fetch pdftotext and pdf_meta from blobs, postgrest

This replaces the temporary COVID-19 content hack with production
content (text, thumbnail URLs) stored in postgrest and seaweedfs.

1 files changed, 9 insertions, 0 deletions

diff --git a/fatcat_scholar/sandcrawler.py b/fatcat_scholar/sandcrawler.py
index 6f0f85c..9c48cd9 100644
--- a/fatcat_scholar/sandcrawler.py
+++ b/fatcat_scholar/sandcrawler.py
@@ -16,6 +16,15 @@ class SandcrawlerPostgrestClient:
         else:
             return None
 
+    def get_pdf_meta(self, sha1: str) -> Optional[Dict[str, Any]]:
+        resp = requests.get(self.api_url + "/pdf_meta", params=dict(sha1hex="eq." + sha1))
+        resp.raise_for_status()
+        resp_json = resp.json()
+        if resp_json:
+            return resp_json[0]
+        else:
+            return None
+
 
 class SandcrawlerMinioClient(object):
     def __init__(