[FIX] dates for Europresse parser: ok.

parsing/FileParsers/EuropressFileParser.py

@@ -29,9 +29,9 @@ class EuropressFileParser(FileParser):
         format_date = re.compile('.*\d{4}.*', re.UNICODE)
 
         if isinstance(file, str):
-            file_open = open(file, 'rb')
+            file = open(file, 'rb')
         
-        contents = file_open.read()
+        contents = file.read()
         encoding = self.detect_encoding(contents)
         
         if encoding != "utf-8":
@@ -91,19 +91,27 @@ class EuropressFileParser(FileParser):
                     header = header.split(', ')
                     if format_date.match(header[0]):
                         date       = header[0]
-                    else:
+                    elif format_date.match(header[1]):
                         hyperdata['rubrique']   = header[0]
                         date       = header[1]
-
-                    try:
-                        hyperdata['page']       = header[2].split(' ')[1]
-                    except:
-                        pass
+                        try:
+                            hyperdata['page']       = header[2].split(' ')[1]
+                        except:
+                            pass
+                    else:
+                        date       = header[2]
+                
                 try:
-                    hyperdata['publication_date'] = dateparser.parse(date, languages=['fr', 'en'])
+                    hyperdata['publication_date'] = dateparser.parse(date.strip(), languages=['fr', 'en'])
+                    
                 except:
-                    hyperdata['publication_date'] = timezone.now()
+                    hyperdata['publication_date'] = timezone.now().strftime("%Y-%m-%d %H:%M:%S")
                 
+                hyperdata['publication_year']  = hyperdata['publication_date'].strftime('%Y')
+                hyperdata['publication_month'] = hyperdata['publication_date'].strftime('%m')
+                hyperdata['publication_day']  = hyperdata['publication_date'].strftime('%d')
+
+                #print(hyperdata['publication_date'])
                 try:
                     title   = paragraph_list(html_article.xpath(title_xpath))
                     hyperdata['title'] = title[0]
@@ -118,8 +126,6 @@ class EuropressFileParser(FileParser):
 
                 yield hyperdata
 
-            file_open.close()
-
         except :
             PrintException()
             pass
@@ -133,4 +139,3 @@ if __name__ == "__main__":
         except:
             pass
 
-

parsing/FileParsers/FileParser.py

@@ -126,7 +126,7 @@ class FileParser:
         # initialize the list of hyperdata
         hyperdata_list = []
         if zipfile.is_zipfile(file):
-            print(file, "# is the file is a ZIP archive, recurse on each of its files...")
+            #print(file, "# is the file is a ZIP archive, recurse on each of its files...")
             zipArchive = zipfile.ZipFile(file)
             for filename in zipArchive.namelist():
                 try:
@@ -137,7 +137,7 @@ class FileParser:
                     print(error)
         # ...otherwise, let's parse it directly!
         else:
-            print(file, "it is not a zip file")
+            #print(file, "it is not a zip file")
             try:
                 for hyperdata in self._parse(file):
                     hyperdata_list.append(self.format_hyperdata(hyperdata))