remove temporary trace logging

brozzler/frontier.py

@@ -313,9 +313,6 @@ class RethinkDbFrontier:
         representing the same url but with possibly different metadata.
         '''
         existing_page.priority += fresh_page.priority
-        self.logger.trace(
-                'adding hashtags %r to existing hashtags %r for page %s',
-                existing_page.hashtags, fresh_page.hashtags, fresh_page.url)
         existing_page.hashtags = list(set(
             (existing_page.hashtags or []) + (fresh_page.hashtags or [])))
         existing_page.hops_off = min(
@@ -371,8 +368,6 @@ class RethinkDbFrontier:
         # get existing pages from rethinkdb
         results = self.rr.table('pages').get_all(*fresh_pages.keys()).run()
         pages = {doc['id']: brozzler.Page(self.rr, doc) for doc in results}
-        self.logger.trace('fresh_pages.keys()=%r', fresh_pages.keys())
-        self.logger.trace('existing pages.keys()=%r', pages.keys())
 
         # build list of pages to save, consisting of new pages, and existing
         # pages updated with higher priority and new hashtags
@@ -422,10 +417,6 @@ class RethinkDbFrontier:
                 counts['added'], counts['updated'], counts['rejected'],
                 counts['blocked'], parent_page)
 
-        for page_id in pages:
-            page = self.rr.table('pages').get(page_id).run()
-            self.logger.trace('retrieved page after save: %r', page)
-
     def reached_limit(self, site, e):
         self.logger.info("reached_limit site=%s e=%s", site, e)
         assert isinstance(e, brozzler.ReachedLimit)

tests/test_cluster.py

@@ -510,10 +510,7 @@ def test_seed_redirect(httpd):
         {'ssurt': '%s//%s:http:/site5/redirect/' % (local_address, httpd.server_port)},
         {'ssurt': '%s//%s:http:/site5/destination/' % (local_address, httpd.server_port)}]}
 
-def test_hashtags(httpd, caplog):
-    caplog.set_level(0) # https://docs.pytest.org/en/latest/logging.html
-    logging.trace('here we are in test_hashtags')
-
+def test_hashtags(httpd):
     test_id = 'test_hashtags-%s' % datetime.datetime.utcnow().isoformat()
     rr = doublethink.Rethinker('localhost', db='brozzler')
     seed_url = make_url(httpd, '/site7/')
@@ -532,8 +529,6 @@ def test_hashtags(httpd, caplog):
         site.refresh()
     assert site.status == 'FINISHED'
 
-    print(datetime.datetime.utcnow().isoformat() + ' finished brozzling site, loading pages from rethinkdb')
-
     # check that we the page we expected
     pages = sorted(list(frontier.site_pages(site.id)), key=lambda p: p.url)
     assert len(pages) == 2

tests/test_frontier.py

@@ -732,9 +732,7 @@ def test_hashtag_seed():
     assert pages[0].url == 'http://example.org/'
     assert pages[0].hashtags == ['#hash',]
 
-def test_hashtag_links(caplog):
-    caplog.set_level(0) # https://docs.pytest.org/en/latest/logging.html
-
+def test_hashtag_links():
     rr = doublethink.Rethinker('localhost', db='test_hashtag_links')
     frontier = brozzler.RethinkDbFrontier(rr)