Init

.gitattributes

@@ -0,0 +1,2 @@
+registered_books_annas_archive_es.jsonl filter=lfs diff=lfs merge=lfs -text
+unregistered_books_annas_archive_es.jsonl filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+annas_archive.jsonl
+annas_archive_es.jsonl

keys_list.csv

@@ -0,0 +1,68 @@
+key,len,freq
+aacid,243,1.0
+metadata.oclc_number,243,1.0
+metadata.type,243,1.0
+metadata.from_filenames,243,1.0
+metadata.record.oclcNumber,243,1.0
+metadata.record.title,243,1.0
+metadata.record.creator,243,1.0
+metadata.record.generalFormat,243,1.0
+metadata.record.specificFormat,243,1.0
+metadata.record.edition,243,1.0
+metadata.record.totalEditions,243,1.0
+metadata.record.publisher,243,1.0
+metadata.record.publicationPlace,226,0.93004
+metadata.record.publicationDate,243,1.0
+metadata.record.catalogingLanguage,243,1.0
+metadata.record.summary,76,0.31276
+metadata.record.physicalDescription,203,0.83539
+metadata.record.series,203,0.83539
+metadata.record.castNotes,203,0.83539
+metadata.record.languageNotes,203,0.83539
+metadata.record.subjectsText,203,0.83539
+metadata.record.cartographicData,203,0.83539
+metadata.record.dissertationInfo,196,0.80658
+metadata.record.performerNotes,203,0.83539
+metadata.record.genre,203,0.83539
+metadata.record.numericDesignation,203,0.83539
+metadata.record.audience,203,0.83539
+metadata.record.generalNotes,203,0.83539
+metadata.record.creditNotes,203,0.83539
+metadata.record.contentNotes,194,0.79835
+metadata.record.reproductionNotes,203,0.83539
+metadata.record.eventNotes,203,0.83539
+metadata.record.doi,203,0.83539
+metadata.record.peerReviewed,243,1.0
+metadata.record.mediumOfPerformance,203,0.83539
+metadata.record.issns,203,0.83539
+metadata.record.additionalPhysicalFormEntries,203,0.83539
+metadata.record.digitalAccessAndLocations,203,0.83539
+metadata.record.digitalObjectInfo,242,0.99588
+metadata.record.abstract,243,1.0
+metadata.record.evaluativeContent,203,0.83539
+metadata.record.otherFormats,243,1.0
+metadata.record.isbns,243,1.0
+metadata.record.isbn13,243,1.0
+metadata.record.openAccessLinks,217,0.893
+metadata.record.publication,243,1.0
+metadata.record.sourceIssn,203,0.83539
+metadata.record.sourceIsbns,203,0.83539
+metadata.record.contributors,243,1.0
+metadata.record.titleInfo.text,189,0.77778
+metadata.record.publisherName.text,169,0.69547
+metadata.record.machineReadableDate,42,0.17284
+metadata.record.seriesVolumes,42,0.17284
+metadata.record.subjects,40,0.16461
+metadata.record.summaries,40,0.16461
+metadata.record.openAccessLink,40,0.16461
+metadata.record.contentNotes.text,9,0.03704
+metadata.record.publisherName,20,0.0823
+metadata.record.dissertationInfo.institution,1,0.00412
+metadata.record.dissertationInfo.year,1,0.00412
+metadata.record.digitalObjectInfo.thumbnailImage,1,0.00412
+metadata.record.digitalObjectInfo.iiifImageInfoUrl,1,0.00412
+metadata.record.digitalObjectInfo.iiifItemManifestUrl,1,0.00412
+metadata.record.digitalObjectInfo.contentDMCollectionId,1,0.00412
+metadata.record.digitalObjectInfo.iiifCollectionManifestUrl,1,0.00412
+metadata.record.digitalObjectInfo.oaiSetName,1,0.00412
+metadata.record.filmInfo,1,0.00412

registered_books_annas_archive_es.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c3713837bfdec4604aad806b8ab8e56bd1bb5666867932e392c5ffddd69321
+size 1651151480

scripts/clean_spa.py

@@ -0,0 +1,94 @@
+import re
+import json
+import jsonlines
+from pathlib import Path
+
+path_index = Path("index.txt")
+curr_index = int(path_index.read_text().strip()) if path_index.exists() else 0
+index = 0
+oclc = set()
+isbn = set()
+
+
+def newitem(item1):
+    item2 = {"temas": [], "isbns": [], "descripcion": []}
+    keysmap = {
+        "title": "titulo",
+        "subjectsText": "temas",
+        "genre": "temas",
+        "subjects": "temas",
+        "series": "serie",
+        "physicalDescription": "paginas",
+        "oclcNumber": "oclc",
+        "isbns": "isbns",
+        "isbn13": "isbn13",
+        "publicationDate": "año",
+        "publisher": "editorial",
+        "summary": "descripcion",
+        "abstract": "descripcion",
+        "summaries": "descripcion",
+        "creator": "autor",
+    }
+    if "book" not in item1["generalFormat"].lower():
+        return None
+    for key1 in item1.keys():
+        if not item1[key1] or key1 not in keysmap.keys():
+            continue
+        key2 = keysmap[key1]
+        if key2 not in item2.keys():
+            item2[key2] = toint(item1[key1])
+        else:
+            if isinstance(item1[key1], list):
+                [item2[key2].append(toint(val)) for val in item1[key1]]
+            else:
+                item2[key2].append(toint(item1[key1]))
+    [item2.setdefault(v, "") for v in keysmap.values()]
+    return item2
+
+
+def additem(dump, index, prefix):
+    filename = "%s_books_annas_archive_es.jsonl" % prefix
+    if index > curr_index:
+        print(index, dump[0:99])
+        with open(filename, "a") as myfile:
+            myfile.write(dump)
+    else:
+        print("Ignoring item %s" % index)
+
+
+def toint(val):
+    return int(val) if val.isdigit() else val
+
+
+def setint(val1, rgx):
+    val2 = re.findall(rgx, str(val1))
+    return int(val2[0]) if val2 else None
+
+
+with jsonlines.open("annas_archive_es.jsonl") as reader:
+    for obj in reader:
+        try:
+            index += 1
+            item = newitem(obj["metadata"]["record"])
+            if not item:
+                continue
+            item["año"] = setint(item["año"], r"(\d+?)")
+            item["paginas"] = setint(item["paginas"], r"(\d+?)\s*pages")
+            if item["isbns"]:
+                isbns = list(map(lambda e: str(e), item["isbns"]))
+                extra = "ISBN Relacionados: %s" % ", ".join(isbns)
+                item["descripcion"].append(extra)
+            item["descripcion"] = "\n\n".join(item["descripcion"])
+            if item["oclc"] not in oclc:
+                oclc.add(item["oclc"])
+                dump = json.dumps(item, ensure_ascii=False).encode("utf8")
+                dump = dump.decode() + "\n"
+                if not item["isbn13"]:
+                    additem(dump, index, "unregistered")
+                elif item["isbn13"] not in isbn:
+                    isbn.add(item["isbn13"])
+                    additem(dump, index, "registered")
+        except Exception as err:
+            strs = (type(err).__name__, err.__traceback__.tb_lineno, str(err))
+            print("%s at line %s: %s" % strs)
+            pass

scripts/select_spa.sh

@@ -0,0 +1 @@
+jq -c 'select(.metadata.record.catalogingLanguage=="spa")' annas_archive.jsonl | tee -a annas_archive_es.jsonl

unregistered_books_annas_archive_es.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2de2d0227404c8c0b5cc88bd7280632d98dbfa28b127feaef02d73e31f1d2f
+size 4548521533