added RedirectSaveError - for failed saves if the URL is a permanent … (

#93)

* added RedirectSaveError - for failed saves if the URL is a permanent redirect.

* check if url is redirect before throwing exceptions, res.url is the redirect url if redirected at all

* update tests and cli errors

tests/test_cli.py

@@ -29,7 +29,7 @@ def test_save():
         get=None,
     )
     reply = cli.args_handler(args)
-    assert "could happen because either your waybackpy" in str(reply)
+    assert "could happen because either your waybackpy" or "cannot be archived by wayback machine as it is a redirect" in str(reply)
 
 
 def test_json():

waybackpy/cli.py

@@ -29,6 +29,8 @@ def _save(obj):
                     version=__version__, header=header
                 )
             )
+        if "URL cannot be archived by wayback machine as it is a redirect" in e:
+            return ("URL cannot be archived by wayback machine as it is a redirect")
         raise WaybackError(err)
 
 

waybackpy/exceptions.py

@@ -13,6 +13,13 @@ class WaybackError(Exception):
     """
 
 
+class RedirectSaveError(WaybackError):
+    """
+    Raised when the original URL is redirected and the
+    redirect URL is archived but not the original URL.
+    """
+
+
 class URLError(Exception):
     """
     Raised when malformed URLs are passed as arguments.

waybackpy/utils.py

@@ -3,7 +3,7 @@
 import requests
 from datetime import datetime
 
-from .exceptions import WaybackError, URLError
+from .exceptions import WaybackError, URLError, RedirectSaveError
 from .__version__ import __version__
 
 from urllib3.util.retry import Retry
@@ -302,7 +302,9 @@ def _get_total_pages(url, user_agent):
     return int((_get_response(total_pages_url, headers=headers).text).strip())
 
 
-def _archive_url_parser(header, url, latest_version=__version__, instance=None):
+def _archive_url_parser(
+    header, url, latest_version=__version__, instance=None, response=None
+):
     """Returns the archive after parsing it from the response header.
 
     Parameters
@@ -388,6 +390,16 @@ def _archive_url_parser(header, url, latest_version=__version__, instance=None):
     if m:
         return m.group(1)
 
+    if response:
+        if response.url:
+            if "web.archive.org/web" in response.url:
+                m = re.search(
+                    r"web\.archive\.org/web/(?:[0-9]*?)/(?:.*)$",
+                    str(response.url).strip(),
+                )
+                if m:
+                    return m.group(0)
+
     if instance:
         newest_archive = None
         try:
@@ -414,6 +426,13 @@ def _archive_url_parser(header, url, latest_version=__version__, instance=None):
             "Wayback Machine is malfunctioning or it refused to archive your URL."
             "\nHeader:\n{header}".format(url=url, header=header)
         )
+
+        if "save redirected" == header.strip():
+            raise RedirectSaveError(
+                "URL cannot be archived by wayback machine as it is a redirect.\nHeader:\n{header}".format(
+                    header=header
+                )
+            )
     else:
         exc_message = (
             "No archive URL found in the API response. "

waybackpy/wrapper.py

@@ -225,6 +225,7 @@ def save(self):
             self.url,
             latest_version=self.latest_version,
             instance=self,
+            response=response,
         )
 
         m = re.search(