[IDK] trying to push

parsing/FileParsers/EuropressFileParser.py

@@ -3,6 +3,7 @@ import locale
 from lxml import etree
 from datetime import datetime, date
 from django.utils import timezone
+import dateutil.parser
 
 from .FileParser import FileParser
 from ..NgramsExtractors import *
@@ -23,9 +24,15 @@ class EuropressFileParser(FileParser):
         #print(len(contents))
         #return []
         encoding = self.detect_encoding(contents)
-        print(encoding)
+        #print(encoding)
         if encoding != "utf-8":
+            try:
+                contents = contents.decode("latin1", errors='replace').encode(codif)
+            except :
+                try:
                     contents = contents.decode(encoding, errors='replace').encode(codif)
+                except Exception as error:
+                    print(error)
 
         try:
             html_parser = etree.HTMLParser(encoding=codif)
@@ -37,7 +44,7 @@ class EuropressFileParser(FileParser):
         # initialize the list of metadata
         metadata_list = []
         # parse all the articles, one by one
-
+        try:
             for html_article in html_articles:
                 
                 metadata = {}
@@ -54,7 +61,12 @@ class EuropressFileParser(FileParser):
                                 metadata['source'] = name.text.encode(codif)
 
                     for header in html_article.xpath("./tr/td/span[@class = 'DocHeader']"):
+                        try:
                             text = header.text
+                        except Exception as error:
+                            print(error)
+
+                        
                         if isinstance(text, bytes):
                             text = text.decode(encoding)
 
@@ -78,12 +90,17 @@ class EuropressFileParser(FileParser):
                                 text = text.replace('ű', 'û')
                                 text = text.replace(' aot ', ' août ')
 
+
                             try :
                                 metadata['publication_date'] = datetime.strptime(text, '%d %B %Y')
                             except :
                                 try:
                                     metadata['publication_date'] = datetime.strptime(text, '%B %Y')
                                 except :
+                                    try:
+                                        metadata['publication_date'] = dateutil.parser.parse(text)
+                                    except Exception as error:
+                                        print(error)
                                         print(text)
                                         pass
                         
@@ -167,6 +184,10 @@ class EuropressFileParser(FileParser):
                     metadata_list.append(metadata)
                     count += 1
         
+        except Exception as error:
+            print(error)
+            pass
+
 #       from pprint import pprint
 #       pprint(metadata_list)
 #       return []

parsing/FileParsers/RisFileParser.py

@@ -36,6 +36,10 @@ class RisFileParser(FileParser):
                             #print(metadata)
                             try:
                                 #print("append")
+                                if 'language_fullname' not in metadata.keys():
+                                    if 'language_iso3' not in metadata.keys():
+                                        if 'language_iso2' not in metadata.keys():
+                                            metadata['language_iso2'] = 'en'
                                 metadata_list.append(metadata)
                                 metadata = {}
                                 #print("append succeeded")

templates/menu.html

@@ -23,12 +23,12 @@
         <div class="navbar-collapse collapse">
           <ul class="nav navbar-nav">
 							<!-- <li><a href="/admin/">Admin/</a></li> --!>
-            <li><a href="/projects/">Projects/</a></li>
+            <li><a href="/projects/">Projects</a></li>
 						{% if project %}
-						<li><a href="/project/{{project.id}}">{{project.name}}/</a></li>
+						<li><a href="/project/{{project.id}}">{{project.name}}</a></li>
 						{% endif %}
 						{% if corpus %}
-						<li><a href="/project/{{project.id}}/corpus/{{corpus.id}}">{{corpus.name}}/</a></li>
+						<li><a href="/project/{{project.id}}/corpus/{{corpus.id}}">{{corpus.name}}</a></li>
 						{% endif %}
 
 
@@ -61,7 +61,7 @@
 <hr>
 
 <footer>
-        <p>Gargantext v.1.0 (Copyrights {{ date.year }})</p>
+        <p>Gargantext v.1.0 (Copyrights CNRS {{ date.year }})</p>
 </footer>
 
 

templates/project.html

@@ -56,6 +56,7 @@
 							{{ formResource.as_p}}
 							<input type="submit" class="btn" value="Add this corpus" />
 					</form>
+
     </center>
 				</p>