aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--python/sandcrawler/html_metadata.py8
1 files changed, 8 insertions, 0 deletions
diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py
index f9f48a6..1c054fa 100644
--- a/python/sandcrawler/html_metadata.py
+++ b/python/sandcrawler/html_metadata.py
@@ -375,6 +375,14 @@ PDF_FULLTEXT_PATTERNS: List[dict] = [
"technique": "PDF URL link",
"example_page": "http://www.bezmialemscience.org/archives/archive-detail/article-preview/editorial/20439",
},
+ {
+ "in_doc_url": "degruyter.com/document/",
+ "in_fulltext_url": "/pdf",
+ "selector": "a.downloadPdf",
+ "attr": "href",
+ "technique": "PDF URL link",
+ "example_page": "https://www.degruyter.com/document/doi/10.1515/zaw-2021-0001/html",
+ },
]
FULLTEXT_URL_PATTERNS_SKIP = [