have SPN client differentiate between SPN and remote errors

This is only a partial implementation. The requests client will still
make way too many SPN requests trying to figure out if this is a real
error or not (eg, if remote was a 502, we'll retry many times).

We may just want to switch to SPNv2 for everything.

2 files changed, 11 insertions, 3 deletions

diff --git a/python/sandcrawler/__init__.py b/python/sandcrawler/__init__.py
index e8fbcdf..c9cc0c9 100644
--- a/python/sandcrawler/__init__.py
+++ b/python/sandcrawler/__init__.py
@@ -2,6 +2,6 @@
 from .grobid import GrobidClient, GrobidWorker, GrobidBlobWorker
 from .misc import gen_file_metadata, b32_hex, parse_cdx_line, parse_cdx_datetime
 from .workers import KafkaSink, KafkaGrobidSink, JsonLinePusher, CdxLinePusher, CdxLinePusher, KafkaJsonPusher, BlackholeSink, ZipfilePusher, MultiprocessWrapper
-from .ia import WaybackClient, WaybackError, CdxApiClient, CdxApiError, SavePageNowClient, SavePageNowError
+from .ia import WaybackClient, WaybackError, CdxApiClient, CdxApiError, SavePageNowClient, SavePageNowError, SavePageNowRemoteError
 from .ingest import IngestFileWorker
 
diff --git a/python/sandcrawler/ia.py b/python/sandcrawler/ia.py
index 455c9f6..489736e 100644
--- a/python/sandcrawler/ia.py
+++ b/python/sandcrawler/ia.py
@@ -126,6 +126,9 @@ class WaybackClient:
 class SavePageNowError(Exception):
     pass
 
+class SavePageNowRemoteError(Exception):
+    pass
+
 class SavePageNowClient:
 
     def __init__(self, cdx_client=None,
@@ -156,13 +159,18 @@ class SavePageNowClient:
         error on non-success.
         """
         resp = self.http_session.get(self.v1endpoint + url)
-        if resp.status_code != 200:
+        if resp.status_code != 200 and not resp.headers.get('X-Archive-Orig-Location'):
+            # looks like an error which was *not* a remote server error. Some
+            # problem with wayback, might need to short-circuit
             raise SavePageNowError("HTTP status: {}, url: {}".format(resp.status_code, url))
+        if resp.headers.get('X-Archive-Wayback-Runtime-Error'):
+            # looks like a weird remote error; would not expect a CDX reply so bailing here
+            raise SavePageNowRemoteError(resp.headers['X-Archive-Wayback-Runtime-Error'])
         terminal_url = '/'.join(resp.url.split('/')[5:])
         body = resp.content
         cdx = self.cdx_client.lookup_latest(terminal_url)
         if not cdx:
-            raise SavePageNowError("SPN was successful, but CDX lookup then failed")
+            raise SavePageNowError("SPN was successful, but CDX lookup then failed. URL: {}".format(terminal_url))
         return (cdx, body)
 
     def save_url_now_v2(self, url):