Fixed handling of multi-line link extraction

README.md

@@ -176,5 +176,4 @@ Feedback, ideas and pull requests are welcome!
 Possible:
 
 - Timeout (see [#43](https://github.com/metachris/pdfx/issues/43))
-- Cuts off links that span two lines [#40](https://github.com/metachris/pdfx/issues/40)
 - Include Check-Links Results in Output [#39](https://github.com/metachris/pdfx/issues/39)

pdfx/__init__.py

@@ -33,7 +33,7 @@
 from __future__ import absolute_import, division, print_function, unicode_literals
 
 __title__ = "pdfx"
-__version__ = "1.4.1"
+__version__ = "1.4.2"
 __author__ = "Chris Hager"
 __license__ = "Apache 2.0"
 __copyright__ = "Copyright 2015 Chris Hager"

pdfx/extractor.py

@@ -23,6 +23,8 @@
 
 
 def extract_urls(text):
+    # Remove line breaks in order to include links spanning over multiple lines
+    text = text.replace("\n", "")
     return set(re.findall(URL_REGEX, text, re.IGNORECASE))
 
 

setup.py

@@ -32,7 +32,7 @@ def parse_requirements(filename):
     # Versions should comply with PEP440.  For a discussion on single-sourcing
     # the version across setup.py and the project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
-    version="1.4.1",
+    version="1.4.2",
     description="Extract metadata and URLs from PDF files"
     ", and download all referenced PDFs",
     long_description=long_description,