first commit

event_scrapers/Working/news/minnpost.mn.py

@@ -0,0 +1,78 @@
+import os, sys
+from datetime import datetime
+from dateutil import relativedelta
+
+import django
+sys.path.append('../../../')
+os.environ['DJANGO_SETTINGS_MODULE'] = 'ds_events.settings'
+django.setup()
+
+from time import sleep
+from pprint import pprint as ppr
+import pytz
+
+from events.models import Organization, Scraper
+from events.digitools import getBrowser, createURL, createBasicArticle, getSource
+
+
+org, created = Organization.objects.get_or_create(
+     name="MinnPost",
+     city="Minneapolis",
+     website="https://www.minnpost.com/",
+     is_venue=False,
+    )
+
+try:
+    scraper, created = Scraper.objects.get_or_create(
+        name=org.name,
+        website=org.website,
+        items = 0,
+        last_ran = datetime.now(),
+    )
+except Exception as e:
+    print(e)
+    scraper = Scraper.objects.get(name=org.name)
+    print("Scraper: ", scraper)
+
+event_type = "Ja"
+
+# Time Signatures
+tz = pytz.timezone("US/Central")
+DATETIME_FORMAT = '%b %d %Y %I:%M %p'
+DATETIME_FORMAT_2 = '%A, %B %d @ %I%p %Y'
+
+def get_events(ps, event_type):
+    contents = ps.xpath('.//*/article')
+    count = 0
+    ppr(contents)
+    for c in contents:
+        try:
+            if count > 10:
+                br.close()
+                quit()
+            article = {}
+            article['title'] = c.xpath('.//*/h2[@class="entry-title"]/a/text()')[0]
+            article['link'] = c.xpath('.//*/h2[@class="entry-title"]/a/@href')[0]
+            createBasicArticle(article, event_type, org)
+            ppr(article)
+            print("Success")
+            count+=1
+        except Exception as e:
+            print(e)
+            ppr(article)
+            print("\n\n+++\n\n")
+
+if len(sys.argv) >= 2:
+    arg1 = sys.argv[1]
+    br = getBrowser(arg1)
+else:
+    print("No run_env")
+    quit()
+
+
+ps = getSource(br, org.website)
+get_events(ps, "Ed")
+sleep(3)
+
+br.close()
+scraper.save()