diff options
author | Bryan Newbold <bnewbold@archive.org> | 2020-10-21 12:20:52 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2020-10-21 12:20:54 -0700 |
commit | 200bf734bd459dd3c7a147b3dfe127dbf0ed7f70 (patch) | |
tree | 4f010e66a059271ac3b9c496d15a3bc90bd763c4 /python/sandcrawler/__init__.py | |
parent | 33249f2679851afb64142c428be45d16f35f5539 (diff) | |
download | sandcrawler-200bf734bd459dd3c7a147b3dfe127dbf0ed7f70.tar.gz sandcrawler-200bf734bd459dd3c7a147b3dfe127dbf0ed7f70.zip |
differential wayback-error from wayback-content-error
The motivation here is to distinguish errors due to current content in
wayback (eg, in WARCs) from operational errors (eg, wayback machine is
down, or network failures/disruption).
Diffstat (limited to 'python/sandcrawler/__init__.py')
-rw-r--r-- | python/sandcrawler/__init__.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/sandcrawler/__init__.py b/python/sandcrawler/__init__.py index 71c2023..e461462 100644 --- a/python/sandcrawler/__init__.py +++ b/python/sandcrawler/__init__.py @@ -3,7 +3,7 @@ from .grobid import GrobidClient, GrobidWorker, GrobidBlobWorker from .pdftrio import PdfTrioClient, PdfTrioWorker, PdfTrioBlobWorker from .misc import gen_file_metadata, b32_hex, parse_cdx_line, parse_cdx_datetime, clean_url from .workers import KafkaSink, KafkaCompressSink, JsonLinePusher, CdxLinePusher, CdxLinePusher, KafkaJsonPusher, BlackholeSink, ZipfilePusher, MultiprocessWrapper -from .ia import WaybackClient, WaybackError, CdxApiClient, CdxApiError, SavePageNowClient, SavePageNowError, PetaboxError, ResourceResult, WarcResource, CdxPartial, CdxRow +from .ia import WaybackClient, WaybackError, WaybackContentError, CdxApiClient, CdxApiError, SavePageNowClient, SavePageNowError, PetaboxError, ResourceResult, WarcResource, CdxPartial, CdxRow from .ingest import IngestFileWorker from .persist import PersistCdxWorker, PersistIngestFileResultWorker, PersistGrobidWorker, PersistGrobidDiskWorker, PersistPdfTrioWorker, PersistIngestRequestWorker, PersistPdfTextWorker, PersistThumbnailWorker from .db import SandcrawlerPostgrestClient, SandcrawlerPostgresClient |