Trying Same URL Regex as 2.3

rottingresearch · Dec 11, 2021 · 02a7fed · 02a7fed
1 parent b4a987c
commit 02a7fed
Show file tree

Hide file tree

Showing 2 changed files with 29 additions and 56 deletions.
diff --git a/linkrot/extractor.py b/linkrot/extractor.py
@@ -19,61 +19,34 @@
 # DOI
 DOI_REGEX = r"""DOI:\s?([^\s,]+)"""
 
-# URL REGEX
-URL_REGEX = r"""
-    (?:
-      # Scheme
-      https?://
-      # Domain
-      (?:
-        # IP address
-        (?:
-          # IP address
-          \d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}
-          |
-          # Hostname
-          (?:[a-z0-9][a-z0-9-]{0,61}[a-z0-9]\.)+[a-z]{2,6}
-        )
-        # Port
-        (?::\d{1,5})?
-        # Path
-        (?:/[a-z0-9_\-\.%&?/=+]*)?
-      )
-      # URL
-      (?:\?[a-z0-9_\-\.%&?/=+]*)?
-      # Anchor
-      (?:\#[a-z0-9_\-\.%&?/=+]*)?
-    )
-    |
-    # Email
-    (?:
-      # Name
-      [a-z0-9!#$%&'*+/=?^_`{|}~-]+(?:\.[a-z0-9!#$%&'*+/=?^_`{|}~-]+)*
-      # @
-      @
-      # Domain
-      (?:
-        # IP address
-        (?:
-          # IP address
-          \d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}
-          |
-          # Hostname
-          (?:[a-z0-9][a-z0-9-]{0,61}[a-z0-9]\.)+[a-z]{2,6}
-        )
-        # Port
-        (?::\d{1,5})?
-      )
-    )
-    |
-    # Hash
-    (?:
-      # Hash
-      \#
-      # Hash contents
-      [a-z0-9_\-\.%&?/=+]*
-    )
-"""
+# URL
+URL_REGEX = r"""(?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|\
+net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|\
+museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|\
+au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|\
+cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|\
+eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|\
+gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|\
+kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|\
+mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|\
+nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|\
+sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|\
+tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|\
+ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([\
+^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:\
+'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:com|net|org|edu|gov|\
+mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|\
+museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|\
+au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|\
+cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|\
+eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|\
+gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|\
+kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|\
+mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|\
+nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|\
+sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|\
+tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|\
+ye|yt|yu|za|zm|zw)\b/?(?!@)))"""
 
 def extract_urls(text):
     """

diff --git a/setup.py b/setup.py
@@ -31,7 +31,7 @@ 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="3.3",
+    version="3.4",
 
     # Package Descriptions
     description='Extract metadata and URLs from PDF files',