diff options
| -rw-r--r-- | python/sandcrawler/html_metadata.py | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py index c64d4f3..114d9a1 100644 --- a/python/sandcrawler/html_metadata.py +++ b/python/sandcrawler/html_metadata.py @@ -653,6 +653,7 @@ FULLTEXT_URL_PATTERNS_SKIP: List[str] = [ "://onlinelibrary.wiley.com/doi/pdf/", "://doi.org/", "://dx.doi.org/", + "{'embed': '", ] FULLTEXT_URL_PREFIX_SKIP: List[str] = [ |