Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions newspaper/extractors.py
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
TITLE_REPLACEMENTS = ReplaceSequence().create(u"»").append(u"»")
PIPE_SPLITTER = StringSplitter("\\|")
DASH_SPLITTER = StringSplitter(" - ")
UNDERSCORE_SPLITTER = StringSplitter("_")
ARROWS_SPLITTER = StringSplitter("»")
COLON_SPLITTER = StringSplitter(":")
SPACE_SPLITTER = StringSplitter(' ')
Expand Down Expand Up @@ -182,6 +183,11 @@ def get_title(self, doc):
title_text = self.split_title(title_text, DASH_SPLITTER)
used_delimeter = True

# split title with _
if not used_delimeter and '_' in title_text:
title_text = self.split_title(title_text, UNDERSCORE_SPLITTER)
used_delimeter = True

# split title with »
if not used_delimeter and u'»' in title_text:
title_text = self.split_title(title_text, ARROWS_SPLITTER)
Expand Down