diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-08-11 17:16:39 -0700 | 
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-08-11 17:16:39 -0700 | 
| commit | d5f0602e80847adf3d359a7fd06cc131c07cb6dd (patch) | |
| tree | fa89dadd5f19d7a1c26069254748f5142f5fce06 /python | |
| parent | 5c7f9bc60b372006adac8e47ee2f4f1f73b84897 (diff) | |
| download | sandcrawler-d5f0602e80847adf3d359a7fd06cc131c07cb6dd.tar.gz sandcrawler-d5f0602e80847adf3d359a7fd06cc131c07cb6dd.zip  | |
ingest: check for URL blocklist and cookie URL patterns on every hop
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/ingest.py | 13 | 
1 files changed, 13 insertions, 0 deletions
diff --git a/python/sandcrawler/ingest.py b/python/sandcrawler/ingest.py index 263b9d5..1f693dc 100644 --- a/python/sandcrawler/ingest.py +++ b/python/sandcrawler/ingest.py @@ -323,6 +323,19 @@ class IngestFileWorker(SandcrawlerWorker):          while len(hops) <= self.max_hops:              result['hops'] = hops + +            # check against blocklist again on each hop +            for block in self.base_url_blocklist: +                if block in next_url: +                    result['status'] = "skip-url-blocklist" +                    return result + +            # check for popular cookie blocking URL patterns. On successful SPN +            # crawls, shouldn't see these redirect URLs +            if '/cookieAbsent' in next_url or 'cookieSet=1' in next_url: +                result['status'] = 'blocked-cookie' +                return result +              try:                  resource = self.find_resource(next_url, best_mimetype, force_recrawl=force_recrawl)              except SavePageNowError as e:  | 
