| 1 | # test to retrieve subtitles
|
|---|
| 2 |
|
|---|
| 3 | from habanero import Crossref
|
|---|
| 4 | from diophila import OpenAlex
|
|---|
| 5 | import sys, argparse, json
|
|---|
| 6 |
|
|---|
| 7 | cr = Crossref(mailto="[email protected]")
|
|---|
| 8 | oa = OpenAlex("[email protected]")
|
|---|
| 9 | dateRegex = "[0-9]{4}-{1}[0-9]+-{1}[0-9]+"
|
|---|
| 10 |
|
|---|
| 11 | doiToCheck = []
|
|---|
| 12 |
|
|---|
| 13 | def retrieveDOIsWithSubtitles(num):
|
|---|
| 14 | currentDate = "2015-01-01"
|
|---|
| 15 | numCounted = 0
|
|---|
| 16 | while numCounted < num:
|
|---|
| 17 | datasegment = []
|
|---|
| 18 | query = cr.works(filter = {'type' : ['journal-article', 'proceedings-article', 'book-chapter']}, progress_bar=True, sample=100)
|
|---|
| 19 |
|
|---|
| 20 | items = query["message"]["items"]
|
|---|
| 21 | for item in items:
|
|---|
| 22 | #print(item["title"][0])
|
|---|
| 23 | if "subtitle" in item.keys():
|
|---|
| 24 | print("Title: " + item["title"][0] + " | Subtitle: " + item["subtitle"][0] + " | DOI: https://doi.org/" + item["DOI"])
|
|---|
| 25 | if item["DOI"] not in doiToCheck:
|
|---|
| 26 | numCounted = numCounted + 1
|
|---|
| 27 | datasegment.append(item["DOI"])
|
|---|
| 28 |
|
|---|
| 29 | doiToCheck.append({"dois":datasegment})
|
|---|
| 30 |
|
|---|
| 31 | def main(argv):
|
|---|
| 32 | parser = argparse.ArgumentParser()
|
|---|
| 33 | parser.add_argument("numberDOIToGet", type=int, help="the number of DOIs that is wanted")
|
|---|
| 34 | parser.add_argument("outputFilePath", help="the output file path")
|
|---|
| 35 | args = parser.parse_args()
|
|---|
| 36 |
|
|---|
| 37 | outputFile = open(args.outputFilePath, "w", encoding="utf-8")
|
|---|
| 38 | retrieveDOIsWithSubtitles(args.numberDOIToGet)
|
|---|
| 39 | json.dump({"dataArray": doiToCheck}, outputFile)
|
|---|
| 40 |
|
|---|
| 41 | if __name__ == "__main__":
|
|---|
| 42 | main(sys.argv) |
|---|
