diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-07-31 15:51:45 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-08-03 10:50:14 -0700 |
| commit | 482f185496b7baa9e421829c6ebe8da31d7850d8 (patch) | |
| tree | dc63dbca7a5cb83d8a1b39f4bc370f178fa688fc | |
| parent | ee65634b8f7d8cc482b8bbe521f7ad9e62e4211c (diff) | |
| download | chocula-482f185496b7baa9e421829c6ebe8da31d7850d8.tar.gz chocula-482f185496b7baa9e421829c6ebe8da31d7850d8.zip | |
fatcat export improvements
| -rw-r--r-- | chocula/database.py | 37 |
1 files changed, 28 insertions, 9 deletions
diff --git a/chocula/database.py b/chocula/database.py index fa8d105..e266b1c 100644 --- a/chocula/database.py +++ b/chocula/database.py @@ -684,7 +684,10 @@ class ChoculaDatabase: ) extra = dict( - issnp=row["issnp"], issne=row["issne"], country=row["country"], + issnp=row["issnp"], + issne=row["issne"], + country=row["country"], + publisher_type=row["publisher_type"], ) if row["lang"]: extra["languages"] = [ @@ -786,24 +789,40 @@ class ChoculaDatabase: "SELECT * FROM directory WHERE issnl = ?;", [row["issnl"]] ) for drow in cur: + dextra = dict() + if drow["extra"]: + dextra = json.loads(drow["extra"]) if drow["slug"] == "ezb": - ezb = json.loads(drow["extra"]) extra["ezb"] = dict( - ezb_id=drow["identifier"], color=ezb["ezb_color"] + ezb_id=drow["identifier"], color=dextra["ezb_color"] ) elif drow["slug"] == "szczepanski": - extra["szczepanski"] = drow["extra"] + extra["szczepanski"] = dict(as_of=dextra["as_of"]) + elif drow["slug"] == "norwegian": + extra["norwegian"] = dict(as_of=dextra["as_of"], level=dextra.get("level")) elif drow["slug"] == "doaj": - extra["doaj"] = json.loads(drow["extra"]) + extra["doaj"] = dict(as_of=dextra["as_of"]) + for k in ("seal", "default_license", "crawl_permission", "archive", "mimetypes"): + if dextra.get(k) is not None: + extra["doaj"][k] = dextra[k] elif drow["slug"] == "scielo": - extra["scielo"] = json.loads(drow["extra"]) + extra["scielo"] = dict() + for k in ("collection", "status"): + if dextra.get(k) is not None: + extra["scielo"][k] = dextra[k] elif drow["slug"] == "sim": extra["ia"] = extra.get("ia", {}) - extra["ia"]["sim"] = json.loads(drow["extra"]) - extra["ia"]["sim"]["sim_pubid"] = drow["identifier"] + extra["ia"]["sim"] = dict(sim_pubid=drow["identifier"]) + for k in ("year_spans", "pub_type", "peer_reviewed", "scholarly_peer_reviewed"): + if dextra.get(k) is not None: + extra["ia"]["sim"][k] = dextra[k] elif drow["slug"] in ("lockss", "clockss", "portico", "jstor"): extra["kbart"] = extra.get("kbart", {}) - extra["kbart"][drow["slug"]] = json.loads(drow["extra"]) + extra["kbart"][drow["slug"]] = dict(year_spans=dextra['year_spans']) + if dextra.get('abbrev'): + extra['abbrev'] = dextra['abbrev'] + if dextra.get('platform'): + extra['platform'] = dextra['platform'] out["extra"] = extra print(json.dumps(out)) |