importer code updates

4 files changed, 18 insertions, 3 deletions

diff --git a/python/fatcat_tools/importers/cdl_dash_dat.py b/python/fatcat_tools/importers/cdl_dash_dat.py
index e1252b6d..c1ea075d 100755
--- a/python/fatcat_tools/importers/cdl_dash_dat.py
+++ b/python/fatcat_tools/importers/cdl_dash_dat.py
@@ -70,7 +70,6 @@ def cdl_dash_release(meta, extra=None):
         if extid['value'].startswith('ark:'):
             ark_id = extid['value']
     assert ark_id
-    extra['ark_id'] = ark_id
 
     license_slug = lookup_license_slug(meta['rights']['uri'])
 
@@ -98,6 +97,7 @@ def cdl_dash_release(meta, extra=None):
     r = ReleaseEntity(
         ext_ids=ReleaseEntityExtIds(
             doi=doi,
+            ark=ark_id,
         ),
         title=clean(meta['title'], force_xml=True),
         publisher=clean(meta['publisher']),
diff --git a/python/fatcat_tools/importers/crossref.py b/python/fatcat_tools/importers/crossref.py
index 999ce13f..c875010c 100644
--- a/python/fatcat_tools/importers/crossref.py
+++ b/python/fatcat_tools/importers/crossref.py
@@ -218,6 +218,8 @@ class CrossrefImporter(EntityImporter):
                     creator_id=creator_id,
                     index=index,
                     raw_name=raw_name,
+                    given_name=clean(am.get('given')),
+                    surname=clean(am.get('family')),
                     raw_affiliation=clean(raw_affiliation),
                     role=ctype,
                     extra=extra))
@@ -318,13 +320,15 @@ class CrossrefImporter(EntityImporter):
         if not container_id:
             if obj.get('container-title'):
                 extra['container_name'] = clean(obj['container-title'][0])
-        for key in ('group-title', 'subtitle'):
+        for key in ('group-title'):
             val = obj.get(key)
             if val:
                 if type(val) == list:
                     val = val[0]
                 if type(val) == str:
-                    extra[key] = clean(val)
+                    val = clean(val)
+                    if val:
+                        extra[key] = clean(val)
                 else:
                     extra[key] = val
         # crossref-nested extra keys
@@ -397,6 +401,13 @@ class CrossrefImporter(EntityImporter):
                 # title can't be just a single character
                 return None
 
+        subtitle = None
+        if obj.get('subtitle'):
+            subtitle = clean(obj.get('subtitle')[0], force_xml=True)
+            if not subtitle or len(subtitle) <= 1:
+                # subtitle can't be just a single character
+                return None
+
         if extra_crossref:
             extra['crossref'] = extra_crossref
         if not extra:
@@ -406,6 +417,7 @@ class CrossrefImporter(EntityImporter):
             work_id=None,
             container_id=container_id,
             title=title,
+            subtitle=subtitle,
             original_title=original_title,
             release_type=release_type,
             release_stage=release_stage,
diff --git a/python/fatcat_tools/importers/grobid_metadata.py b/python/fatcat_tools/importers/grobid_metadata.py
index ba91d183..9e99bc0a 100644
--- a/python/fatcat_tools/importers/grobid_metadata.py
+++ b/python/fatcat_tools/importers/grobid_metadata.py
@@ -94,6 +94,8 @@ class GrobidMetadataImporter(EntityImporter):
             contribs.append(fatcat_client.ReleaseContrib(
                 index=i,
                 raw_name=clean(a['name']),
+                given_name=clean(a.get('given_name')),
+                surname=clean(a.get('surname')),
                 role="author",
                 extra=None))
 
diff --git a/python/fatcat_tools/importers/wayback_static.py b/python/fatcat_tools/importers/wayback_static.py
index 114920f7..c4f4f21e 100755
--- a/python/fatcat_tools/importers/wayback_static.py
+++ b/python/fatcat_tools/importers/wayback_static.py
@@ -120,6 +120,7 @@ def lookup_cdx(embed_url, verify_hashes=True, cdx_output=None):
             resp.raise_for_status()
             assert webcapture_cdx.sha1 == hashlib.sha1(resp.content).digest().hex()
             webcapture_cdx.sha256 = hashlib.sha256(resp.content).digest().hex()
+            webcapture_cdx.size_bytes = len(resp.content)
         return webcapture_cdx
     else:
         return None