ingest: clean_url() in more places

Some 'cdx-error' results were due to URLs with ':' after the hostname or
trailing newline ("\n") characters in the URL. This attempts to work
around this categroy of error.

1 files changed, 4 insertions, 1 deletions

diff --git a/python/sandcrawler/ia.py b/python/sandcrawler/ia.py
index 25697be..cc176d0 100644
--- a/python/sandcrawler/ia.py
+++ b/python/sandcrawler/ia.py
@@ -18,7 +18,7 @@ from http.client import IncompleteRead
 from wayback.resourcestore import ResourceStore
 from gwb.loader import CDXLoaderFactory
 
-from .misc import b32_hex, requests_retry_session, gen_file_metadata
+from .misc import b32_hex, requests_retry_session, gen_file_metadata, clean_url
 
 class SandcrawlerBackoffError(Exception):
     """
@@ -543,6 +543,7 @@ class WaybackClient:
         if redirect_url and redirect_url.startswith("https://web.archive.org/web/"):
             redirect_url = "/".join(redirect_url.split("/")[5:])
         #print(redirect_url, file=sys.stderr)
+        redirect_url = clean_url(redirect_url)
         if redirect_url and redirect_url.startswith("http"):
             return redirect_url
         else:
@@ -666,11 +667,13 @@ class WaybackClient:
                         next_url = domain_prefix + resource.location
                     else:
                         next_url = resource.location
+                    next_url = clean_url(next_url)
                 else:
                     next_url = self.fetch_replay_redirect(
                         url=cdx_row.url,
                         datetime=cdx_row.datetime,
                     )
+                    next_url = clean_url(next_url)
                     cdx_row = cdx_partial_from_row(cdx_row)
                     if not next_url:
                         print("bad redirect record: {}".format(cdx_row), file=sys.stderr)