In [1]:
import pandas as pd
import pysolr
import requests
from tqdm.notebook import tqdm

In [2]:
df = pd.read_csv('metadata.csv')

In [3]:
df


Out[3]:
sha source_x title doi pmcid pubmed_id license abstract publish_time authors journal Microsoft Academic Paper ID WHO #Covidence has_full_text full_text_file
0 NaN Elsevier Intrauterine virus infections and congenital h... 10.1016/0002-8703(72)90077-4 NaN 4361535.0 els-covid Abstract The etiologic basis for the vast majo... 1972-12-31 Overall, James C. American Heart Journal NaN NaN False custom_license
1 NaN Elsevier Coronaviruses in Balkan nephritis 10.1016/0002-8703(80)90355-5 NaN 6243850.0 els-covid NaN 1980-03-31 Georgescu, Leonida; Diosi, Peter; Buţiu, Ioan;... American Heart Journal NaN NaN False custom_license
2 NaN Elsevier Cigarette smoking and coronary heart disease: ... 10.1016/0002-8703(80)90356-7 NaN 7355701.0 els-covid NaN 1980-03-31 Friedman, Gary D American Heart Journal NaN NaN False custom_license
3 aecbc613ebdab36753235197ffb4f35734b5ca63 Elsevier Clinical and immunologic studies in identical ... 10.1016/0002-9343(73)90176-9 NaN 4579077.0 els-covid Abstract Middle-aged female identical twins, o... 1973-08-31 Brunner, Carolyn M.; Horwitz, David A.; Shann,... The American Journal of Medicine NaN NaN True custom_license
4 NaN Elsevier Epidemiology of community-acquired respiratory... 10.1016/0002-9343(85)90361-4 NaN 4014285.0 els-covid Abstract Upper respiratory tract infections ar... 1985-06-28 Garibaldi, Richard A. The American Journal of Medicine NaN NaN False custom_license
5 212e990b378e8d267042753d5f9d4a64ea5e9869 Elsevier Infectious diarrhea: Pathogenesis and risk fac... 10.1016/0002-9343(85)90367-5 NaN 2861742.0 els-covid Abstract Our understanding of the pathogenesis... 1985-06-28 Cantey, J.Robert The American Journal of Medicine NaN NaN True custom_license
6 bf5d344243153d58be692ceb26f52c08e2bd2d2f Elsevier New perspectives on the pathogenesis of rheuma... 10.1016/0002-9343(88)90356-7 NaN 3052052.0 els-covid Abstract In the pathogenesis of rheumatoid art... 1988-10-14 Zvaifler, Nathan J. The American Journal of Medicine NaN NaN True custom_license
7 ddd2ecf42ec86ad66072962081e1ce4594431f9c Elsevier Management of acute and chronic respiratory tr... 10.1016/0002-9343(88)90456-1 NaN 3048091.0 els-covid Abstract Pharyngitis, bronchitis, and pneumoni... 1988-09-16 Ellner, Jerrold J. The American Journal of Medicine NaN NaN True custom_license
8 a55cb4e724091ced46b5e55b982a14525eea1c7e Elsevier Acute bronchitis: Results of U.S. and European... 10.1016/0002-9343(92)90608-E NaN 1621745.0 els-covid Abstract Acute bronchitis, an illness frequent... 1992-06-22 Dere, Willard H. The American Journal of Medicine NaN NaN True custom_license
9 a1fd28115cfa14869f29f30d2121c1058e6e81e9 Elsevier Clinical and Immunologic Responses in Patients... 10.1016/0002-9394(75)90398-0 NaN 170831.0 els-covid NaN 1975-10-31 Knopf, Harry L.S.; Hierholzer, John C. American Journal of Ophthalmology NaN NaN True custom_license
10 60bf634cf15582a6b7f72eb3811ca5d8b8825c44 Elsevier Determination of microsomal lauric acid hydrox... 10.1016/0003-2697(88)90093-0 NaN 3389520.0 els-covid Abstract An assay for the microsomal hydroxyla... 1988-04-30 Romano, Maria C.; Straub, Kenneth M.; Yodis, L... Analytical Biochemistry NaN NaN True custom_license
11 b84658904af7f828615c7de04ffcb088bd49c50d Elsevier Phospholipid vesicles containing bovine heart ... 10.1016/0003-9861(91)90605-I NaN 1716878.0 els-covid Abstract Phospholipid vesicles containing bovi... 1991-10-31 Prochaska, Lawrence J.; Wilson, Kathryn S. Archives of Biochemistry and Biophysics NaN NaN True custom_license
12 c05ffd04482059ba3cd3965a389003e814ee2699 Elsevier The oligomeric structure of renal aminopeptida... 10.1016/0005-2736(93)90386-E NaN 8093665.0 els-covid Abstract Bovine renal brush-border membrane ve... 1993-01-18 Plakidou-Dymock, Stella; McGivan, John D. Biochimica et Biophysica Acta (BBA) - Biomembr... NaN NaN True custom_license
13 NaN Elsevier Monoclonal antibodies identify multiple epitop... 10.1016/0006-291X(85)91946-1 NaN 2409966.0 els-covid Abstract Nine hybridoma cell lines secreting a... 1985-06-28 Cherel, Isabelle; Grosclaude, Jeanne; Rouze, P... Biochemical and Biophysical Research Communica... NaN NaN False custom_license
14 0fa2750b5605f80e81064c6442a823ca3bf65f85 Elsevier Predict7, a program for protein structure pred... 10.1016/0006-291X(89)90049-1 NaN 2539121.0 els-covid Abstract We describe a program for protein seq... 1989-03-15 Cármenes, R.S.; Freije, J.P.; Molina, M.M.; Ma... Biochemical and Biophysical Research Communica... NaN NaN True custom_license
15 d9d3627bd3e93877a8934f06db472f3d641bbc99 Elsevier Suppression of MHV3 virus-activated macrophage... 10.1016/0006-2952(86)90056-0 NaN 3017357.0 els-covid Abstract Dieldrin (36 mg/kg body weight) admin... 1986-08-01 Krzystyniak, Krzysztof; Bernier, Jacques; Hugo... Biochemical Pharmacology NaN NaN True custom_license
16 005d48b545794f09d6db2d03a770466dcacaf7c2 Elsevier Broad-spectrum antiviral activity of carbodine... 10.1016/0006-2952(90)90031-F NaN 1689159.0 els-covid Abstract Carbocyclic cytidine (C-Cyd) is a bro... 1990-01-15 De Clercq, Erik; Bernaerts, Ria; Shealy, Y.Ful... Biochemical Pharmacology NaN NaN True custom_license
17 5c2e73c15119b111f62143f5b94bc531963eb799 Elsevier Inhibition of ribonucleotide reductase and gro... 10.1016/0006-2952(90)90356-P NaN 2242014.0 els-covid Abstract A series of N-hydroxy-N′-aminoguanidi... 1990-10-15 Masahiko, Matsumoto; Fox, John G.; Pou-Hsiung,... Biochemical Pharmacology NaN NaN True custom_license
18 8b4c7bd63dceaa9bab63a5ceefc1fdb203d1b784 Elsevier Antitumor activity and biochemical effects of ... 10.1016/0006-2952(91)90031-Y NaN NaN els-covid Abstract Topsentin, a bis(indolyl)imidazole ma... 1991-07-25 Burres, Neal S.; Barber, Dustan A.; Gunasekera... Biochemical Pharmacology NaN NaN True custom_license
19 fccbe2d1dab29119bf24e065b589725df5ae2c7a Elsevier Broad-spectrum antiviral and cytocidal activit... 10.1016/0006-2952(91)90120-T NaN 1710119.0 els-covid Abstract Cyclopentenylcytosine (Ce-Cyd) is a b... 1991-06-15 de Clercq, Erik; Murase, Junichi; Marquez, Vic... Biochemical Pharmacology NaN NaN True custom_license
20 3843020862eda73775740154e71c3e991ebaaf8f Elsevier Inhibition of aminopeptidases N, A and W A re-... 10.1016/0006-2952(92)90065-Q NaN 1360211.0 els-covid Abstract The effects of a range of metallopept... 1992-11-03 Tieku, Stephen; Hooper, Nigel M. Biochemical Pharmacology NaN NaN True custom_license
21 5055a81a32741e8c2d188c49c6e5290a09d615cd Elsevier Paraneoplastic limbic encephalitis: Neuropsych... 10.1016/0006-3223(90)90444-7 NaN 2155672.0 els-covid Abstract Limbic encephalitis as a distinct cli... 1990-03-01 Newman, Nancy J.; Bell, Iris R.; McKee, Ann C. Biological Psychiatry NaN NaN True custom_license
22 e6caa9eaa2171e4bc3f9ad3128989f1c2715bd91 Elsevier The relationship between axonal transport of p... 10.1016/0006-8993(86)91364-8 NaN 2432991.0 els-covid Abstract Fast and slow axonal transport of pro... 1986-11-05 Tansey, E.M.; Ikeda, Hisako Brain Research NaN NaN True custom_license
23 d8172a2a6371134b3128daffebd064ef33cd7eb5 Elsevier Regulation of astrocyte proliferation by prost... 10.1016/0006-8993(93)90455-V NaN 8348305.0 els-covid Abstract We found that astrocytes expressed th... 1993-06-04 Sawada, Makoto; Suzumura, Akio; Ohno, Kazushig... Brain Research NaN NaN True custom_license
24 94e2a71897a537ab0bab3710a9efeb8f0fe0c864 Elsevier Polarity of processes with Golgi apparatus in ... 10.1016/0006-8993(94)91327-7 NaN 7922504.0 els-covid Abstract The Golgi apparatus-complex (GA), is ... 1994-06-06 Lavi, Ehud; Wang, Qian; Stieber, Anna; Gonatas... Brain Research NaN NaN True custom_license
25 0a6b1d04aece4d54892d911e8367d0028ab78ee7 Elsevier Selective induction of interleukin-6 in mouse ... 10.1016/0006-8993(95)01535-3 NaN 8724991.0 els-covid Abstract Astrocytes produce granulocyte/macrop... 1996-03-25 Suzumura, Akio; Sawada, Makoto; Marunouchi, Tohru Brain Research NaN NaN True custom_license
26 1e47b54dffb8ee413f484a490005310037d36806 Elsevier A study of infective and other factors in exac... 10.1016/0007-0971(80)90048-0 NaN 6968574.0 els-covid NaN 1980-12-31 McHardy, Valentine U.; Inglis, J.M.; Calder, M... British Journal of Diseases of the Chest NaN NaN True custom_license
27 52b3b423a2935768a26ee1f95becf72f3b27817e Elsevier Diarrhoea in the dog and cat I. Acute diarrhoea 10.1016/0007-1935(86)90026-6 NaN 3594163.0 els-covid Abstract Faeces are not always uniform in cons... 1986-08-31 Murdoch, D.B. British Veterinary Journal NaN NaN True custom_license
28 NaN Elsevier Horses in health and disease J. L. Naviaux Phi... 10.1016/0007-1935(86)90081-3 NaN NaN els-covid NaN 1986-06-30 Vogel, C.J. British Veterinary Journal NaN NaN False custom_license
29 NaN Elsevier Animal health 1984—Report of the chief veterin... 10.1016/0007-1935(86)90082-5 NaN NaN els-covid NaN 1986-06-30 Andrews, A.H. British Veterinary Journal NaN NaN False custom_license
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
44190 059d5acb8af8bd2bedab06b5dcc0510691fe0f1e CZI Laboratory readiness and response for novel co... 10.2807/1560-7917.ES.2020.25.6.2000082 PMC7029448 32046815.0 cc-by Timely detection of novel coronavirus (2019-nC... 2020 Reusken, Chantal B.E.M.; Broberg, Eeva K.; Haa... Eurosurveillance 3.006255e+09 #664 True comm_use_subset
44191 53c5b444db5bde8e975a22df9e3c80250e8ad3d1 PMC Disease features of equine coronavirus and ent... 10.1111/jvim.15386 PMC6430874 30632200.0 cc-by-nc BACKGROUND: Equine coronavirus (ECoV) is an em... 2019 Jan 10 Mar-Apr Manship, Arlie J.; Blikslager, Anthony T.; Elf... J Vet Intern Med NaN NaN True noncomm_use_subset
44192 bf473015ec0534efc1d29bbdc3a9c37034eeb749; 57ce... PMC Vaccines, inspiring innovation in health() 10.1016/j.vaccine.2018.05.035 PMC6238075 29789241.0 cc-by This report covers the topics of pandemics, ep... 2018 Nov 19 Pagliusi, Sonia; Dennehy, Maureen; Kim, Hun Vaccine NaN NaN True comm_use_subset
44193 222534164391422210b3089109605e8ff4d1d46c PMC SARS coronavirus papain-like protease induces ... 10.1038/srep25754 PMC4865725 27173006.0 cc-by SARS coronavirus (SARS-CoV) papain-like protea... 2016 May 13 Li, Shih-Wein; Wang, Ching-Ying; Jou, Yu-Jen; ... Sci Rep NaN NaN True comm_use_subset
44194 680fb6a1caf3ad6cf8e730498317b5d400cea1d4 Elsevier Stressor-Induced Alterations of Adaptive Immun... 10.1016/j.iac.2010.09.002 PMC3339561 21094924.0 els-covid NaN 2011-02-28 Powell, Nicole D.; Allen, Rebecca G.; Hufnagle... Immunology and Allergy Clinics of North America NaN NaN True custom_license
44195 2883a8e6fafe65f0dc49b8e2aa1b1f4640f1a8d7 PMC A Circulating miRNA Signature for Stratificati... 10.3390/cancers11121872 PMC6966622 31769433.0 cc-by Although mammography is the gold standard for ... 2019 Nov 26 Loke, Sau Yeen; Munusamy, Prabhakaran; Koh, Ge... Cancers (Basel) NaN NaN True comm_use_subset
44196 b7ab9571dc69783d3b84dc3c5a24656db182afb6 PMC Viral Respiratory Tract Infection During the F... 10.1097/TXD.0000000000000808 PMC6092179 30255130.0 cc-by-nc-nd BACKGROUND: Chronic lung allograft dysfunction... 2018 Jul 11 Magnusson, Jesper; Westin, Johan; Andersson, L... Transplant Direct NaN NaN True noncomm_use_subset
44197 2520763bf2ffec5a1aac7eb0a45346af795eb35f Elsevier Are high-performing health systems resilient a... 10.1016/S0140-6736(20)30551-1 NaN NaN els-covid As of March 5, 2020, there has been sustained ... 2020-03-20 Legido-Quigley, Helena; Asgari, Nima; Teo, Yik... The Lancet 2.980700e+09 #5422 True custom_license
44198 737e13b0236c1e2a6ada9c31ad3d8987a559b244 PMC High Pulmonary Levels of IL-6 and IL-1β in Chi... 10.1371/journal.pone.0129517 PMC4466570 26066058.0 cc-by Non-typeable Haemophilus influenzae (NTHi) is ... 2015 Jun 12 Pizzutto, Susan J.; Upham, John W.; Yerkovich,... PLoS One NaN NaN True comm_use_subset
44199 8adc81255b4ba0eb48cbd7ddfe86f13959f39c7d PMC Discovery of an essential nucleotidylating act... 10.1093/nar/gkv838 PMC4787807 26304538.0 cc-by-nc RNA viruses encode an RNA-dependent RNA polyme... 2015 Sep 30 Lehmann, Kathleen C.; Gulyaeva, Anastasia; Zev... Nucleic Acids Res NaN NaN True noncomm_use_subset
44200 1369823dbf5f34fd8e2f5d5bba470711dfca4032; d057... PMC Multicentre randomised controlled trial to inv... 10.1136/bmjopen-2017-017003 PMC5724199 28790042.0 cc-by-nc INTRODUCTION: Severe trauma represents the lea... 2017 Aug 7 Marjanovic, Nicolas; Frasca, Denis; Asehnoune,... BMJ Open NaN NaN True noncomm_use_subset
44201 a044d99ce4fd194fe5d572aada61a4a83c4a274f Elsevier Positive rate of RT-PCR detection of SARS-CoV-... 10.1016/j.cca.2020.03.009 NaN NaN els-covid Abstract Background There’s an outbreak of a n... 2020-06-30 Liu, Rui; Han, Huan; Liu, Fang; Lv, Zhihua; Wu... Clinica Chimica Acta 2.053973e+09 #5447 True custom_license
44202 220fbe1f5e79e25737c0624de9a4245bfee48ec0; 59b5... PMC Complete genome sequence of canine astrovirus ... 10.1016/j.vetmic.2015.03.011 PMC4401448 25818578.0 cc-by Astroviruses are a common cause of gastroenter... 2015 May 15 Caddy, Sarah L.; Goodfellow, Ian Vet Microbiol NaN NaN True comm_use_subset
44203 55a2b6184753d85b19f0425ac2d68868e73248b7 PMC Use of Piezoelectric Immunosensors for Detecti... 10.3390/s16010096 PMC4732129 26791304.0 cc-by In preliminary ELISA studies where released-ac... 2016 Jan 20 Don, Elena; Farafonova, Olga; Pokhil, Suzanna;... Sensors (Basel) NaN NaN True comm_use_subset
44204 360d7a85fefdad638d52a705f668d2047fc63ce7; 97d0... PMC Characterization of patients transported with ... 10.5935/0103-507X.20180052 PMC6180471 30328986.0 cc-by OBJECTIVE: To characterize the transport of se... 2018 Li, Ho Yeh; Mendes, Pedro Vitale; Melro, Livia... Rev Bras Ter Intensiva NaN NaN True comm_use_subset
44205 4ecbacf61daab591e76f7471eb6e7fc1a4e0ed70; b31a... CZI Potential role of inanimate surfaces for the s... 10.1016/j.infpip.2020.100044 NaN NaN cc-by-nc-nd Summary The novel human coronavirus 2019-nCoV ... 2020 Kampf, Günter Infection Prevention in Practice 3.006062e+09 #867 True noncomm_use_subset
44206 1378320afa873bdb81e3f3314a430c7a208d2d08 PMC Acquired immunity and asymptomatic reservoir i... 10.1186/2049-9957-3-41 PMC4333876 25699182.0 cc-by The number of surveillance networks for infect... 2014 Oct 29 Tambo, Ernest; Xiao-Nong, Zhou Infect Dis Poverty NaN NaN True comm_use_subset
44207 e44632c9b598cac15ccda521e13c65ca9fcf7426; 6695... PMC The Healthy Infant Nasal Transcriptome: A Benc... 10.1038/srep33994 PMC5034274 27658638.0 cc-by Responses by resident cells are likely to play... 2016 Sep 23 Chu, Chin-Yi; Qiu, Xing; Wang, Lu; Bhattachary... Sci Rep NaN NaN True comm_use_subset
44208 a52566f6d96ec5a9a371582766a992a4ac38bd64 PMC Using GPS collars to investigate the frequency... 10.1371/journal.pone.0213910 PMC6447186 30943236.0 cc-by Intraspecific interactions between individuals... 2019 Apr 3 Broekhuis, Femke; Madsen, Emily K.; Keiwua, Ko... PLoS One NaN NaN True comm_use_subset
44209 b3cfc4dab5d54f17baa4dbf0887b3c0b8bf862b0 Elsevier Sequential affinity purification of peroxidase... 10.1016/j.jchromb.2008.01.003 PMC2678934 18258500.0 els-covid Abstract Hybrid hybridomas (quadromas) are der... 2008-03-01 Bhatnagar, Pravin K.; Das, Dipankar; Suresh, M... Journal of Chromatography B NaN NaN True custom_license
44210 a396657b0c580d496e109b82967c1a89d191ee9b; 560c... PMC The intrinsic vulnerability of networks to epi... 10.1016/j.ecolmodel.2018.05.013 PMC6039859 30210182.0 cc-by-nc-nd Contact networks are convenient models to inve... 2018 Sep 10 Strona, G.; Carstens, C.J.; Beck, P.S.A.; Han,... Ecol Modell NaN NaN True noncomm_use_subset
44211 7d77a852039f1cfc2c13843ecfa721c1fe49528c; fc02... PMC Lung ultrasound as a diagnostic tool for radio... 10.1016/j.rmed.2017.05.007 PMC5480773 28610670.0 cc-by BACKGROUND: Pneumonia is a leading cause of mo... 2017 Jul Ellington, Laura E.; Gilman, Robert H.; Chavez... Respir Med NaN NaN True comm_use_subset
44212 NaN Elsevier Calculating virus spread 10.1016/S0262-4079(20)30402-4 NaN NaN els-covid Getting a full picture of the coronavirus outb... 2020-02-22 Kucharski, Adam New Scientist 3.006474e+09 #1600 False custom_license
44213 428d1091cf63872ea81cb3c1632d76c4813748a1; 8244... PMC Viral etiology of hospitalized acute lower res... 10.3325/cmj.2013.54.122 PMC3641872 23630140.0 cc-by AIM: To estimate the proportional contribution... 2013 Apr Lukšić, Ivana; Kearns, Patrick K; Scott, Fiona... Croat Med J NaN NaN True comm_use_subset
44214 17de15d04f7a7643550666d2f0da773f5b7dc95c Elsevier COVID-19 Therapeutic and Prevention 10.1016/j.ijantimicag.2020.105937 NaN NaN els-covid NaN 2020-03-07 Raoult, Didier; Hsueh, Po-Ren; Stefani, Stefan... International Journal of Antimicrobial Agents NaN #5723 True custom_license
44215 d4f00f66c732c292fcfc28b19f44daa2fa620901 PMC Epidemiology and clinical profile of pathogens... 10.1371/journal.pone.0188325 PMC5693464 29149199.0 cc-by This study aimed to identify a broad spectrum ... 2017 Nov 17 Brini, Ines; Guerrero, Aida; Hannachi, Naila; ... PLoS One NaN NaN True comm_use_subset
44216 ec575d33c0d3b34af7644fcfed64af045a75ab63 Elsevier Functional Analysis of the Transmembrane Domai... 10.1016/j.jmb.2008.12.029 PMC2750892 19121325.0 els-covid Abstract To enter cells, enveloped viruses use... 2009-02-13 Bissonnette, Mei Lin Z.; Donald, Jason E.; DeG... Journal of Molecular Biology NaN NaN True custom_license
44217 7f8715a818bfd325bf4413d3c07003d7ce7b6f7e PMC Viral Entry Properties Required for Fitness in... 10.1128/mBio.00898-18 PMC6030562 29970463.0 cc-by Human parainfluenza viruses cause a large burd... 2018 Jul 3 Iketani, Sho; Shean, Ryan C.; Ferren, Marion; ... mBio NaN NaN True comm_use_subset
44218 07e78e218a159c35e9599e3751a99551a271597b Elsevier Arenavirus reverse genetics: New approaches fo... 10.1016/j.virol.2011.01.013 PMC3057228 21324503.0 els-covid Abstract Several arenaviruses, chiefly Lassa v... 2011-03-15 Emonet, Sebastien E.; Urata, Shuzo; de la Torr... Virology NaN NaN True custom_license
44219 04bc03c90437934a75fc6fdc228817234ef84c3a PMC A New Immunosuppressive Molecule Emodin Induce... 10.3389/fimmu.2017.01519 PMC5682309 29167674.0 cc-by Due to vigorous alloimmunity, an allograft is ... 2017 Nov 8 Qiu, Feifei; Liu, Huazhen; Liang, Chun-Ling; N... Front Immunol NaN NaN True comm_use_subset

44220 rows × 15 columns


In [4]:
json_docs = []
doc_id = 0
for index, row in tqdm(df.iterrows()):
    json_doc = {}
    json_doc["text"] = str(row['title']) + ' ' + str(row['abstract'])
    json_doc["id"] = str(doc_id)
    doc_id  = doc_id +1
    json_docs.append(json_doc)




In [6]:
core_name = 'covid19'
# Create a client instance. The timeout and authentication options are not required.
solr = pysolr.Solr('http://localhost:8983/solr/'+core_name, always_commit=True, timeout=10)

In [7]:
for doc in tqdm(json_docs):
    # How you'd index data.
    solr.add([
        doc
    ])




In [ ]: