add datacite clients

0371df2a · Maxence Larrieu · ca197325 · 0371df2a · 0371df2a · 0371df2a
Commit 0371df2a authored 1 year ago by Maxence Larrieu
--- a/.gitignore
+++ b/.gitignore
@@ -2,4 +2,7 @@
 /0-collect-data/bso/
 /1-enrich-with-datacite/__pycache__/
 /2-produce-graph/__pycache__/
-/hide
\ No newline at end of file
+/hide
+0-collect-data/.ipynb_checkpoints/z-datacite-demo-checkpoint.ipynb
+0-collect-data/.ipynb_checkpoints/z-resultats-demo-datacite-checkpoint.csv
+0-collect-data/z-resultats-demo-datacite.csv
--- a/0-collect-data/datacite-dois.txt
+++ b/0-collect-data/datacite-dois.txt
-10.5281/zenodo.8269854
-10.5281/zenodo.8269855
-10.5281/zenodo.10069275
-10.5281/zenodo.10069276
+10.25384/sage.c.6837354.v1
+10.6084/m9.figshare.23575390.v1
+10.5061/dryad.5s77q
+10.18709/perscido.2021.04.ds331
+10.48537/hal-03220363
 10.5281/zenodo.10055461
-10.5281/zenodo.10055462
-10.5281/zenodo.10036360
-10.5281/zenodo.10049814
-10.5281/zenodo.10013099
-10.5281/zenodo.10013098
-10.5281/zenodo.10053092
-10.5281/zenodo.10053093
-10.5281/zenodo.10050502
-10.5281/zenodo.10050503
-10.6084/m9.figshare.24447574.v1
-10.6084/m9.figshare.c.6900580
-10.6084/m9.figshare.c.6900580.v1
-10.6084/m9.figshare.24447574
-10.7280/d1595v
-10.7280/d1b114
-10.7280/d1gw91
 10.7280/d1667w
-10.7280/d1r085
-10.7280/d1z69g
-10.7280/d11h3x
-10.7280/d1wt11
-10.7280/d1mm37
+10.48537/hal-03220248
+10.6084/m9.figshare.23575381
 10.5061/dryad.zw3r2286h
+10.57757/iugg23-2595
+10.5061/dryad.18tg7
+10.6084/m9.figshare.23822163.v1
+10.25384/sage.c.6567921
+10.5061/dryad.dv41ns1wf
+10.34746/cahierscostech48
+10.25384/sage.22573164
+10.6084/m9.figshare.22621187.v1
+10.6084/m9.figshare.21430974
+10.48537/hal-03220350
+10.48390/0005-gz84
 10.5061/dryad.wpzgmsbp2
-10.5061/dryad.wm37pvmkw
-10.5061/dryad.wh70rxwpz
-10.5061/dryad.wh70rxwnf
-10.5061/dryad.v475g
-10.5061/dryad.ttdz08ktn
-10.5061/dryad.ttdz08m16
-10.5061/dryad.st350
-10.5061/dryad.rjdfn2z7p
-10.5061/dryad.rxwdbrvbg
-10.5061/dryad.qv9s4mwf3
-10.5061/dryad.rb0qk13
+10.5281/zenodo.8269854
+10.48537/hal-03220301
+10.48537/hal-03220303
+10.6084/m9.figshare.23822157
+10.18709/perscido.2022.09.ds375
+10.48537/hal-03220343
+10.5061/dryad.jq2bvq8bm
+10.5061/dryad.m0cfxpp06
+10.5281/zenodo.10036360
+10.6084/m9.figshare.22610681
+10.48537/hal-03220375
+10.5061/dryad.m37pvmd0v
+10.5281/zenodo.10205606
+10.6084/m9.figshare.21430971.v1
+10.5061/dryad.jwstqjqbr
 10.5061/dryad.qrfj6q5h6
+10.48537/hal-03220254
+10.5061/dryad.1qt12
+10.5061/dryad.rjdfn2z7p
+10.5061/dryad.jq2bvq878
+10.5281/zenodo.10013099
+10.48537/hal-03220274
+10.5061/dryad.m905qftwt
+10.6084/m9.figshare.24196813
+10.5061/dryad.d51c5b019
+10.60662/re4y-6g57
+10.18709/perscido.2017.10.ds117
+10.48537/hal-03220298
+10.5281/zenodo.10262983
+10.48380/dggv-p1k4-1p40
+10.48537/hal-03220374
+10.18709/perscido.2022.02.ds365
+10.18709/perscido.2018.10.ds133
 10.5061/dryad.qrfj6q5hv
+10.60662/7nek-jq08
+10.5061/dryad.283pp
+10.18709/perscido.2023.07.ds397
+10.48537/hal-03220314
+10.5281/zenodo.10050503
+10.57726/grx4-f695
+10.5061/dryad.060d2
+10.48537/hal-03220335
+10.48537/hal-03220319
+10.18709/perscido.2023.04.ds391
+10.48537/hal-03220365
+10.48537/hal-03220309
+10.5061/dryad.490p9
+10.5281/zenodo.10055462
+10.48537/hal-03220242
+10.48537/hal-03220288
+10.34745/numerev_1937
+10.5281/zenodo.10014633
+10.25384/sage.c.6567921.v1
+10.48537/hal-03220382
+10.48537/hal-03220297
+10.25364/19.2022.7.3
+10.48537/hal-03220355
+10.48649/asdc.1201
+10.6084/m9.figshare.24165071
+10.6084/m9.figshare.22735503.v1
+10.5061/dryad.3ffbg79pv
 10.5061/dryad.pc866t1k5
-10.5061/dryad.pp72j
-10.5061/dryad.n5tb2rbx9
-10.5061/dryad.mw6m905tc
-10.5061/dryad.n230404
-10.5061/dryad.n13hn
-10.5061/dryad.m905qftwt
-10.5061/dryad.m1t32
-10.5061/dryad.ksn02v746
-10.5061/dryad.m37pvmd0v
-10.5061/dryad.m0cfxpp06
-10.5061/dryad.jq2bvq878
-10.5061/dryad.k98sf7m98
-10.5061/dryad.jwstqjqbr
+10.6084/m9.figshare.c.6627480
+10.18709/perscido.2020.03.ds300
+10.48537/hal-03220332
+10.5061/dryad.612jm643q
+10.57726/cbag-z376
+10.6084/m9.figshare.23488967
+10.18709/perscido.2023.08.ds398
+10.6084/m9.figshare.24647123
+10.6084/m9.figshare.21550639
+10.6084/m9.figshare.c.6583718.v1
+10.6084/m9.figshare.c.6583718
+10.6084/m9.figshare.23575381.v1
+10.5061/dryad.fbg79cnx2
+10.6084/m9.figshare.23575369
+10.5061/dryad.k31d4
+10.7280/d11h3x
+10.13127/efsm20
+10.5061/dryad.2j5s7
+10.6084/m9.figshare.c.6593063.v1
+10.5061/dryad.3r2280ggb
+10.7275/bp3n-mw53
+10.48537/hal-03220269
+10.5281/zenodo.10276252
 10.5061/dryad.jm63xsj7b
-10.5061/dryad.jm58p
+10.6084/m9.figshare.23488967.v1
+10.48537/hal-03220312
+10.48537/hal-03220360
+10.7280/d1gw91
+10.6084/m9.figshare.23983484
+10.6084/m9.figshare.23822160.v1
+10.6084/m9.figshare.23575360.v1
+10.25647/liepp.wp.36
+10.5061/dryad.d2547d810
+10.48537/hal-03220357
+10.18709/perscido.2019.04.ds242
+10.48537/hal-03220369
+10.18709/perscido.2023.06.ds396
+10.6084/m9.figshare.c.6795368
+10.5061/dryad.7h44j100f
+10.48537/hal-03220272
+10.6084/m9.figshare.c.6851803
+10.48537/hal-03220380
+10.48537/hal-03220275
+10.6084/m9.figshare.21717750.v1
 10.5061/dryad.hmgqnk9hh
-10.5061/dryad.j6q573n7x
-10.5061/dryad.g72v731
-10.5061/dryad.f4qrfj6wr
-10.5061/dryad.dv41ns1wf
-10.5061/dryad.dbrv15f06
-10.5061/dryad.d51c5b019
-10.5061/dryad.cz8w9gj06
-10.5061/dryad.c866t1g49
-10.5061/dryad.brv15dvcj
-10.5061/dryad.c670tq2
-10.5061/dryad.c1jr3
+10.6084/m9.figshare.21430977.v1
+10.6084/m9.figshare.24165071.v1
+10.6084/m9.figshare.22613066
+10.23658/taltech.43/2020
+10.18709/perscido.2023.02.ds384
+10.6084/m9.figshare.c.6604292
+10.18709/perscido.2017.10.ds144
+10.48537/hal-03220302
+10.6084/m9.figshare.c.6853693.v1
+10.5281/zenodo.10205605
+10.18709/perscido.2019.10.ds267
+10.5281/zenodo.10005463
+10.5281/zenodo.10119871
+10.5061/dryad.3bk3j9kph
+10.48537/hal-03220366
+10.48537/hal-03220322
+10.6084/m9.figshare.c.6756888
 10.5061/dryad.b8gtht78h
-10.5061/dryad.9s4mw6mm3
-10.5061/dryad.93n5r
-10.5061/dryad.8gtht76tq
-10.5061/dryad.7wm37pvx5
-10.5061/dryad.7h44j100f
-10.5061/dryad.78642
-10.5061/dryad.6q573n621
-10.5061/dryad.6c886
-10.5061/dryad.689110r
-10.5061/dryad.6226d
-10.5061/dryad.612jm643q
+10.48380/gq45-dv88
+10.48537/hal-03220247
+10.48537/hal-03220340
+10.6084/m9.figshare.23575384
+10.57726/9c6a-cb74
+10.48537/hal-03220346
+10.5061/dryad.0p2ngf1w2
+10.6084/m9.figshare.c.6272373
+10.48537/hal-03220347
+10.5281/zenodo.8269855
+10.6084/m9.figshare.c.6592858
+10.57757/iugg23-4563
+10.6084/m9.figshare.22620895.v1
+10.48537/hal-03220323
+10.5061/dryad.cz8w9gj06
+10.6084/m9.figshare.22621187
+10.5281/zenodo.10014634
+10.48537/hal-03220324
+10.6084/m9.figshare.23737431.v2
+10.6084/m9.figshare.c.6604292.v1
+10.48537/hal-03220379
+10.6084/m9.figshare.22735503
+10.48537/hal-03220318
+10.5061/dryad.pp72j
+10.5061/dryad.n5tb2rbx9
+10.18709/perscido.2020.03.ds294
+10.6084/m9.figshare.23575360
+10.18709/perscido.2023.06.ds395
+10.6084/m9.figshare.22649276
 10.5061/dryad.6171j
+10.48537/hal-03220348
+10.6084/m9.figshare.23822163
+10.15146/zf0j-5m50
+10.18709/perscido.2022.06.ds369
+10.5061/dryad.n13hn
+10.48537/hal-03220368
+10.48537/hal-03220333
+10.48537/hal-03220334
+10.5281/zenodo.10119872
+10.48537/hal-03220255
+10.6084/m9.figshare.c.6950873
+10.5061/dryad.wh70rxwpz
+10.5281/zenodo.10165853
+10.48537/hal-03220377
+10.5281/zenodo.10069275
+10.48537/hal-03220250
+10.5281/zenodo.10053093
+10.5281/zenodo.10262984
+10.6084/m9.figshare.22620895
+10.6084/m9.figshare.23575378
+10.6084/m9.figshare.22610681.v1
+10.7914/wqvg-2272
+10.6084/m9.figshare.c.6756888.v1
+10.2312/yes19.15
+10.6084/m9.figshare.23822157.v1
+10.6084/m9.figshare.c.6250158
+10.6084/m9.figshare.c.6250158.v1
+10.5061/dryad.k98sf7m98
+10.48537/hal-03220352
+10.6084/m9.figshare.23575363.v1
+10.48537/hal-03220378
 10.5061/dryad.4rr39
-10.5061/dryad.4j0zpc8h2
-10.5061/dryad.4n5929c
-10.5061/dryad.4f4qrfjjc
-10.5061/dryad.490p9
-10.5061/dryad.3r2280ggb
-10.5061/dryad.3ffbg79pv
-10.5061/dryad.2v1m1fj
-10.5061/dryad.2j5s7
-10.5061/dryad.2fqz612m4
+10.5061/dryad.6226d
+10.18709/perscido.2022.06.ds370
+10.6084/m9.figshare.c.6627480.v1
+10.6084/m9.figshare.c.6584765
+10.18709/perscido.2023.04.ds390
+10.5061/dryad.6q573n621
+10.6084/m9.figshare.23822166.v1
+10.48537/hal-03220307
+10.6084/m9.figshare.23575372
+10.5061/dryad.wm37pvmkw
+10.5061/dryad.rxwdbrvbg
+10.5281/zenodo.10049814
+10.48537/hal-03220246
+10.18709/perscido.2023.06.ds392
 10.5061/dryad.27qf3
-10.5061/dryad.283pp
-10.5061/dryad.1s7v5
-10.5061/dryad.1sf007b
-10.5061/dryad.18tg7
-10.5061/dryad.0p2ngf1w2
+10.6084/m9.figshare.23822154
+10.48537/hal-03220317
+10.48537/hal-03220306
+10.48537/hal-03220325
+10.48380/evdd-zw82
+10.5061/dryad.9s4mw6mm3
+10.5061/dryad.2fqz612m4
+10.48537/hal-03220304
+10.18150/wyyjk6
+10.6084/m9.figshare.c.6579520.v1
+10.6084/m9.figshare.22609319.v1
+10.18709/mp70-ey27
+10.6084/m9.figshare.c.6593063
+10.18709/perscido.2018.07.ds225
+10.48537/hal-03220295
+10.5061/dryad.jm58p
+10.57726/pw2d-az70
+10.6084/m9.figshare.21341628.v1
+10.6084/m9.figshare.23575375.v1
+10.5061/dryad.4j0zpc8h2
+10.5281/zenodo.10005462
+10.5061/dryad.689110r
+10.5281/zenodo.10053092
+10.18709/perscido.2020.05.ds314
+10.60662/x25q-yv27
+10.18709/perscido.2020.01.ds289
+10.5061/dryad.c1jr3
+10.48537/hal-03220330
+10.18709/perscido.2017.06.ds80
+10.6084/m9.figshare.23575366.v1
+10.5281/zenodo.10222605
+10.5281/zenodo.10341149
 10.5061/dryad.000000046
-10.15146/zf0j-5m50
-10.5061/dryad.k31d4
-10.5061/dryad.jq2bvq8bm
-10.5061/dryad.fbg79cnx2
-10.5061/dryad.d2547d810
-10.5061/dryad.bnzs7h4dx
+10.48380/7gdm-j630
+10.6084/m9.figshare.23737431
+10.6084/m9.figshare.24202753
+10.48537/hal-03220316
+10.6084/m9.figshare.22609322
+10.48537/hal-03220361
+10.5061/dryad.6c886
+10.25384/sage.c.6837354
+10.48537/hal-03220308
+10.7280/d1wt11
+10.6084/m9.figshare.20235676.v1
+10.34616/wse.2019.13.61.80
+10.60662/0yc3-e898
+10.5061/dryad.v475g
+10.6084/m9.figshare.22604164.v1
+10.25647/liepp.pb.11
 10.5061/dryad.9w0vt4bd1
-10.5061/dryad.8290n
-10.5061/dryad.5s77q
-10.5061/dryad.5b58400
-10.5061/dryad.3bk3j9kph
-10.5061/dryad.1qt12
-10.5061/dryad.060d2
-10.5281/zenodo.10014634
-10.5281/zenodo.10014633
-10.5281/zenodo.10005462
-10.5281/zenodo.10005463
-10.5281/zenodo.10005439
-10.5281/zenodo.10005440
+10.6084/m9.figshare.22649276.v1
+10.48537/hal-03220372
+10.6084/m9.figshare.23983484.v1
+10.34929/sep.vi06.151
+10.48537/hal-03220354
+10.18709/perscido.2021.09.ds353
+10.6084/m9.figshare.24447574.v1
+10.48537/hal-03220286
+10.48537/hal-03220331
+10.48537/hal-03220284
+10.18709/perscido.2023.05.ds394
+10.6084/m9.figshare.24447574
+10.18709/perscido.2020.01.ds280
+10.5061/dryad.m1t32
+10.6084/m9.figshare.23822151.v1
+10.48537/hal-03220367
 10.6084/m9.figshare.c.6853693
+10.25647/liepp.wp.38bis
+10.5061/dryad.78642
+10.48537/hal-03220244
+10.48537/hal-03220329
+10.6084/m9.figshare.23575363
+10.5061/dryad.c866t1g49
+10.18709/perscido.2017.03.ds55
+10.18709/perscido.2021.11.ds356
+10.5061/dryad.ksn02v746
+10.6084/m9.figshare.c.6584765.v1
 10.6084/m9.figshare.24202753.v1
+10.57726/9782919732890
+10.18709/perscido.2022.05.ds367
+10.5061/dryad.rb0qk13
+10.5061/dryad.1s7v5
 10.6084/m9.figshare.24202750.v1
-10.6084/m9.figshare.24202753
-10.6084/m9.figshare.c.6853693.v1
-10.6084/m9.figshare.24202750
-10.6084/m9.figshare.24202747.v1
-10.6084/m9.figshare.24202747
-10.6084/m9.figshare.c.6851803
-10.6084/m9.figshare.c.6851803.v1
-10.6084/m9.figshare.24196813
-10.6084/m9.figshare.24196813.v1
-10.48380/evdd-zw82
-10.6084/m9.figshare.c.6842762.v1
-10.6084/m9.figshare.24165071.v1
-10.6084/m9.figshare.24165071
-10.6084/m9.figshare.c.6842762
-10.25384/sage.c.6837354.v1
-10.25384/sage.c.6837354
+10.6084/m9.figshare.23822151
+10.25364/19.2021.5.2
+10.18709/perscido.2017.11.ds100
 10.25384/sage.24147060
+10.48537/hal-03220321
 10.25384/sage.24147060.v1
-10.60662/7nek-jq08
-10.7914/wqvg-2272
-10.60662/pyvs-cj63
-10.60662/x25q-yv27
-10.60662/0yc3-e898
-10.60662/ydh4-8904
-10.60662/re4y-6g57
-10.60662/n581-qq67
-10.6084/m9.figshare.c.6795368.v1
-10.6084/m9.figshare.23983487
+10.6084/m9.figshare.24202747.v1
+10.5061/dryad.8290n
 10.6084/m9.figshare.23983487.v1
-10.6084/m9.figshare.c.6795368
-10.6084/m9.figshare.23983484
-10.6084/m9.figshare.23983484.v1
-10.6084/m9.figshare.c.6756888.v1
-10.6084/m9.figshare.c.6756888.v2
-10.6084/m9.figshare.23737431.v1
-10.6084/m9.figshare.23737431.v2
-10.6084/m9.figshare.c.6756888
-10.6084/m9.figshare.23737431
+10.6084/m9.figshare.22613066.v1
+10.48380/cwsp-mj37
+10.48537/hal-03220351
+10.6084/m9.figshare.c.6272373.v1
+10.48537/hal-03220337
 10.6084/m9.figshare.23822166
-10.6084/m9.figshare.c.6771537.v1
+10.48537/hal-03220283
+10.18709/perscido.2017.11.ds185
+10.2312/yes19
+10.5061/dryad.ttdz08ktn
+10.6084/m9.figshare.21717750
+10.6084/m9.figshare.c.6690029
+10.18709/perscido.2017.12.ds166
+10.18709/perscido.2022.01.ds364
+10.5061/dryad.mw6m905tc
+10.18709/perscido.2016.10.ds06
+10.5061/dryad.93n5r
+10.18709/perscido.2016.10.ds32
+10.57726/nt1t-n566
+10.6084/m9.figshare.24202750
+10.5061/dryad.ttdz08m16
+10.6084/m9.figshare.22613069.v1
+10.6084/m9.figshare.c.6712342
+10.48537/hal-03220267
+10.6084/m9.figshare.22609322.v1
+10.5281/zenodo.10069276
+10.6084/m9.figshare.24202747
+10.6084/m9.figshare.20235676
+10.5061/dryad.j6q573n7x
 10.6084/m9.figshare.c.6771537
-10.6084/m9.figshare.23822166.v1
-10.6084/m9.figshare.23822163
-10.6084/m9.figshare.23822163.v1
-10.6084/m9.figshare.23822160.v1
-10.6084/m9.figshare.23822157.v1
-10.6084/m9.figshare.23822160
-10.6084/m9.figshare.23822154
-10.6084/m9.figshare.23822154.v1
-10.6084/m9.figshare.23822157
-10.6084/m9.figshare.23822151.v1
-10.6084/m9.figshare.23822151
+10.5061/dryad.st350
+10.6084/m9.figshare.c.6851803.v1
+10.18709/perscido.2023.02.ds382
+10.18709/perscido.2021.12.ds363
+10.48537/hal-03220311
+10.48537/hal-03220249
+10.48537/hal-03220291
+10.5281/zenodo.10013098
+10.48537/hal-03220342
+10.5281/zenodo.10005440
+10.18709/perscido.2016.08.ds04
+10.5061/dryad.4n5929c
+10.5061/dryad.7wm37pvx5
+10.60662/n581-qq67
+10.48537/hal-03220282
 10.57757/iugg23-4534
-10.57757/iugg23-4563
-10.6084/m9.figshare.23575390.v1
-10.6084/m9.figshare.23575390
-10.6084/m9.figshare.c.6712342
+10.18709/perscido.2021.11.ds357
+10.18709/perscido.2017.10.ds129
+10.5061/dryad.2v1m1fj
+10.48537/hal-03220270
+10.7280/d1b114
+10.48537/hal-03220271
+10.18709/perscido.2016.11.ds08
+10.7280/d1mm37
+10.48537/hal-03220359
+10.6084/m9.figshare.c.6842762
+10.6084/m9.figshare.23822154.v1
+10.6084/m9.figshare.22609319
+10.5061/dryad.8gtht76tq
+10.5061/dryad.bnzs7h4dx
+10.48537/hal-03220253
+10.48380/dggv-h2gp-1860
+10.6084/m9.figshare.21341628
+10.48537/hal-03220256
+10.5281/zenodo.10050502
+10.6084/m9.figshare.24647123.v1
+10.6084/m9.figshare.23983487
+10.6084/m9.figshare.21430974.v1
+10.6084/m9.figshare.c.6795368.v1
+10.6084/m9.figshare.c.6900580.v1
 10.6084/m9.figshare.c.6712342.v1
-10.6084/m9.figshare.23575384
-10.6084/m9.figshare.23575384.v1
+10.48380/6fh7-7m80
+10.5061/dryad.wh70rxwnf
+10.5061/dryad.qv9s4mwf3
+10.48537/hal-03220273
+10.5061/dryad.c670tq2
+10.48537/hal-03220371
+10.6084/m9.figshare.23822160
+10.48537/hal-03220370
+10.48537/hal-03220328
+10.18709/perscido.2018.09.ds236
+10.18709/perscido.2019.07.ds249
+10.48537/hal-03220327
+10.48537/hal-03220341
+10.48537/hal-03220353
+10.18709/perscido.2017.10.ds138
+10.48537/hal-03220373
+10.48537/hal-03220296
 10.6084/m9.figshare.23575387
-10.6084/m9.figshare.23575387.v1
+10.6084/m9.figshare.24196813.v1
+10.6084/m9.figshare.22604164
+10.48537/hal-03220280
+10.48537/hal-03220364
+10.6084/m9.figshare.c.6592858.v1
+10.6084/m9.figshare.22613069
+10.6084/m9.figshare.23737431.v1
+10.48537/hal-03220293
+10.25519/6w2g-dr94
+10.5281/zenodo.10222606
+10.5285/634ee206-258f-4b47-9237-efff4ef9eedd
+10.48537/hal-03220381
+10.48537/10.48537/hal-03220247
+10.48537/hal-03220383
 10.6084/m9.figshare.23575372.v1
-10.6084/m9.figshare.23575378.v1
-10.6084/m9.figshare.23575369
-10.6084/m9.figshare.23575375
-10.6084/m9.figshare.23575378
-10.6084/m9.figshare.23575381.v1
-10.6084/m9.figshare.23575381
-10.6084/m9.figshare.23575366
-10.6084/m9.figshare.23575372
-10.6084/m9.figshare.23575366.v1
-10.6084/m9.figshare.23575369.v1
-10.6084/m9.figshare.23575375.v1
-10.6084/m9.figshare.23575363
-10.6084/m9.figshare.23575360.v1
-10.6084/m9.figshare.23575363.v1
-10.6084/m9.figshare.23575360
-10.48649/asdc.1201
-10.6084/m9.figshare.20235676
-10.6084/m9.figshare.20235676.v1
-10.6084/m9.figshare.c.6690029
-10.6084/m9.figshare.c.6690029.v1
-10.6084/m9.figshare.23488967.v1
-10.6084/m9.figshare.23488967
-10.48380/061t-ae68
-10.6084/m9.figshare.c.6627480
-10.6084/m9.figshare.c.6627480.v1
-10.6084/m9.figshare.22735503
-10.6084/m9.figshare.22735503.v1
-10.18150/wyyjk6
-10.6084/m9.figshare.c.6604292
-10.6084/m9.figshare.c.6604292.v1
-10.6084/m9.figshare.22649276.v1
-10.6084/m9.figshare.22649273.v1
-10.6084/m9.figshare.22649276
+10.48537/hal-03220310
+10.5061/dryad.1sf007b
+10.48537/hal-03220294
+10.6084/m9.figshare.c.6842762.v1
+10.6084/m9.figshare.21430971
+10.5061/dryad.g72v731
 10.6084/m9.figshare.22649273
-10.6084/m9.figshare.22621187.v1
-10.6084/m9.figshare.22621187
-10.6084/m9.figshare.c.6593063
-10.6084/m9.figshare.c.6593063.v1
-10.6084/m9.figshare.c.6592858
-10.6084/m9.figshare.22620895
-10.6084/m9.figshare.22620895.v1
-10.6084/m9.figshare.c.6592858.v1
-10.6084/m9.figshare.c.6586643
+10.48537/hal-03220356
+10.48537/hal-03220300
+10.48537/hal-03220292
+10.48537/hal-03220344
 10.6084/m9.figshare.c.6586643.v1
-10.6084/m9.figshare.22613069
-10.6084/m9.figshare.22613069.v1
-10.6084/m9.figshare.22613066.v1
-10.6084/m9.figshare.22613066
-10.6084/m9.figshare.c.6584765
-10.6084/m9.figshare.c.6584765.v1
-10.6084/m9.figshare.22610681.v1
-10.6084/m9.figshare.22610681
-10.6084/m9.figshare.c.6583718.v1
-10.6084/m9.figshare.c.6583718
-10.6084/m9.figshare.22609322.v1
-10.6084/m9.figshare.22609319
-10.6084/m9.figshare.22609319.v1
-10.6084/m9.figshare.22609322
-10.6084/m9.figshare.c.6579520.v1
+10.7280/d1595v
+10.6084/m9.figshare.23575375
+10.48537/hal-03220336
+10.18709/perscido.2023.12.ds403
+10.7280/d1z69g
 10.6084/m9.figshare.c.6579520
-10.6084/m9.figshare.22604164
-10.6084/m9.figshare.22604164.v1
+10.5281/zenodo.10276253
+10.6084/m9.figshare.c.6771537.v1
+10.6084/m9.figshare.23575369.v1
+10.5061/dryad.5b58400
+10.18709/perscido.2020.06.ds299
+10.18709/perscido.2021.09.ds334
 10.6084/m9.figshare.21550639.v1
-10.6084/m9.figshare.21550639
-10.25384/sage.c.6567921
-10.25384/sage.22573164
+10.48537/hal-03220289
+10.6084/m9.figshare.c.6586643
+10.6084/m9.figshare.c.6756888.v2
+10.5281/zenodo.10165854
+10.5061/dryad.dbrv15f06
+10.5061/dryad.n230404
+10.18709/perscido.2020.04.ds310
+10.5285/3ea504d8-41c2-40dc-86dc-284c341badaa
+10.18709/perscido.2022.09.ds376
+10.6084/m9.figshare.c.6690029.v1
+10.48537/hal-03220313
+10.5061/dryad.f4qrfj6wr
 10.25384/sage.22573164.v1
-10.25384/sage.c.6567921.v1
-10.13127/efsm20
-10.6084/m9.figshare.21717750
-10.6084/m9.figshare.21717750.v1
-10.6084/m9.figshare.21430974.v1
-10.6084/m9.figshare.21430977.v1
-10.6084/m9.figshare.21430971
-10.6084/m9.figshare.21430971.v1
-10.6084/m9.figshare.21430977
-10.6084/m9.figshare.21430974
-10.6084/m9.figshare.c.6272373.v1
-10.6084/m9.figshare.c.6272373
-10.6084/m9.figshare.21341628.v1
-10.6084/m9.figshare.21341628
-10.6084/m9.figshare.c.6250158
-10.6084/m9.figshare.c.6250158.v1
-10.48380/dggv-h2gp-1860
-10.34746/cahierscostech48
-10.34929/xttd-nb60
-10.25647/liepp.wp.36
-10.25647/liepp.wp.38bis
-10.48380/dggv-p1k4-1p40
-10.25364/19.2022.7.3
-10.57726/grx4-f695
 10.57726/j3mg-e206
-10.57726/nt1t-n566
-10.57726/cbag-z376
-10.57726/9c6a-cb74
-10.57726/pw2d-az70
-10.57726/9782919732890
-10.5285/3ea504d8-41c2-40dc-86dc-284c341badaa
-10.25647/liepp.pb.11
-10.34616/wse.2019.13.61.80
-10.48390/0005-gz84
-10.5285/634ee206-258f-4b47-9237-efff4ef9eedd
-10.2312/yes19.15
-10.2312/yes19
+10.5061/dryad.4f4qrfjjc
+10.5061/dryad.brv15dvcj
+10.48537/hal-03220299
+10.48537/hal-03220320
+10.6084/m9.figshare.23575366
+10.6084/m9.figshare.c.6950873.v1
+10.5281/zenodo.10005439
+10.34929/xttd-nb60
+10.18709/perscido.2020.09.ds330
+10.60662/pyvs-cj63
+10.6084/m9.figshare.23575378.v1
+10.48537/hal-03220287
+10.48380/061t-ae68
 10.35088/hh7x-gr77
-10.34929/sep.vi06.151
-10.25364/19.2021.5.2
-10.7275/bp3n-mw53
+10.48537/hal-03220285
+10.5281/zenodo.10341148
+10.48537/hal-03220349
+10.6084/m9.figshare.23575390
+10.6084/m9.figshare.c.6900580
+10.48537/hal-03220268
+10.18709/perscido.2018.11.ds155
+10.48537/hal-03220315
+10.7280/d1r085
+10.6084/m9.figshare.23575387.v1
+10.6084/m9.figshare.22649273.v1
+10.60662/ydh4-8904
+10.48537/10.48537/hal-03220281
+10.6084/m9.figshare.21430977
+10.18709/perscido.2017.03.ds31
--- a/0-collect-data/datacite.py
+++ b/0-collect-data/datacite.py
@@ -3,19 +3,26 @@

 """
 ## todo
- v2 : périmètre UGA : ajouter les ROR des unités, des établissements/laboratoires associés (par exemple Grenoble INP)
+- v2 : périmètre UGA : ajouter les ROR des unités, des établissements/laboratoires associés (eg Grenoble INP, sciencepo grenoble)

 ## Documentation
 * Doc générale API Datacite : https://support.datacite.org/docs/api
 * Recherche d'un DOI : https://support.datacite.org/docs/api-sampling
 * Pagination : https://support.datacite.org/docs/pagination
+
+## memo sur les requêtes
+client_id=JBRU.AAU le laboratoire AAU
+client_id=inist.persyval données issues du Labex Persyval-lab (PIA)
+
 """

 import requests

 urls = [
    'https://api.datacite.org/dois?affiliation=true&query=creators.affiliation.affiliationIdentifier:"https://ror.org/02rx3b187"&page[size]=100',
-    'https://api.datacite.org/dois?affiliation=true&query=contributors.affiliation.affiliationIdentifier:"https://ror.org/02rx3b187"&page[size]=100'
+    'https://api.datacite.org/dois?affiliation=true&query=contributors.affiliation.affiliationIdentifier:"https://ror.org/02rx3b187"&page[size]=100',
+    "https://api.datacite.org/dois?client_id=JBRU.AAU&page[size]=100",
+    "https://api.datacite.org/dois?client_id=inist.persyval&page[size]=100"
    # possibilité d'ajouter d'autres requêtes
 ]

@@ -52,8 +59,7 @@ def get_dois(results):
                dois.append(doi)
    return dois, not_dois

-# on récupère les dois
-
+# récupérer les dois
 dois = []
 not_dois = []

@@ -62,14 +68,14 @@ for url in urls:
    dois += doi
    not_dois += not_doi

-# on supprime les doublons

+# supprimer les doublons
 unique_dois = list(set(dois))

-print("Nombre de dois différents trouvés : " + str(len(unique_dois)))
+print(f"Nombre de dois différents trouvés\t{len(unique_dois)}")

-# exporter la liste de DOI au format txt

+# exporter la liste de DOI au format txt
 with open("datacite-dois.txt", 'w') as f :
    [f.write(f"{line}\n") for line in unique_dois]

--- a/0-collect-data/z-datacite-demo.ipynb
+++ b/0-collect-data/z-datacite-demo.ipynb
@@ -17,7 +17,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 1,
   "id": "d229201d-4e79-40a8-9472-9ea46b344b1c",
   "metadata": {},
   "outputs": [],
@@ -27,7 +27,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 2,
   "id": "7ce19b89-d5b7-4dbe-9fab-a15a81b42078",
   "metadata": {},
   "outputs": [],
@@ -43,7 +43,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 3,
   "id": "ec73be41-21df-4448-b58e-e21306f6b9fa",
   "metadata": {},
   "outputs": [
@@ -91,7 +91,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 4,
   "id": "e0722b5b-0059-4842-8e8a-2125239a7b7d",
   "metadata": {},
   "outputs": [
@@ -139,19 +139,19 @@
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
-       "      <td>10.7280/d1667w</td>\n",
-       "      <td>Greenland Marine-Terminating Glacier Retreat Data</td>\n",
-       "      <td>2020-12-01T18:09:19Z</td>\n",
-       "      <td>[Wood, Michael, Rignot, Eric, Bjørk, Anders, V...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
       "      <td>10.7280/d1595v</td>\n",
       "      <td>Annual Ice Velocity of the Greenland Ice Sheet...</td>\n",
       "      <td>2019-03-29T10:37:23Z</td>\n",
       "      <td>[Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>10.7280/d1667w</td>\n",
+       "      <td>Greenland Marine-Terminating Glacier Retreat Data</td>\n",
+       "      <td>2020-12-01T18:09:19Z</td>\n",
+       "      <td>[Wood, Michael, Rignot, Eric, Bjørk, Anders, V...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10.7280/d1b114</td>\n",
       "      <td>Dataset for: Fast retreat of Pope, Smith, and ...</td>\n",
@@ -209,8 +209,8 @@
       "                                              DOI  \\\n",
       "0                                  10.7280/d11h3x   \n",
       "1                                  10.7280/d1mm37   \n",
-       "2                                  10.7280/d1667w   \n",
-       "3                                  10.7280/d1595v   \n",
+       "2                                  10.7280/d1595v   \n",
+       "3                                  10.7280/d1667w   \n",
       "4                                  10.7280/d1b114   \n",
       "..                                            ...   \n",
       "137                  10.6084/m9.figshare.23488967   \n",
@@ -222,8 +222,8 @@
       "                                                 Titre                  Date  \\\n",
       "0    Annual Ice Velocity of the Greenland Ice Sheet...  2019-03-29T12:53:36Z   \n",
       "1    Annual Ice Velocity of the Greenland Ice Sheet...  2018-12-14T09:39:45Z   \n",
-       "2    Greenland Marine-Terminating Glacier Retreat Data  2020-12-01T18:09:19Z   \n",
-       "3    Annual Ice Velocity of the Greenland Ice Sheet...  2019-03-29T10:37:23Z   \n",
+       "2    Annual Ice Velocity of the Greenland Ice Sheet...  2019-03-29T10:37:23Z   \n",
+       "3    Greenland Marine-Terminating Glacier Retreat Data  2020-12-01T18:09:19Z   \n",
       "4    Dataset for: Fast retreat of Pope, Smith, and ...  2021-11-01T23:46:08Z   \n",
       "..                                                 ...                   ...   \n",
       "137  Additional file 1 of 3DVizSNP: a tool for rapi...  2023-06-10T03:21:52Z   \n",
@@ -235,8 +235,8 @@
       "                                               Auteurs  \n",
       "0    [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...  \n",
       "1    [Mouginot, Jeremie, Rignot, Eric, Millan, Roma...  \n",
-       "2    [Wood, Michael, Rignot, Eric, Bjørk, Anders, V...  \n",
-       "3    [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...  \n",
+       "2    [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...  \n",
+       "3    [Wood, Michael, Rignot, Eric, Bjørk, Anders, V...  \n",
       "4    [Milillo, Pietro, Rignot, Eric, Rizzoli, Paola...  \n",
       "..                                                 ...  \n",
       "137  [Sierk, Michael, Ratnayake, Shashikala, Wagle,...  \n",
@@ -248,7 +248,7 @@
       "[142 rows x 4 columns]"
      ]
     },
-     "execution_count": 29,
+     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -286,7 +286,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.11.5"
  }
 },
 "nbformat": 4,

 %% Cell type:markdown id:ce5cebe1-a058-4c0f-a5b5-23a02baa3521 tags:

 # Démo récupération des DOIs affiliés à l'UGA depuis Datacite

 ## Documentation
 * Doc générale API Datacite : https://support.datacite.org/docs/api
 * Recherche d'un DOI : https://support.datacite.org/docs/api-sampling
 * Pagination : https://support.datacite.org/docs/pagination

 ## Code

 %% Cell type:code id:d229201d-4e79-40a8-9472-9ea46b344b1c tags:

 ``` python
 import requests, json, pandas
 ```

 %% Cell type:code id:7ce19b89-d5b7-4dbe-9fab-a15a81b42078 tags:

 ``` python
 # construction de l'url
 url_pre = 'https://api.datacite.org/dois?affiliation=true&page[size]=1000'
 url_query = '&query=(creators.affiliation.affiliationIdentifier:"https://ror.org/02rx3b187") AND (types.resourceTypeGeneral:Dataset)'

 # obtention des résultats de la requête
 req = requests.get(url_pre + url_query)
 results = req.json()
 ```

 %% Cell type:code id:ec73be41-21df-4448-b58e-e21306f6b9fa tags:

 ``` python
 # ajouter les DOIs dans une liste, sans ajouter les résultats qui ne sont pas des DOIs
 # ajouter les autres résultats qui nous intéressent dans des listes afin de construire un DataFrame
 dois = []
 not_dois = []
 titles = []
 dates = []
 authors = []

 # boucler pour ajouter les informations relatives à chaque dépôt
 all_md_list = results["data"]
 nb_dois = len(all_md_list)

 for item in all_md_list :
    doi = item["id"]
    # si l'identifiant n'est pas un doi, on ne le prend pas
    if item.get("type") != "dois":
        print("Le résultat " + str(item) + " est de type " + item.get("type") + " : " + doi)
        not_dois.append(doi)
    # sinon, on récupère les informations dont on a besoin
    else:
        dois.append(doi)
        titles.append(item["attributes"]["titles"][0].get("title"))
        dates.append(item["attributes"]["created"])
        # boucler pour obtenir tous les auteurs
        auts = []
        for aut in item["attributes"]["creators"]:
            auts.append(aut.get("name"))
        authors.append(auts)

 # affichage du résultat
 print("Nombre de résultats trouvés : " + str(nb_dois))
 ```

 %% Output

    Nombre de résultats trouvés : 142

 %% Cell type:code id:e0722b5b-0059-4842-8e8a-2125239a7b7d tags:

 ``` python
 # construction du DataFrame
 df = pandas.DataFrame({'DOI':dois, 'Titre':titles, 'Date':dates, 'Auteurs':authors})

 df.to_csv("z-resultats-demo-datacite.csv")
 df
 ```

 %% Output

                                                  DOI  \
    0                                  10.7280/d11h3x
    1                                  10.7280/d1mm37
-    2                                  10.7280/d1667w
-    3                                  10.7280/d1595v
+    2                                  10.7280/d1595v
+    3                                  10.7280/d1667w
    4                                  10.7280/d1b114
    ..                                            ...
    137                  10.6084/m9.figshare.23488967
    138                               10.18150/wyyjk6
    139                               10.13127/efsm20
    140  10.5285/3ea504d8-41c2-40dc-86dc-284c341badaa
    141  10.5285/634ee206-258f-4b47-9237-efff4ef9eedd
    
                                                     Titre                  Date  \
    0    Annual Ice Velocity of the Greenland Ice Sheet...  2019-03-29T12:53:36Z
    1    Annual Ice Velocity of the Greenland Ice Sheet...  2018-12-14T09:39:45Z
-    2    Greenland Marine-Terminating Glacier Retreat Data  2020-12-01T18:09:19Z
-    3    Annual Ice Velocity of the Greenland Ice Sheet...  2019-03-29T10:37:23Z
+    2    Annual Ice Velocity of the Greenland Ice Sheet...  2019-03-29T10:37:23Z
+    3    Greenland Marine-Terminating Glacier Retreat Data  2020-12-01T18:09:19Z
    4    Dataset for: Fast retreat of Pope, Smith, and ...  2021-11-01T23:46:08Z
    ..                                                 ...                   ...
    137  Additional file 1 of 3DVizSNP: a tool for rapi...  2023-06-10T03:21:52Z
    138  Estimates for recombination coefficients from ...  2022-04-21T14:17:28Z
    139  European Fault-Source Model 2020 (EFSM20): onl...  2022-10-30T16:28:46Z
    140  Ice radar data from Little Dome C, Antarctica,...  2022-03-04T09:26:18Z
    141  Polarimetric ApRES data on a profile across Do...  2021-09-16T11:17:15Z
    
                                                   Auteurs
    0    [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...
    1    [Mouginot, Jeremie, Rignot, Eric, Millan, Roma...
-    2    [Wood, Michael, Rignot, Eric, Bjørk, Anders, V...
-    3    [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...
+    2    [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...
+    3    [Wood, Michael, Rignot, Eric, Bjørk, Anders, V...
    4    [Milillo, Pietro, Rignot, Eric, Rizzoli, Paola...
    ..                                                 ...
    137  [Sierk, Michael, Ratnayake, Shashikala, Wagle,...
    138  [Sakowski, Konrad, Borowik, Lukasz, Rochat, Né...
    139  [Basili, Roberto, Danciu, Laurentiu, Beauval, ...
    140  [Mulvaney, Robert, King, Edward, Martin, Carlo...
    141      [Corr, Hugh, Ritz, Catherine, Martin, Carlos]
    
    [142 rows x 4 columns]

 %% Cell type:code id:0308feea-2560-4e33-836a-285a65db2429 tags:

 ``` python
 ```

--- a/1-enrich-with-datacite/concatenet-enrich-dois.py
+++ b/1-enrich-with-datacite/concatenet-enrich-dois.py
@@ -39,7 +39,9 @@ for doi in dois : #[:300]
 		continue

 	## get md from datacite
+
 	raw_md = my_functions.get_md_from_datacite(doi)
+	## to debug print(f"\t{doi}")

 	### if doi not in datacite
 	if raw_md == "error" : 

--- a/1-enrich-with-datacite/datacite-parser-instructions.json
+++ b/1-enrich-with-datacite/datacite-parser-instructions.json
@@ -3,7 +3,7 @@
 	"version" : "2023-11-20",
 	"comentaires" : {
 		"0" : "non prise en compte de l'attribut dates",
-		"1" : "non prise en compte de l'attrbut relatedIdentifiers"
+		"1" : "non prise en compte de l'attribut relatedIdentifiers"
 	},
 	"path-and-fields" : {


--- a/1-enrich-with-datacite/z_personal_functions.py
+++ b/1-enrich-with-datacite/z_personal_functions.py
@@ -51,10 +51,11 @@ def parse_value_following_instruction(key, instruction, datacite_content) :
                )
            
            ## quand les données sont des listes et qu'il faut itérer dessus
-            else : 
+            else :
                all_vals = []
                temp_key_to_get = instruction["past_values_w_this_key"]
-                [all_vals.append( item[ temp_key_to_get ]) for item in datacite_content]
+                # itérer sur les éléments, vérifier si la clé est bien présente, si oui ajouter la valeur
+                [all_vals.append( item[ temp_key_to_get ]) for item in datacite_content if item.get(temp_key_to_get)]
                           
                buffer.update(
                    {temp_key_to_get : ",".join(all_vals)}
@@ -103,7 +104,7 @@ def parse_datacite_md(raw_datacite_mds):
        if data from datacite is needed get it with parse_value_following_instruction()
    """
    doi_md = {
-    "doi" : raw_datacite_mds["data"]["id"]
+        "doi" : raw_datacite_mds["data"]["id"]
    }
    
    ## ____0____ from json file load instructions

--- a/2-produce-graph/hist--datasets-by-year.png
+++ b/2-produce-graph/hist--datasets-by-year.png
--- a/2-produce-graph/hist-quantity-by-repo.py
+++ b/2-produce-graph/hist-quantity-by-repo.py
@@ -6,6 +6,7 @@ df = my_fct.load_and_treat_csv()

 print(df.columns)

+
 print("nb de datasets\t", len(df))

 ## publicationYear contient une année de 1995 : on reconstruit un champs année à partir de "created" : date d'enregistrement du dépot
@@ -31,7 +32,7 @@ ax.spines['right'].set_visible(False)
 ax.set_ylabel("number of datasets", labelpad = 10)

 plt.title(f"Number of datasets by year", fontsize = 22, x = 0.5, y = 1.03, alpha = 0.6)
-plt.suptitle(f"n = {len(df)}", fontsize = 12, x = 0.5, y = 0.8, alpha = 0.6)
+plt.suptitle(f"n = {len(df)}", fontsize = 12, x = 0.5, y = 0.9, alpha = 0.6)
 plt.savefig("hist--datasets-by-year.png")



--- a/2-produce-graph/pie--datacite-client.png
+++ b/2-produce-graph/pie--datacite-client.png
--- a/2-produce-graph/pie-datacite-client.py
+++ b/2-produce-graph/pie-datacite-client.py
@@ -12,8 +12,16 @@ df_client_raw = df["client"].value_counts()
 treshold = 8
 df_client = df_client_raw[df_client_raw > treshold]

-## remove point in client name (eg. zenodo.cern)
-clients_name = [item[: item.find(".")] for item in df_client.index]
+## rework client name (eg cern.zenodo)
+clients_name = []
+for item in df_client.index :
+	short_name = item[: item.find(".")]
+	if short_name not in ["inist", "jbru"] : 
+		clients_name.append( short_name)
+	else : 
+		clients_name.append(item)
+
+print(clients_name)

 df_client["other"] = df_client_raw[df_client_raw <= treshold].sum()
 clients_name.append("other")

--- a/dois-uga.csv
+++ b/dois-uga.csv