cherrypicked lexisnexis fix

amcat · Apr 9, 2014 · a5cb344 · a5cb344
1 parent 5456728
commit a5cb344
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/amcat/scripts/article_upload/lexisnexis.py b/amcat/scripts/article_upload/lexisnexis.py
@@ -42,8 +42,8 @@
 
 # Regular expressions used for parsing document
 class RES:
-    # Match at least 20 whitespace characters, followed by # of # DOCUMENTS.
-    DOCUMENT_COUNT = re.compile(" {20,}(FOCUS -)? *\d* of \d* DOCUMENT")
+    # Match at least 20 whitespace characters or at least 7 tabs, followed by # of # DOCUMENTS.
+    DOCUMENT_COUNT = re.compile("( {20,}|\t{7,})(FOCUS -)? *\d* of \d* DOCUMENTS?")
 
     # Header meta information group match
     HEADER_META = re.compile("([\w -]*):(.*)", re.UNICODE)

diff --git a/scrapers b/scrapers