add container url to docs, docinfo rel to absolute

Adding container URL to each document
Change relative url to absolute URL in get_document_details
Clean up a bit

automation/mdms.py

@@ -119,6 +119,7 @@ class MDMSParser:
         # get document ID on MDMS
         parsed_href = urlparse(cols[0].a['href'])
         mdms_id = int(parse_qs(parsed_href.query)['id'][0])
+        container_url = urljoin(DOCUMENT_URL, '?id={}'.format(mdms_id))
 
         # get timestamp of the last uploaded version
         last_version_uploaded = self.try_parsing_date(cols[2].text)
@@ -175,7 +176,8 @@ class MDMSParser:
           'sub_group_text': cols[3].text,
           'title': cols[4].text.strip(),
           'authors': authors,
-          'latest_version_url': latest_url
+          'latest_version_url': latest_url,
+          'container': container_url
         })
       except: # TODO: catch properly
         print('Error: Could not parse input documents data. Did MDMS layout change?')
@@ -261,7 +263,7 @@ class MDMSParser:
             entry = entry.string.strip()
             if len(entry) == 0:
               details['documents'].append({
-                'rel_path': rel_path,
+                'path': rel_path,
                 'version': version,
                 'timestamp': timestamp
               })
@@ -393,51 +395,33 @@ def get_input_documents(meeting_id, standard=Standard.ALL, subgroup=Subgroup.ALL
 
   [{'mdms_id', 'document', 'created', 'last_version_uploaded', 'sub_group_text', 'title', 'authors', 'latest_version_url'}, ...]
   '''
-  debug = False # remove this after dubugging
-
-  if not debug:
-    query = _get_query_string(meeting_id, SearchCategory.INPUT, standard, subgroup)
-    url = urljoin(CURRENT_MEETING_URL, query)
-    response = requests.get(url, auth=(MPEG_LOGIN, MPEG_PWD))
-    if not response.status_code == 200:
-      print('HTTP response {} != 200'.format(response.status_code))
-      print('\t{}'.format(response.text.replace('\n', '\n\t')))
-      return []
-    with open('input.html', 'w') as text_file:
-      text_file.write(response.text)
-      parser = MDMSParser()
-      return parser.parse_input_docs(response.text)
-  else:
-    with open('input.html', 'r') as text_file:
-      data = text_file.read()
-      parser = MDMSParser()
-      return parser.parse_input_docs(data)
+  query = _get_query_string(meeting_id, SearchCategory.INPUT, standard, subgroup)
+  url = urljoin(CURRENT_MEETING_URL, query)
+  response = requests.get(url, auth=(MPEG_LOGIN, MPEG_PWD))
+  if not response.status_code == 200:
+    print('HTTP response {} != 200'.format(response.status_code))
+    print('\t{}'.format(response.text.replace('\n', '\n\t')))
+    return []
+  parser = MDMSParser()
+  return parser.parse_input_docs(response.text)
   
 def get_document_details(document_id):
   '''
   Get more details about a docuemt.
-  {'submitted_by': {'name', 'email'}, 'title', 'authors_string', 'organizations', 'abstract', 'related_docs', 'ahg', 'sub_group', 'group', 'standard', 'activity', 'documents': [{'rel_path', 'version', 'timestamp'}, ... ]}
+  {'submitted_by': {'name', 'email'}, 'title', 'authors_string', 'organizations', 'abstract', 'related_docs', 'ahg', 'sub_group', 'group', 'standard', 'activity', 'documents': [{'path', 'version', 'timestamp'}, ... ]}
   '''
-  debug = False # remove this after dubugging
-
-  if not debug:
-    query = '?id={}'.format(document_id)
-    url = urljoin(DOCUMENT_URL, query)
-    response = requests.post(url, auth=(MPEG_LOGIN, MPEG_PWD))
-    if not response.status_code == 200:
-        print('HTTP response {} != 200'.format(response.status_code))
-        print('\t{}'.format(response.text.replace('\n', '\n\t')))
-        return []
-    parser = MDMSParser()
-    with open('input.html', 'w') as text_file:
-      text_file.write(response.text)
-      parser = MDMSParser()
-    return parser.parse_document_details(response.text)
-  else:
-    with open('input.html', 'r') as text_file:
-      data = text_file.read()
-      parser = MDMSParser()
-      return parser.parse_document_details(data)
+  query = '?id={}'.format(document_id)
+  url = urljoin(DOCUMENT_URL, query)
+  response = requests.post(url, auth=(MPEG_LOGIN, MPEG_PWD))
+  if not response.status_code == 200:
+      print('HTTP response {} != 200'.format(response.status_code))
+      print('\t{}'.format(response.text.replace('\n', '\n\t')))
+      return []
+  parser = MDMSParser()
+  details = parser.parse_document_details(response.text)
+  for n in range(len(details['documents'])):
+    details['documents'][n]['path'] = urljoin(DOCUMENT_URL, details['documents'][n]['path']) # relative to absolute
+  return details
 
 def find_documents( title = '', 
                     number = '', 

example1.py

@@ -7,5 +7,8 @@ last_meeting = mdms.get_current_meeting()
 print('\nLast MPEG#{} ({}) from {} to {}'.format(last_meeting['number'], last_meeting['name'], last_meeting['start_date'], last_meeting['end_date']))
 
 input_docs = mdms.get_input_documents(last_meeting['id'])
-print('\nNumber of input contributions: ', len(input_docs))
-print("First entry: ", input_docs[0])
\ No newline at end of file
+print('\nNumber of input contributions:', len(input_docs))
+print('First entry:', input_docs[0])
+
+doc_details = mdms.get_document_details(input_docs[0]['mdms_id'])
+print('\nDetails of the first document:', doc_details)