appropriate operator is used." % (propName, defaultOperName))
 
         # there should be no other valid types
         else:

eventregistry/EventRegistry.py

@@ -1,11 +1,11 @@
 """
 main class responsible for obtaining results from the Event Registry
 """
-import six, os, sys, traceback, json, re, requests, time
-import threading
+import six, os, sys, traceback, json, re, requests, time, logging, threading
 
 from eventregistry.Base import *
 from eventregistry.ReturnInfo import *
+from eventregistry.Logger import logger
 
 
 class EventRegistry(object):
@@ -17,34 +17,30 @@ def __init__(self,
                  apiKey = None,
                  host = None,
                  hostAnalytics = None,
-                 logging = False,
                  minDelayBetweenRequests = 0.5,
                  repeatFailedRequestCount = -1,
                  allowUseOfArchive = True,
                  verboseOutput = False,
-                 printHostInfo = True,
                  settingsFName = None):
         """
         @param apiKey: API key that should be used to make the requests to the Event Registry. API key is assigned to each user account and can be obtained on
-            this page: http://eventregistry.org/me?tab=settings
+            this page: https://newsapi.ai/dashboard
         @param host: host to use to access the Event Registry backend. Use None to use the default host.
         @param hostAnalytics: the host address to use to perform the analytics api calls
-        @param logging: log all requests made to a 'requests_log.txt' file
         @param minDelayBetweenRequests: the minimum number of seconds between individual api calls
         @param repeatFailedRequestCount: if a request fails (for example, because ER is down), what is the max number of times the request
             should be repeated (-1 for indefinitely)
         @param allowUseOfArchive: default is True. Determines if the queries made should potentially be executed on the archive data.
             If False, all queries (regardless how the date conditions are set) will be executed on data from the last 31 days.
             Queries executed on the archive are more expensive so set it to False if you are just interested in recent data
         @param verboseOutput: if True, additional info about errors etc will be printed to console
-        @param printHostInfo: print which urls are used as the hosts
         @param settingsFName: If provided it should be a full path to 'settings.json' file where apiKey an/or host can be loaded from.
             If None, we will look for the settings file in the eventregistry module folder
         """
         self._host = host
         self._hostAnalytics = hostAnalytics
         self._lastException = None
-        self._logRequests = logging
+        self._logRequests = False
         self._minDelayBetweenRequests = minDelayBetweenRequests
         self._repeatFailedRequestCount = repeatFailedRequestCount
         self._allowUseOfArchive = allowUseOfArchive
@@ -64,17 +60,16 @@ def __init__(self,
         # and to read the host name from it (if custom host is not specified)
         currPath = os.path.split(os.path.realpath(__file__))[0]
         settFName = settingsFName or os.path.join(currPath, "settings.json")
-        if apiKey and printHostInfo:
-            print("using user provided API key for making requests")
+        if apiKey:
+            logger.debug("using user provided API key for making requests")
 
         if os.path.exists(settFName):
             settings = json.load(open(settFName))
             self._host = host or settings.get("host", "http://eventregistry.org")
             self._hostAnalytics = hostAnalytics or settings.get("hostAnalytics", "http://analytics.eventregistry.org")
             # if api key is set, then use it when making the requests
             if "apiKey" in settings and not apiKey:
-                if printHostInfo:
-                    print("found apiKey in settings file which will be used for making requests")
+                logger.debug("found apiKey in settings file which will be used for making requests")
                 self._apiKey = settings["apiKey"]
         else:
             self._host = host or "http://eventregistry.org"
@@ -84,9 +79,8 @@ def __init__(self,
             print("No API key was provided. You will be allowed to perform only a very limited number of requests per day.")
         self._requestLogFName = os.path.join(currPath, "requests_log.txt")
 
-        if printHostInfo:
-            print("Event Registry host: %s" % (self._host))
-            print("Text analytics host: %s" % (self._hostAnalytics))
+        logger.debug("Event Registry host: %s" % (self._host))
+        logger.debug("Text analytics host: %s" % (self._hostAnalytics))
 
         # list of status codes - when we get them as a response from the call, we don't want to repeat the query as the response will likely always be the same
         self._stopStatusCodes = set([
@@ -96,9 +90,6 @@ def __init__(self,
             403,        # Invalid account. The user's IP or account is disabled, potentially due to misuse.
         ])
 
-        # check what is the version of your module compared to the latest one
-        self.checkVersion()
-
 
     def checkVersion(self):
         """
@@ -113,9 +104,9 @@ def checkVersion(self):
             currentVersion = _version.__version__
             for (latest, current) in zip(latestVersion.split("."), currentVersion.split(".")):
                 if int(latest) > int(current):
-                    print("==============\nYour version of the module is outdated, please update to the latest version")
-                    print("Your version is %s while the latest is %s" % (currentVersion, latestVersion))
-                    print("Update by calling: pip install --upgrade eventregistry\n==============")
+                    logger.info("==============\nYour version of the module is outdated, please update to the latest version")
+                    logger.info("Your version is %s while the latest is %s" % (currentVersion, latestVersion))
+                    logger.info("Update by calling: pip install --upgrade eventregistry\n==============")
                     return
                 # in case the server mistakenly has a lower version that the user has, don't report an error
                 elif int(latest) < int(current):
@@ -145,19 +136,14 @@ def getLastException(self):
 
 
     def printLastException(self):
-        print(str(self._lastException))
+        logger.error(str(self._lastException))
 
 
     def format(self, obj):
         """return a string containing the object in a pretty formated version"""
         return json.dumps(obj, sort_keys=True, indent=4, separators=(',', ': '))
 
 
-    def printConsole(self, text):
-        """print time prefix + text to console"""
-        print(time.strftime("%H:%M:%S") + " " + str(text))
-
-
     def getRemainingAvailableRequests(self):
         """get the number of requests that are still available for the user today. Information is only accessible after you make some query."""
         return self._remainingAvailableRequests
@@ -297,7 +283,7 @@ def jsonRequest(self, methodUrl, paramDict, customLogFName = None, allowUseOfArc
                     raise Exception(respInfo.text)
                 # did we get a warning. if yes, print it
                 if self.getLastHeader("warning"):
-                    print("=========== WARNING ===========\n%s\n===============================" % (self.getLastHeader("warning")))
+                    logger.warning("=========== WARNING ===========\n%s\n===============================" % (self.getLastHeader("warning")))
                 # remember the available requests
                 self._dailyAvailableRequests = tryParseInt(self.getLastHeader("x-ratelimit-limit", ""), val = -1)
                 self._remainingAvailableRequests = tryParseInt(self.getLastHeader("x-ratelimit-remaining", ""), val = -1)
@@ -307,15 +293,15 @@ def jsonRequest(self, methodUrl, paramDict, customLogFName = None, allowUseOfArc
             except Exception as ex:
                 self._lastException = ex
                 if self._verboseOutput:
-                    print("Event Registry exception while executing the request:")
-                    print("endpoint: %s\nParams: %s" % (url, json.dumps(paramDict, indent=4)))
+                    logger.error("Event Registry exception while executing the request:")
+                    logger.error("endpoint: %s\nParams: %s" % (url, json.dumps(paramDict, indent=4)))
                     self.printLastException()
                 # in case of invalid input parameters, don't try to repeat the search but we simply raise the same exception again
                 if respInfo != None and respInfo.status_code in self._stopStatusCodes:
                     break
                 # in case of the other exceptions (maybe the service is temporarily unavailable) we try to repeat the query
-                print("The request will be automatically repeated in 3 seconds...")
-                time.sleep(3)   # sleep for X seconds on error
+                logger.info("The request will be automatically repeated in 3 seconds...")
+                time.sleep(5)   # sleep for X seconds on error
         self._lock.release()
         if returnData == None:
             raise self._lastException or Exception("No valid return data provided")
@@ -353,14 +339,14 @@ def jsonRequestAnalytics(self, methodUrl, paramDict):
             except Exception as ex:
                 self._lastException = ex
                 if self._verboseOutput:
-                    print("Event Registry Analytics exception while executing the request:")
-                    print("endpoint: %s\nParams: %s" % (url, json.dumps(paramDict, indent=4)))
+                    logger.error("Event Registry Analytics exception while executing the request:")
+                    logger.error("endpoint: %s\nParams: %s" % (url, json.dumps(paramDict, indent=4)))
                     self.printLastException()
                 # in case of invalid input parameters, don't try to repeat the search but we simply raise the same exception again
                 if respInfo != None and respInfo.status_code in self._stopStatusCodes:
                     break
-                print("The request will be automatically repeated in 3 seconds...")
-                time.sleep(3)   # sleep for X seconds on error
+                logger.info("The request will be automatically repeated in 3 seconds...")
+                time.sleep(5)   # sleep for X seconds on error
         self._lock.release()
         if returnData == None:
             raise self._lastException or Exception("No valid return data provided")

eventregistry/Logger.py

@@ -0,0 +1,8 @@
+import logging, os
+
+logger = logging.getLogger("eventregistry")
+if len(logger.handlers) == 0:
+    logger.addHandler(logging.StreamHandler())
+
+# by default just log from Warning level up
+logger.setLevel(level = os.environ.get("LOGLEVEL", "WARNING"))

eventregistry/QueryArticles.py

@@ -2,6 +2,7 @@
 from eventregistry.Base import *
 from eventregistry.ReturnInfo import *
 from eventregistry.Query import *
+from eventregistry.Logger import logger
 
 
 class QueryArticles(Query):
@@ -251,7 +252,7 @@ def count(self, eventRegistry):
         self.setRequestedResult(RequestArticlesInfo())
         res = eventRegistry.execQuery(self)
         if "error" in res:
-            print(res["error"])
+            logger.error(res["error"])
         count = res.get("articles", {}).get("totalResults", 0)
         return count
 
@@ -328,10 +329,10 @@ def _getNextArticleBatch(self):
             sortBy=self._sortBy, sortByAsc=self._sortByAsc,
             returnInfo = self._returnInfo))
         if self._er._verboseOutput:
-            print("Downloading article page %d..." % (self._articlePage))
+            logger.debug("Downloading article page %d..." % (self._articlePage))
         res = self._er.execQuery(self)
         if "error" in res:
-            print("Error while obtaining a list of articles: " + res["error"])
+            logger.error("Error while obtaining a list of articles: " + res["error"])
         else:
             self._totalPages = res.get("articles", {}).get("pages", 0)
         results = res.get("articles", {}).get("results", [])

eventregistry/QueryEvent.py

@@ -3,7 +3,7 @@
 from eventregistry.ReturnInfo import *
 from eventregistry.QueryArticles import QueryArticles, RequestArticlesInfo
 from eventregistry.Query import *
-
+from eventregistry.Logger import logger
 
 class QueryEvent(Query):
     """
@@ -155,7 +155,7 @@ def count(self, eventRegistry):
         self.setRequestedResult(RequestEventArticles(**self.queryParams))
         res = eventRegistry.execQuery(self)
         if "error" in res:
-            print(res["error"])
+            logger.error(res["error"])
         count = res.get(self.queryParams["eventUri"], {}).get("articles", {}).get("totalResults", 0)
         return count
 
@@ -197,7 +197,7 @@ def _getNextArticleBatch(self):
         if self._totalPages != None and self._articlePage > self._totalPages:
             return
         if self._er._verboseOutput:
-            print("Downloading article page %d from event %s" % (self._articlePage, eventUri))
+            logger.debug("Downloading article page %d from event %s" % (self._articlePage, eventUri))
 
         self.setRequestedResult(RequestEventArticles(
             page = self._articlePage,
@@ -206,7 +206,7 @@ def _getNextArticleBatch(self):
             **self.queryParams))
         res = self._er.execQuery(self)
         if "error" in res:
-            print(res["error"])
+            logger.error(res["error"])
         else:
             self._totalPages = res.get(eventUri, {}).get("articles", {}).get("pages", 0)
         arts = res.get(eventUri, {}).get("articles", {}).get("results", [])

eventregistry/QueryEvents.py

@@ -2,7 +2,7 @@
 from eventregistry.Base import *
 from eventregistry.ReturnInfo import *
 from eventregistry.Query import *
-
+from eventregistry.Logger import logger
 
 class QueryEvents(Query):
     def __init__(self,
@@ -226,7 +226,7 @@ def count(self, eventRegistry):
         self.setRequestedResult(RequestEventsInfo())
         res = eventRegistry.execQuery(self)
         if "error" in res:
-            print(res["error"])
+            logger.error(res["error"])
         count = res.get("events", {}).get("totalResults", 0)
         return count
 
@@ -289,10 +289,10 @@ def _getNextEventBatch(self):
             returnInfo = self._returnInfo))
         # download articles and make sure that we set the same archive flag as it was returned when we were processing the uriList request
         if self._er._verboseOutput:
-            print("Downloading event page %d..." % (self._eventPage))
+            logger.debug("Downloading event page %d..." % (self._eventPage))
         res = self._er.execQuery(self)
         if "error" in res:
-            print("Error while obtaining a list of events: " + res["error"])
+            logger.error("Error while obtaining a list of events: " + res["error"])
         else:
             self._totalPages = res.get("events", {}).get("pages", 0)
         results = res.get("events", {}).get("results", [])

eventregistry/QueryMentions.py

@@ -2,7 +2,7 @@
 from eventregistry.Base import *
 from eventregistry.ReturnInfo import *
 from eventregistry.Query import *
-
+from eventregistry.Logger import logger
 
 class QueryMentions(Query):
     def __init__(self,
@@ -216,7 +216,7 @@ def count(self, eventRegistry):
         self.setRequestedResult(RequestMentionsInfo())
         res = eventRegistry.execQuery(self)
         if "error" in res:
-            print(res["error"])
+            logger.error(res["error"])
         count = res.get("mentions", {}).get("totalResults", 0)
         return count
 
@@ -290,10 +290,10 @@ def _getNextMentionBatch(self):
             sortBy=self._sortBy, sortByAsc=self._sortByAsc,
             returnInfo = self._returnInfo))
         if self._er._verboseOutput:
-            print("Downloading mention page %d..." % (self._mentionPage))
+            logger.debug("Downloading mention page %d..." % (self._mentionPage))
         res = self._er.execQuery(self)
         if "error" in res:
-            print("Error while obtaining a list of mentions: " + res["error"])
+            logger.error("Error while obtaining a list of mentions: " + res["error"])
         else:
             self._totalPages = res.get("mentions", {}).get("pages", 0)
         results = res.get("mentions", {}).get("results", [])

eventregistry/_version.py

@@ -1 +1 @@
-__version__ = "8.11"
+__version__ = "8.12"

eventregistry/tests/TestERAutoSuggestions.py

@@ -26,7 +26,7 @@ def testSource(self):
         # self.assertTrue(self.er.getNewsSourceUri("topix.com") == "topix.com")
 
         self.assertTrue(self.er.suggestLocations("Washington")[0].get("wikiUri") == "http://en.wikipedia.org/wiki/Washington_(state)")
-        self.assertTrue(self.er.suggestLocations("London")[0].get("wikiUri") == "http://en.wikipedia.org/wiki/City_of_London")
+        self.assertTrue(self.er.suggestLocations("London")[0].get("wikiUri") == "http://en.wikipedia.org/wiki/London")
 
         srcList = self.er.suggestSourcesAtPlace(self.er.getConceptUri("New York City"))
         self.assertTrue(len(srcList) > 0)