1 files changed, 43 insertions, 36 deletions

diff --git a/python/scripts/covid2ingestrequest.py b/python/scripts/covid2ingestrequest.py
index 33c425d..e3bf4f0 100755
--- a/python/scripts/covid2ingestrequest.py
+++ b/python/scripts/covid2ingestrequest.py
@@ -1,12 +1,12 @@
 #!/usr/bin/env python3
-
 """
 Transform an unpaywall dump (JSON) into ingest requests.
 """
 
-import sys
-import json
 import argparse
+import json
+import sys
+
 import urlcanon
 
 
@@ -18,38 +18,44 @@ def canon(s):
 def transform_cnki(obj):
 
     requests = []
-    assert obj['cnki_id']
-
+    assert obj["cnki_id"]
 
     requests = []
-    requests.append({
-        'base_url': canon(obj['info_url']),
-        'ingest_type': 'pdf',
-        'link_source': 'cnki_covid19',
-        'link_source_id': obj['cnki_id'],
-        'ingest_request_source': 'scrape-covid19',
-    })
-    if 'read_url' in obj:
-        requests.append({
-            'base_url': canon(obj['read_url']),
-            'ingest_type': 'pdf',  # actually HTML
-            'link_source': 'cnki_covid19',
-            'link_source_id': obj['cnki_id'],
-            'ingest_request_source': 'scrape-covid19',
-        })
+    requests.append(
+        {
+            "base_url": canon(obj["info_url"]),
+            "ingest_type": "pdf",
+            "link_source": "cnki_covid19",
+            "link_source_id": obj["cnki_id"],
+            "ingest_request_source": "scrape-covid19",
+        }
+    )
+    if "read_url" in obj:
+        requests.append(
+            {
+                "base_url": canon(obj["read_url"]),
+                "ingest_type": "pdf",  # actually HTML
+                "link_source": "cnki_covid19",
+                "link_source_id": obj["cnki_id"],
+                "ingest_request_source": "scrape-covid19",
+            }
+        )
 
     return requests
 
+
 def transform_wanfang(obj):
 
-    assert obj['wanfang_id']
-    return [{
-        'base_url': canon(obj['url']),
-        'ingest_type': 'pdf',
-        'link_source': 'wanfang_covid19',
-        'link_source_id': obj['wanfang_id'],
-        'ingest_request_source': 'scrape-covid19',
-    }]
+    assert obj["wanfang_id"]
+    return [
+        {
+            "base_url": canon(obj["url"]),
+            "ingest_type": "pdf",
+            "link_source": "wanfang_covid19",
+            "link_source_id": obj["wanfang_id"],
+            "ingest_request_source": "scrape-covid19",
+        }
+    ]
 
 
 def run(args):
@@ -58,26 +64,27 @@ def run(args):
             continue
         row = json.loads(l)
 
-        if 'wanfang_id' in row:
+        if "wanfang_id" in row:
             requests = transform_wanfang(row) or []
-        elif 'cnki_id' in row:
+        elif "cnki_id" in row:
             requests = transform_cnki(row) or []
         else:
             continue
         for r in requests:
             print("{}".format(json.dumps(r, sort_keys=True)))
 
+
 def main():
-    parser = argparse.ArgumentParser(
-        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-    parser.add_argument('json_file',
-        help="COVID-19 metadata file to use",
-        type=argparse.FileType('r'))
+    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+    parser.add_argument(
+        "json_file", help="COVID-19 metadata file to use", type=argparse.FileType("r")
+    )
     subparsers = parser.add_subparsers()
 
     args = parser.parse_args()
 
     run(args)
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     main()