checking everything in

Parser/extraction-lib.py

@@ -39,12 +39,8 @@ class VersionData():
         self._completion_date = None
         self._completion_date_category = None
         self._overall_status = None
-
-        #Study Design
         self._enrollment = None
         self._enrollment_category = None
-
-        #Sponsors and Collaborators
         self._sponsor = None
         #self._sponsor_category = None #I don't believe this is included in the raw data
         self._responsible_party = None
@@ -361,17 +357,26 @@ def get_data_from_versions(nct_id,html, version_a_int, version_b_int):
 
 if __name__ == "__main__":
 
-    for file in ["NCT00658567", "NCT01303796"]:
-        with open("./{}.html".format(file)) as fh:
-            version1, version2 = get_data_from_versions(file, fh.read(), 1,2)
-        print(version1.__dict__) #order messed up somewhere:w
-        print(version2.__dict__) #order messed up somewhere:w
-
+    with psycopg2.connect(dbname="aact_db", user="root", password="root",host="localhost") as db_connection:
+        #pull the requests from the db
+        with db_connection.cursor() as curse:
+            sql = """
+            SELECT nct_id, version_a,version_b, html
+            FROM http.responses
+            """
+            responses = curse.execute(sql)
+            for response in responses.fetch_all():
+                #
+                nct_id, version_a, version_b, html = response
+
+                version1, version2 = get_data_from_versions(nct_id, html, version_a, version_b)
+
+            if version_b == version_a + 1:
+                version1.load_to_db(db_connection)
+                version2.load_to_db(db_connection)
+            else:
+                version2.load_to_db(db_connection)
 
-        with psycopg2.connect(dbname="aact_db", user="root", password="root",host="will-office") as db_connection:
-            version1.load_to_db(db_connection)
-            version2.load_to_db(db_connection)
-            #print(db_connection)
 
 """
 Documentation: