diff --git a/core/src/main/resources/scrape/journals.csv b/core/src/main/resources/scrape/journals.csv
index 4179235..9ad6623 100644
--- a/core/src/main/resources/scrape/journals.csv
+++ b/core/src/main/resources/scrape/journals.csv
@@ -5,20 +5,20 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,31,71,0,0,0,2,0,https://doi.org/10.1093/BIOINFORMATICS/13.5.555
 0,0,29,40,0,696,0,2,30,https://doi.org/10.1093/BIOINFORMATICS/BTG334
 0,0,29,45,0,1079,9274,2,26,https://doi.org/10.1093/BIOINFORMATICS/BTX116
-0,0,28,95,0,1104,33116,2,35,https://doi.org/10.1093/BIOSTATISTICS/KXJ032
-0,0,23,68,5,1069,0,2,29,https://doi.org/10.1093/CZOOLO/61.5.854
-0,0,23,35,0,1240,29531,2,50,https://doi.org/10.1093/DATABASE/BAP020
-0,0,18,82,0,1265,26496,2,43,https://doi.org/10.1093/HMG/DDT384
-0,0,21,66,0,1876,21830,2,37,https://doi.org/10.1093/JHERED/ESI094
-0,0,21,113,5,1497,43204,2,27,https://doi.org/10.1093/MOLBEV/MSH194
+0,0,28,95,0,1104,33109,2,37,https://doi.org/10.1093/BIOSTATISTICS/KXJ032
+0,0,23,68,5,1069,0,2,31,https://doi.org/10.1093/CZOOLO/61.5.854
+0,0,23,35,0,1240,29531,2,52,https://doi.org/10.1093/DATABASE/BAP020
+0,0,18,82,0,1265,26532,2,45,https://doi.org/10.1093/HMG/DDT384
+0,0,21,66,0,1876,21882,2,37,https://doi.org/10.1093/JHERED/ESI094
+0,0,21,113,5,1497,43220,2,27,https://doi.org/10.1093/MOLBEV/MSH194
 0,0,18,98,0,1442,17079,2,53,https://doi.org/10.1093/NAR/GKG014
-0,0,18,68,0,2330,29041,2,38,https://doi.org/10.1093/NAR/GKH408
-0,0,18,153,0,1328,47191,2,25,https://doi.org/10.1093/NAR/GNJ005
-0,0,18,80,0,1088,17343,2,37,https://doi.org/10.1093/PCP/PCR141
-0,0,23,64,0,767,32329,2,0,https://doi.org/10.1093/PROTEIN/12.1.15
-0,0,25,102,5,2036,38521,2,35,https://doi.org/10.1080/10635150500541599
+0,0,18,68,0,2330,29049,2,38,https://doi.org/10.1093/NAR/GKH408
+0,0,18,153,0,1328,47299,2,25,https://doi.org/10.1093/NAR/GNJ005
+0,0,18,80,0,1088,17363,2,39,https://doi.org/10.1093/PCP/PCR141
+0,0,23,64,0,767,32545,2,0,https://doi.org/10.1093/PROTEIN/12.1.15
+0,0,25,102,5,2036,38569,2,35,https://doi.org/10.1080/10635150500541599
 # keywords question
-0,0,21,83,9,1493,39412,2,37,https://doi.org/10.1093/GLYCOB/CWJ049
+0,0,21,83,9,1493,39611,2,37,https://doi.org/10.1093/GLYCOB/CWJ049
 
 # citeseerx
 # registry from oaDOI
@@ -61,20 +61,20 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 # wiley_full
 0,0,28,83,0,511,0,1,0,https://currentprotocols.onlinelibrary.wiley.com/doi/full/10.1002/0471140864.ps1605s14
 0,0,29,41,0,0,0,1,0,https://onlinelibrary.wiley.com/doi/full/10.1002/9780471650126.dob0949
-0,0,59,75,0,2214,48472,2,39,https://onlinelibrary.wiley.com/doi/full/10.1002/1097-0134(20001001)41:1<108::AID-PROT130>3.0.CO;2-S
+0,0,59,75,0,2214,49801,2,39,https://onlinelibrary.wiley.com/doi/full/10.1002/1097-0134(20001001)41:1<108::AID-PROT130>3.0.CO;2-S
 0,0,52,129,0,1123,0,2,33,https://onlinelibrary.wiley.com/doi/full/10.1002/1098-2272(2000)19:1%2B<::AID-GEPI15>3.0.CO;2-1
 0,0,22,84,0,809,18751,2,44,https://onlinelibrary.wiley.com/doi/full/10.1002/ange.201507047
-0,0,20,73,0,1579,43185,2,28,https://onlinelibrary.wiley.com/doi/full/10.1002/cyto.a.20531
-0,0,18,58,0,1484,29518,2,40,https://onlinelibrary.wiley.com/doi/full/10.1002/humu.21438
-0,0,17,93,0,1088,24465,2,54,https://onlinelibrary.wiley.com/doi/full/10.1002/jcc.10386
+0,0,20,73,0,1579,45757,2,28,https://onlinelibrary.wiley.com/doi/full/10.1002/cyto.a.20531
+0,0,18,58,0,1484,29517,2,40,https://onlinelibrary.wiley.com/doi/full/10.1002/humu.21438
+0,0,17,93,0,1088,25018,2,54,https://onlinelibrary.wiley.com/doi/full/10.1002/jcc.10386
 0,0,22,110,0,1452,0,2,57,https://onlinelibrary.wiley.com/doi/full/10.1002/pmic.200300402
 0,0,22,166,0,459,0,2,53,https://onlinelibrary.wiley.com/doi/full/10.1002/pmic.200300483
-0,0,18,28,0,828,49480,2,49,https://onlinelibrary.wiley.com/doi/full/10.1002/prot.10146
+0,0,18,28,0,828,60976,2,49,https://onlinelibrary.wiley.com/doi/full/10.1002/prot.10146
 0,0,64,71,0,1332,30808,2,60,https://onlinelibrary.wiley.com/doi/full/10.1002/(SICI)1097-0061(20000130)16:2<177::AID-YEA516>3.0.CO;2-9
 0,0,20,52,0,694,10006,2,34,https://onlinelibrary.wiley.com/doi/full/10.1038/clpt.2012.96
 0,0,32,198,0,2188,33157,2,33,https://onlinelibrary.wiley.com/doi/full/10.1046/j.1469-1809.2003.00030.x
 0,0,21,59,0,1779,0,2,41,https://onlinelibrary.wiley.com/doi/full/10.1055/s-2004-817909
-0,0,25,55,0,1052,33768,2,29,https://onlinelibrary.wiley.com/doi/full/10.1111/1755-0998.12009.x
+0,0,25,55,0,1052,34407,2,29,https://onlinelibrary.wiley.com/doi/full/10.1111/1755-0998.12009.x
 0,0,23,123,0,1294,29792,2,33,https://onlinelibrary.wiley.com/doi/full/10.1111/2041-210X.12628
 
 # sciencedirect
@@ -96,30 +96,28 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 
 # springer
 0,0,18,83,4,665,0,1,0,https://doi.org/10.1007/BF00182187
-0,0,25,97,6,1028,23593,2,0,https://doi.org/10.1007/s00216-009-3166-1
+0,0,25,97,6,1028,23557,2,22,https://doi.org/10.1007/s00216-009-3166-1
 0,0,27,112,5,1053,0,2,0,https://doi.org/10.1007/978-0-387-49317-6_9
 0,0,27,89,5,1108,0,1,0,https://doi.org/10.1007/978-1-4939-0366-5_8
 0,0,21,54,3,759,0,2,0,https://doi.org/10.1007/s002510050595
-0,0,27,166,5,1409,0,2,34,https://doi.org/10.1016/j.jasms.2003.12.011
-0,0,29,132,5,1136,0,2,0,https://doi.org/10.1016/S1044-0305(01)00301-4
-0,0,23,108,8,1646,0,2,0,https://doi.org/10.1023/A:1006960004440
-0,0,25,86,5,1708,0,2,0,https://doi.org/10.1134/S1021443716020175
-0,0,26,41,3,936,0,2,0,https://doi.org/10.1140/epje/i2007-10314-1
-0,0,19,87,4,657,0,2,0,https://doi.org/10.1385/MB:22:3:301
-0,0,32,89,5,1191,0,1,35,https://doi.org/10.2165/00822942-200594030-00002
+0,0,23,108,8,1646,0,2,12,https://doi.org/10.1023/A:1006960004440
+0,0,25,86,5,1708,2206,2,11,https://doi.org/10.1134/S1021443716020175
+0,0,26,41,3,936,0,2,9,https://doi.org/10.1140/epje/i2007-10314-1
+0,0,19,87,4,657,0,2,18,https://doi.org/10.1385/MB:22:3:301
+0,0,32,89,5,1191,0,1,12,https://doi.org/10.2165/00822942-200594030-00002
 0,0,25,44,10,1837,0,1,0,https://doi.org/10.1007/978-3-319-24277-4
 0,0,23,135,5,0,0,1,0,https://doi.org/10.1007/0-306-47084-5_3
 0,0,19,66,5,557,0,2,0,https://doi.org/10.1007/11564096_50
 0,0,27,112,5,1053,0,2,0,https://doi.org/10.1007/978-0-387-49317-6_9
 0,0,25,60,5,311,0,1,0,https://doi.org/10.1385/0-89603-276-0:267
-0,0,0,31,0,1825,0,1,0,https://doi.org/10.1007/978-1-4419-9863-7
+0,0,25,31,0,1825,0,1,0,https://doi.org/10.1007/978-1-4419-9863-7
 
 # springer_ref
 0,0,30,7,0,519,978,1,47,https://doi.org/10.1007/978-1-4419-9863-7_1039
 0,0,30,8,0,797,973,1,33,https://doi.org/10.1007/978-1-4419-9863-7_1352
 
 # biomedcentral
-0,0,24,76,4,1279,31742,2,16,https://doi.org/10.1186/1471-2105-10-110
+0,0,24,76,4,1279,31745,2,16,https://doi.org/10.1186/1471-2105-10-110
 0,0,25,69,5,1695,52426,2,11,https://doi.org/10.1186/s12859-015-0686-x
 0,0,21,76,5,1640,20524,2,12,https://doi.org/10.1186/1471-2105-4-1
 0,0,27,61,5,2497,55107,2,37,https://doi.org/10.1186/1471-2105-10-S10-S8
@@ -128,13 +126,13 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,33,69,5,1591,40232,2,12,https://doi.org/10.1186/gb-2002-3-12-research0077
 0,0,24,120,5,681,57152,2,31,https://doi.org/10.1186/gb-2014-15-2-r35
 0,0,14,98,5,0,7805,2,22,https://doi.org/10.1186/gb4173
-0,0,25,77,5,671,79355,2,23,https://doi.org/10.1186/s13059-014-0405-3
+0,0,25,77,5,671,79385,2,23,https://doi.org/10.1186/s13059-014-0405-3
 0,0,24,56,5,1707,16658,2,27,https://doi.org/10.1186/1471-2164-10-375
 0,0,25,109,5,1458,49717,2,13,https://doi.org/10.1186/s12864-015-1704-0
 0,0,22,96,5,1359,22201,2,18,https://doi.org/10.1186/1756-0500-1-30
 0,0,21,76,5,1761,36966,2,13,https://doi.org/10.1186/1752-0509-1-2
 0,0,25,137,5,1157,109882,2,20,https://doi.org/10.1186/s12918-015-0211-x
-0,0,21,92,5,1982,54025,2,13,https://doi.org/10.1186/1748-7188-2-1
+0,0,21,92,5,1982,54027,2,13,https://doi.org/10.1186/1748-7188-2-1
 0,0,21,62,5,2184,17764,2,12,https://doi.org/10.1186/1751-0473-2-1
 0,0,24,147,5,1889,58187,2,16,https://doi.org/10.1186/1471-2148-10-210
 0,0,22,97,5,2106,51167,2,21,https://doi.org/10.1186/1756-8935-3-20
@@ -142,7 +140,7 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,21,53,5,1625,58798,2,18,https://doi.org/10.1186/1756-0381-3-1
 0,0,26,109,5,0,157,2,0,https://doi.org/10.1186/1297-9686-26-6-537
 0,0,22,107,5,1389,41423,2,13,https://doi.org/10.1186/1297-9686-44-9
-0,0,22,49,5,2043,33047,2,20,https://doi.org/10.1186/1472-6807-9-44
+0,0,22,49,5,2043,33052,2,20,https://doi.org/10.1186/1472-6807-9-44
 
 # cshlp
 0,0,19,20,0,1121,0,3,0,https://doi.org/10.1101/gr.10.4.511
@@ -339,7 +337,7 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 
 # f1000research_posters
 # pdf_a not working (because href="#")
-0,0,0,59,5,3934,0,1,41,https://doi.org/10.7490/f1000research.1110127.1
+0,0,0,59,5,3933,0,1,41,https://doi.org/10.7490/f1000research.1110127.1
 0,0,0,86,8,768,0,1,89,https://doi.org/10.7490/f1000research.1112656.1
 0,0,0,97,6,0,0,1,33,https://doi.org/10.7490/f1000research.1113436.1
 
@@ -358,7 +356,7 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,22,80,5,1218,0,1,0,http://orbit.dtu.dk/en/publications/netphosbac--a-predictor-for-serthr-phosphorylation-sites-in-bacterial-proteins(9faf0130-30a2-4a89-80ec-875b20c82e67).html
 
 # tandfonline
-0,0,30,62,0,1621,0,2,0,http://www.tandfonline.com/doi/abs/10.1080/07391102.2005.10507020
+0,0,30,62,0,1631,0,2,0,http://www.tandfonline.com/doi/abs/10.1080/07391102.2005.10507020
 0,0,21,68,0,0,0,2,0,http://www.tandfonline.com/doi/abs/10.1081/CNV-120016428
 0,0,25,61,5,1657,0,2,0,http://www.tandfonline.com/doi/abs/10.1198/jasa.2009.ap07611
 0,0,28,133,6,1515,0,3,0,http://www.tandfonline.com/doi/abs/10.1080/07391102.2014.968875
@@ -367,9 +365,9 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 
 # tandfonline_full
 0,0,21,68,0,0,0,1,0,http://www.tandfonline.com/doi/full/10.1081/CNV-120016428
-0,0,28,133,6,1515,33334,2,0,http://www.tandfonline.com/doi/full/10.1080/07391102.2014.968875
-0,0,29,164,6,1817,41664,2,0,http://www.tandfonline.com/doi/full/10.1080/07391102.2015.1095116
-0,0,22,117,0,0,7094,2,0,http://www.tandfonline.com/doi/full/10.1586/14789450.3.1.1
+0,0,28,133,6,1515,32940,2,0,http://www.tandfonline.com/doi/full/10.1080/07391102.2014.968875
+0,0,29,164,6,1817,40515,2,0,http://www.tandfonline.com/doi/full/10.1080/07391102.2015.1095116
+0,0,22,117,0,0,7091,2,0,http://www.tandfonline.com/doi/full/10.1586/14789450.3.1.1
 
 # asm
 0,0,20,196,0,2009,36823,2,45,https://doi.org/10.1128/JCM.00540-08
@@ -384,7 +382,7 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,23,62,0,627,0,2,0,https://doi.org/10.1145/2618243.2618289
 
 # degruyter
-0,0,22,81,4,973,0,1,0,https://doi.org/10.2202/1544-6115.1046
+0,0,22,81,4,975,0,1,0,https://doi.org/10.2202/1544-6115.1046
 0,0,22,61,6,1545,0,1,0,https://doi.org/10.1515/1544-6115.1753
 0,0,23,76,4,1459,0,1,0,https://doi.org/10.1515/sagmb-2012-0046
 
@@ -470,8 +468,8 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,29,86,0,496,0,1,0,https://doi.org/10.3233/978-1-61499-769-6-182
 
 # researchgate
-0,0,0,89,0,1608,0,2,0,https://doi.org/10.13140/RG.2.1.2763.4807
-0,0,0,73,0,1435,0,2,0,https://doi.org/10.13140/RG.2.1.3547.6561
+0,0,25,89,0,1608,0,2,0,https://doi.org/10.13140/RG.2.1.2763.4807
+0,0,25,73,0,1435,0,2,0,https://doi.org/10.13140/RG.2.1.3547.6561
 
 # frontiersin
 0,0,24,215,0,0,7809,2,0,https://doi.org/10.3389/FGENE.2014.00130
@@ -497,7 +495,7 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,27,95,0,579,30064,2,0,https://doi.org/10.1534/GENETICS.107.085332
 
 # plantphysiol
-0,0,17,70,0,1268,30332,2,31,https://doi.org/10.1104/PP.011577
+0,0,17,70,0,1268,30332,2,0,https://doi.org/10.1104/PP.011577
 0,0,21,118,0,2160,80460,2,32,https://doi.org/10.1104/PP.110.156851
 0,0,19,90,0,1123,26486,2,58,https://doi.org/10.1104/PP.15.01327
 
@@ -506,10 +504,10 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,22,112,0,1600,76501,2,39,https://doi.org/10.1105/TPC.113.121913
 
 # bloodjournal, now ashpublications.org
-0,0,28,67,2,0,5034,2,0,https://doi.org/10.1182/BLOOD-2010-04-282616
+0,0,28,67,2,0,5050,2,0,https://doi.org/10.1182/BLOOD-2010-04-282616
 
 # bloodadvances, now ashpublications.org
-0,0,32,107,12,1950,34205,2,0,https://doi.org/10.1182/BLOODADVANCES.2016000794
+0,0,32,107,12,1950,34217,2,0,https://doi.org/10.1182/BLOODADVANCES.2016000794
 
 # biochemj, portlandpress.com
 0,0,17,133,0,1700,0,1,0,https://doi.org/10.1042/BJ3080801
@@ -523,14 +521,14 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 # zenodo
 0,0,22,46,0,59,0,1,0,https://doi.org/10.5281/ZENODO.1251638
 0,0,22,19,11,546,0,1,0,https://doi.org/10.5281/ZENODO.1217112
-0,0,20,82,7,835,0,1,0,https://doi.org/10.5281/ZENODO.34090
+0,0,20,6,7,835,0,1,0,https://doi.org/10.5281/ZENODO.34090
 0,0,21,53,0,83,0,1,0,https://doi.org/10.5281/ZENODO.573771
 0,0,0,58,0,2627,0,2,0,https://zenodo.org/record/1259625
 0,0,0,46,0,46,0,2,0,https://zenodo.org/record/1233395
 
 # future-science
-0,0,0,101,4,1334,37006,2,36,https://doi.org/10.2144/000113999
-0,0,0,126,5,724,10940,2,40,https://doi.org/10.2144/000113978
+0,0,0,101,4,1334,37014,2,36,https://doi.org/10.2144/000113999
+0,0,0,126,5,724,10943,2,40,https://doi.org/10.2144/000113978
 
 # jstatsoft
 0,0,21,68,0,1302,0,2,0,https://doi.org/10.18637/JSS.V046.I11
@@ -559,13 +557,13 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,20,159,5,1579,0,3,6,https://doi.org/10.3390/ijms15057594
 
 # mdpi_full
-0,0,16,154,8,1489,40737,2,22,https://www.mdpi.com/1999-4915/4/11/3209/htm
-0,0,20,80,5,1168,22350,2,16,https://www.mdpi.com/1422-0067/17/8/1215/htm
-0,0,20,77,4,1175,27055,2,34,https://www.mdpi.com/1422-0067/18/2/274/htm
-0,0,16,75,3,1287,50026,2,12,https://www.mdpi.com/1999-4893/6/2/352/htm
-0,0,20,87,4,2209,33410,2,7,https://www.mdpi.com/1422-0067/20/5/1070/htm
-0,0,21,129,3,1648,52141,2,18,https://www.mdpi.com/2218-1989/6/4/39/htm
-0,0,20,159,5,1564,23971,2,6,https://www.mdpi.com/1422-0067/15/5/7594/htm
+0,0,16,154,8,1489,40855,2,22,https://www.mdpi.com/1999-4915/4/11/3209/htm
+0,0,20,80,5,1168,22359,2,16,https://www.mdpi.com/1422-0067/17/8/1215/htm
+0,0,20,77,4,1175,27089,2,34,https://www.mdpi.com/1422-0067/18/2/274/htm
+0,0,16,75,3,1265,50015,2,12,https://www.mdpi.com/1999-4893/6/2/352/htm
+0,0,20,87,4,2209,33431,2,7,https://www.mdpi.com/1422-0067/20/5/1070/htm
+0,0,21,129,3,1648,52188,2,18,https://www.mdpi.com/2218-1989/6/4/39/htm
+0,0,20,159,5,1564,24019,2,6,https://www.mdpi.com/1422-0067/15/5/7594/htm
 
 # preprints
 0,0,0,26,4,976,0,2,0,https://doi.org/10.20944/preprints201905.0056.v1
@@ -585,7 +583,7 @@ pmid,pmcid,doi,title,keywords,abstract,fulltext,links,corresp,site
 0,0,0,56,2,1770,0,2,0,https://doi.org/10.26434/chemrxiv.8178722.v1
 
 # iop
-0,0,24,120,0,2178,55355,2,0,https://doi.org/10.1088/1741-2552/ab208d
+0,0,24,120,0,2178,55211,2,0,https://doi.org/10.1088/1741-2552/ab208d
 0,0,24,100,0,0,6170,2,0,https://doi.org/10.1088/1752-7163/ab2fa2
 0,0,24,135,0,2014,31338,2,0,https://doi.org/10.1088/1361-6560/ab2f47
 
diff --git a/core/src/main/resources/scrape/journals.yaml b/core/src/main/resources/scrape/journals.yaml
index 7b321ae..58ebaa5 100644
--- a/core/src/main/resources/scrape/journals.yaml
+++ b/core/src/main/resources/scrape/journals.yaml
@@ -1,5 +1,5 @@
 #
-#  Copyright © 2016, 2018 Erik Jaaniso
+#  Copyright © 2016, 2018, 2020 Erik Jaaniso
 #
 #  This file is part of PubFetcher.
 #
@@ -156,8 +156,8 @@ oup:
   doi: .ww-citation-primary > a
   title: h1
   keywords: .kwd-group > .kwd-part
-  abstract: section.abstract > p, section.abstract > .sec > *
-  fulltext: .widget-ArticleFulltext > div > div > :not(.abstract-title):not(section.abstract):not(.article-metadata-panel):not(.article-metadata-standalone-panel):not(.kwd-group):not(.backreferences-title):not(.ref-list):not(.copyright):not(.reveal-modal):not(.license):not(.authorNotes-section-title):not(.authorNotes-section-title + p):not(.backacknowledgements-title):not(.backacknowledgements-title + p):not(.pdf-notice):not(:has(.footnote-content)):not(.table-modal)
+  abstract: section.abstract > p, section.abstract > .sec > *, section.abstract > div > .title, section.abstract > div > p
+  fulltext: .widget-ArticleFulltext > div > div > :not(.abstract-title):not(section.abstract):not(.article-metadata-panel):not(.article-metadata-standalone-panel):not(.kwd-group):not(.backreferences-title):not(.ref-list):not(.copyright):not(.reveal-modal):not(.license):not(.authorNotes-section-title):not(.authorNotes-section-title + p):not(.backacknowledgements-title):not(.backacknowledgements-title + p):not(.pdf-notice):not(:has(.footnote-content)):not(.table-modal):not(.widget-FirstPagePreview)
   pdf_a: .article-pdfLink
   corresp_author_names: .info-card-author:has(.info-author-correspondence) .info-card-name
   corresp_author_emails: .info-card-author .info-author-correspondence a, .info-card-author:has(.info-author-correspondence) .info-card-affilitation a[href^=mailto]
@@ -212,9 +212,8 @@ springer:
   keywords: .Keyword, .c-article-subject-list__subject
   abstract: 'section.Abstract > p, #book-description > *, #Abs1-content > p'
   fulltext: '#body > section > *, article div[data-article-body=true] > section > :not(#abstract-section):not(#Abs1-section):not(#references-section):not(#Bib1-section):not(#acknowledgements-section):not(#Ack1-section):not(#author-information-section):not(#author-contribution-section):not(#article-comments-section):not(#rightslink-section):not(#article-info-section):not(#further-reading-section):not(#ethics-section) > *'
-  pdf_a: '.test-pdf-link > :not([id$=no_access_banner]) > a'
-  corresp_author_names: .authors__list li:has(.authors__contact) .authors__name
-  corresp_author_emails: .authors__list li .authors__contact a
+  pdf_a: '.test-pdf-link > :not([id$=no_access_banner]) > a, .c-pdf-download__link'
+  corresp_author_names: .c-author-list a[data-test=author-name]:has(.u-icon)
 
 springer_ref:
   doi: .FulltextWrapper .ChapterDOI
@@ -250,8 +249,8 @@ nature:
   doi: 'h3:has(abbr[title=Digital Object Identifier]) + p > a[data-track-action=view doi], #article-info-section a[data-track-action=view doi]'
   title: 'article header h1, #article #content > .article > h2.article-title'
   keywords: div[data-component=article-subject-links] a[data-track-action=view subject], .c-article-subject-list__subject
-  abstract: 'article div[data-article-body=true] > section > #abstract-section > div > *, article div[data-article-body=true] > section > #Abs1-section > div > *, article div[data-article-body=true] > section > #Abs2-section > div > *, #article #content > .article > #Summary + p'
-  fulltext: 'article div[data-article-body=true] > section > :not(#abstract-section):not(#Abs1-section):not(#Abs2-section):not(#references-section):not(#Bib1-section):not(#acknowledgements-section):not(#Ack1-section):not(#author-information-section):not(#author-contribution-section):not(#article-comments-section):not(#rightslink-section):not(#article-info-section):not(#further-reading-section):not(#ethics-section) > *, article div[data-article-body=true] > div:not(:has(#access-options)):not([aria-hidden=true]):not(.c-pdf-button__container)'
+  abstract: 'article .c-article-body > section > #abstract-section > div > *, article .c-article-body > section > #Abs1-section > div > *, article .c-article-body > section > #Abs2-section > div > *, #article #content > .article > #Summary + p'
+  fulltext: 'article .c-article-body > section > :not(#abstract-section):not(#Abs1-section):not(#Abs2-section):not(#references-section):not(#Bib1-section):not(#acknowledgements-section):not(#Ack1-section):not(#author-information-section):not(#author-contribution-section):not(#article-comments-section):not(#rightslink-section):not(#article-info-section):not(#further-reading-section):not(#ethics-section) > *, article .c-article-body > div:not(:has(#access-options)):not([aria-hidden=true]):not(.c-pdf-button__container)'
   pdf_a: a[data-article-pdf]
   corresp_author_names: .c-author-list a[data-test=author-name]:has(.u-icon)
 
@@ -412,7 +411,7 @@ f1000research_articles:
 f1000research_posters:
   title: .asset-title > h1
   keywords_split: .asset-subcontainer__title:containsOwn(Keywords) + *
-  abstract: .abstract__content
+  abstract: .abstract__content:not(:has(.abstract__content))
   # pdf_a not working (because href="#")
   corresp_author_names: .asset-details-container-large .asset-authors > a
   corresp_author_emails: .asset-details-container-large .asset-authors > a
@@ -468,11 +467,11 @@ acm:
   pdf_a: article .citation a[title=PDF]
 
 degruyter:
-  doi: .article-doi
-  title: h1.entryTitle
-  keywords: .articleBody_keywords > a
-  abstract: .articleBody_abstract > p
-  pdf_a: .gs-access-fullcontentlink .pdf-link
+  doi: dt.c-List__item:matchesOwn(^DOI:$) + dd.c-List__item > a
+  title: '#pageBody h1'
+  keywords: dt.c-List__item:matchesOwn(^Keywords:$) + dd.c-List__item > a
+  abstract: '#pageBody section.abstract > p'
+  pdf_a: '#pdf-download'
 
 hindawi:
   doi: .middle_content pre a[href^=http://dx.doi.org], .article_citation a[aria-label=Doi-link]
@@ -573,9 +572,9 @@ iospress:
   abstract: '#contentcolumn .metadata > .abstract > p'
 
 researchgate:
-  #doi: .publication-details__section > .publication-meta > div:first-child + div
-  title: .publication-header > h1, .publication-details__section > h1
-  abstract: .publication-abstract > :not(:first-child), .publication-details__section > div > div:matches(^Abstract$) + div
+  doi: .research-detail-header-section__metadata > div:matchesOwn(^DOI:) > a
+  title: main h1
+  abstract: main .research-detail-middle-section__abstract
   pdf_a: a:matches(^Download full-text PDF$)
 
 frontiersin:
@@ -649,13 +648,13 @@ mdpi:
   corresp_author_names: .art-authors > span:has(.emailCaptcha) > span > a
 
 mdpi_full:
-  doi: article .html-art-header a
-  title: '#html-article-title'
-  keywords_split: '#html-keywords > div'
-  abstract: '#html-abstract > div'
-  fulltext: 'article > .html-body > section > *, article > .html-back > #html-glossary'
-  pdf_a: article .download > a:matchesOwn(^Download PDF$)
-  corresp_author_names: .html-author-group > span:has(.emailCaptcha) > span > a
+  doi: '#abstract .bib-identity > a'
+  title: '#abstract h1'
+  keywords: '#abstract .art-keywords a'
+  abstract: '#abstract .art-abstract'
+  fulltext: 'article .html-body section > :not(section), article #SupplementaryFiles, article #html-glossary'
+  pdf_a: '#abstract .download > a:matchesOwn(^Download PDF$)'
+  corresp_author_names: .art-authors > span:has(.emailCaptcha) > span > a
 
 preprints:
   title: '#submission-content > h1'
@@ -669,16 +668,16 @@ aip:
   title: .publicationContentTitle > h1
   keywords: .topicList a:matches(^Topics$) + ul > .topicTags
   abstract: article .abstractSection
-  fulltext: .hlFld-Fulltext .NLM_sec > :not(.NLM_sec)
-  pdf_a: .article-menu > .download-pdf a.pdf
+  fulltext: .hlFld-Fulltext .NLM_sec > :not(.NLM_sec):not(.sectionInfo), .hlFld-Fulltext .NLM_sec > .sectionInfo > .sectionHeading
+  pdf_a: .article-menu > .download-pdf a:not(.notVisible)
   corresp_author_names: .entryAuthor > .contrib-author:has(.email) > a[href^=/author/]
   # corresp_author_emails: .entryAuthor > .contrib-author > .email # email-protection
 
 chemrxiv:
-  title: .item-left > h2.title
-  keywords: .item-right > .tags a
-  abstract: .item-left > .description
-  pdf_a: .actions-bar .download-button
+  title: main h2
+  keywords: main h3:matchesOwn(^Keyword\(s\)$) + div > a
+  abstract: main ._1bqUT
+  pdf_a: '#a11y-1-tab-tab-download'
 
 iop:
   doi: '#doi'
@@ -699,7 +698,6 @@ iop:
 - 'ieeexplore\.ieee\.org'
 - 'xlink\.rsc\.org' # for fulltext_a, pdf_a
 - 'pubs\.rsc\.org' # for fulltext_a, pdf_a
-- 'f1000research\.com/+posters'
 
 # highwire2
 - 'mcponline\.org'
diff --git a/core/src/main/resources/scrape/webpages.csv b/core/src/main/resources/scrape/webpages.csv
index ea79349..19abe3f 100644
--- a/core/src/main/resources/scrape/webpages.csv
+++ b/core/src/main/resources/scrape/webpages.csv
@@ -1,25 +1,25 @@
 title,content,license,language,webpage
 
 # bioconductor.org
-9,642,5,8,http://bioconductor.org/packages/release/bioc/html/RIPSeeker.html
-7,835,12,8,https://bioconductor.org/packages/release/bioc/html/biomaRt.html
+9,536,5,0,http://bioconductor.org/packages/release/bioc/html/RIPSeeker.html
+7,878,12,18,https://bioconductor.org/packages/release/bioc/html/biomaRt.html
 9,264,12,18,http://bioconductor.org/packages/release/bioc/html/BiocStyle.html
 8,640,5,28,http://bioconductor.org/packages/release/bioc/html/synapter.html
 10,247,5,8,http://www.bioconductor.org/packages//2.13/bioc/html/DAVIDQuery.html
 
 # bioconductor.org vignettes
-23,54890,0,0,http://bioconductor.org/packages/release/bioc/vignettes/EBImage/inst/doc/EBImage-introduction.html
-69,30057,0,0,http://bioconductor.org/packages/release/bioc/vignettes/IHW/inst/doc/introduction_to_ihw.html
+23,54306,0,0,http://bioconductor.org/packages/release/bioc/vignettes/EBImage/inst/doc/EBImage-introduction.html
+69,30055,0,0,http://bioconductor.org/packages/release/bioc/vignettes/IHW/inst/doc/introduction_to_ihw.html
 
 # git.bioconductor.org
 0,0,0,0,https://git.bioconductor.org/packages/RIVER
 
 # github.com
-7,942,0,11,https://github.com/sgoodswe/vacceed
+7,175,0,11,https://github.com/sgoodswe/vacceed
 4,5887,0,27,https://github.com/SciLifeLab/facs/
-10,10673,7,6,https://github.com/petmri/ROCKETSHIP
-4,1863,3,7,https://github.com/pschorderet/NEAT
-9,422,3,24,https://github.com/arq5x/poretools
+10,10673,15,6,https://github.com/petmri/ROCKETSHIP
+4,1863,11,7,https://github.com/pschorderet/NEAT
+9,422,11,24,https://github.com/arq5x/poretools
 
 # github.com user
 7,1281,0,0,https://github.com/SeqWare
@@ -49,16 +49,17 @@ title,content,license,language,webpage
 4,493,0,0,https://github.com/chapmanb/bcbb/blob/master/nextgen/README.md
 
 # galaxy.pasteur.fr
+# switched off, as requires JavaScript that for this case is too resource intensive for some reason
 # java.lang.NullPointerException: JavascriptThread has not created a Document!
-0,0,0,0,https://galaxy.pasteur.fr/tool_runner?tool_id=toolshed.pasteur.fr/repos/odoppelt/taxonomy_analysis/taxoptimizer/0.0.2
-100,1845,0,0,https://galaxy.pasteur.fr/root?tool_id=aggregate_scores_in_intervals2
-85,1425,0,0,https://galaxy.pasteur.fr/root?tool_id=clustalw
-50,187,0,0,https://galaxy.pasteur.fr/root?tool_id=toolshed.g2.bx.psu.edu%2Frepos%2Fdevteam%2Fbam_to_sam%2Fbam_to_sam%2F1.0.3
-88,2368,0,0,https://galaxy.pasteur.fr/root?tool_id=toolshed.pasteur.fr%2Frepos%2Fafelten%2Fmicrobiome_analyses%2FCD-HIT%2F4.6.1
+#0,0,0,0,https://galaxy.pasteur.fr/tool_runner?tool_id=toolshed.pasteur.fr/repos/odoppelt/taxonomy_analysis/taxoptimizer/0.0.2
+#100,1845,0,0,https://galaxy.pasteur.fr/root?tool_id=aggregate_scores_in_intervals2
+#85,1425,0,0,https://galaxy.pasteur.fr/root?tool_id=clustalw
+#50,187,0,0,https://galaxy.pasteur.fr/root?tool_id=toolshed.g2.bx.psu.edu%2Frepos%2Fdevteam%2Fbam_to_sam%2Fbam_to_sam%2F1.0.3
+#88,2368,0,0,https://galaxy.pasteur.fr/root?tool_id=toolshed.pasteur.fr%2Frepos%2Fafelten%2Fmicrobiome_analyses%2FCD-HIT%2F4.6.1
 # java.lang.NullPointerException: JavascriptThread has not created a Document!
-0,0,0,0,https://galaxy.pasteur.fr/root?tool_id=toolshed.pasteur.fr/repos/khillion/salmonella_crispr_typing/salmonella_crispr_typing/1.0.0
-75,774,0,0,https://galaxy.pasteur.fr/root?tool_id=vcf_intersect
-101,73,0,0,https://galaxy.pasteur.fr/tool_runner?tool_id=CONVERTER_genbank_to_fasta
+#0,0,0,0,https://galaxy.pasteur.fr/root?tool_id=toolshed.pasteur.fr/repos/khillion/salmonella_crispr_typing/salmonella_crispr_typing/1.0.0
+#75,774,0,0,https://galaxy.pasteur.fr/root?tool_id=vcf_intersect
+#101,73,0,0,https://galaxy.pasteur.fr/tool_runner?tool_id=CONVERTER_genbank_to_fasta
 
 # emboss.open-bio.org
 # begins wrongly with "The master copies of EMBOSS documentation are available at on the EMBOSS Wiki."
@@ -98,7 +99,7 @@ title,content,license,language,webpage
 87,412,5,0,https://cran.r-project.org/web/packages/linkcomm/index.html
 54,373,5,0,https://cran.r-project.org/web/packages/lme4/index.html
 39,163,5,0,https://cran.r-project.org/web/packages/GUniFrac/index.html
-0,4421,0,0,https://cran.r-project.org/web/packages/linkcomm/NEWS
+0,4484,0,0,https://cran.r-project.org/web/packages/linkcomm/NEWS
 
 # cran.r-project.org vignettes
 25,29820,0,0,https://cran.r-project.org/web/packages/pergola/vignettes/my-vignette.html
@@ -122,13 +123,8 @@ title,content,license,language,webpage
 0,0,0,0,https://bitbucket.org/paiyetan/xglycscan/src
 
 # sanger.ac.uk
-7,233,0,0,http://www.sanger.ac.uk/science/tools/artemis
-22,888,0,0,http://www.sanger.ac.uk/science/tools/ssahasnp
-
-# dna.leeds.ac.uk
-21,1465,0,0,http://dna.leeds.ac.uk/AffyErrorRate/
-14,1519,0,0,http://dna.leeds.ac.uk/agile/AgileGenotyper/
-12,1762,0,0,http://dna.leeds.ac.uk/methylviewer/
+7,468,392,0,http://www.sanger.ac.uk/science/tools/artemis
+8,1772,699,0,http://www.sanger.ac.uk/science/tools/ssahasnp
 
 # tools.proteomecenter.org
 14,1004,0,0,http://tools.proteomecenter.org/Libra.php
@@ -143,7 +139,7 @@ title,content,license,language,webpage
 
 # zhanglab.ccmb.med.umich.edu
 47,776,0,0,https://zhanglab.ccmb.med.umich.edu/BSpred/
-79,3568,0,0,https://zhanglab.ccmb.med.umich.edu/EvoDesign/
+79,3747,0,0,https://zhanglab.ccmb.med.umich.edu/EvoDesign/
 
 # bioinformatics.mdanderson.org
 10,1261,6,4,http://bioinformatics.mdanderson.org/main/BreakTrans
@@ -152,17 +148,13 @@ title,content,license,language,webpage
 6,302,19,0,https://www.bcgsc.ca/resources/software/anchor
 
 # compomics.github.io
-13,12795,0,0,https://compomics.github.io/projects/peptide-shaker.html
+13,13547,0,0,https://compomics.github.io/projects/peptide-shaker.html
 8,397,0,0,http://compomics.github.io/projects/reporter.html
 
 # rostlab.org wiki
-7,8025,0,0,https://rostlab.org/owiki/index.php/CHOPPER
+7,8021,0,0,https://rostlab.org/owiki/index.php/CHOPPER
 10,1450,0,0,https://rostlab.org/owiki/index.php/Uniqueprot
 
-# uea.ac.uk
-5,3042,0,0,https://www.uea.ac.uk/computing/psiko
-10,2306,0,0,http://www.uea.ac.uk/computing/my-closure
-
 # rna.informatik.uni-freiburg.de
 25,3437,0,0,http://rna.informatik.uni-freiburg.de/CopraRNA/Input.jsp
 27,2231,0,0,http://rna.informatik.uni-freiburg.de/MARNA/Input.jsp
@@ -174,7 +166,7 @@ title,content,license,language,webpage
 
 # pypi.org
 16,779,26,6,https://pypi.python.org/pypi/omics_pipe
-13,1963,35,69,http://pypi.python.org/pypi/plastid
+13,2311,35,97,http://pypi.python.org/pypi/plastid
 17,69,48,11,https://pypi.org/project/bio-apricot/
 
 # bioinformatics.org wiki
diff --git a/core/src/main/resources/scrape/webpages.yaml b/core/src/main/resources/scrape/webpages.yaml
index f947d79..7bdd9b5 100644
--- a/core/src/main/resources/scrape/webpages.yaml
+++ b/core/src/main/resources/scrape/webpages.yaml
@@ -50,9 +50,9 @@
 
 'github\.com/+[^/]+/+[^/]+/*$':
   title: h1 > [itemprop=name]
-  content: '.repository-content [itemprop=about], #readme > .Box-body > * > *'
-  license: .numbers-summary a:has(.octicon-law):not(:matches(^View license$))
-  language: .repository-lang-stats-numbers a:has(.percent:matchesOwn(^(100|[1-9][0-9]|[5-9])\.[0-9]%$)) > .lang # only take languages with percentage >= 5%
+  content: '.BorderGrid-cell > h2:matchesOwn(^About$) + p, #readme > .Box-body > * > *'
+  license: a:has(.octicon-law):not(:matches(^View license$))
+  language: a[href~=/search\?l=]:has(span:matchesOwn(^(100|[1-9][0-9]|[5-9])\.[0-9]%$)) > span.text-bold
 
 'github\.com/+[^/]+/*$':
   title: h1
@@ -60,7 +60,7 @@
 
 'github\.com/+[^/]+/+[^/]+/+wiki(/|$)':
   title: h1 > [itemprop=name]
-  content: 'h1.gh-header-title, #wiki-body > :not(#wiki-footer), #wiki-rightbar #wiki-pages-box a, #wiki-rightbar .wiki-custom-sidebar'
+  content: 'h1.gh-header-title, #wiki-body > :not(#wiki-footer), .wiki-rightbar #wiki-pages-box a, .wiki-rightbar .wiki-custom-sidebar'
 
 'github\.com/+[^/]+/+[^/]+/+tree/':
   title: h1 > [itemprop=name]
@@ -77,7 +77,7 @@
 'galaxy\.pasteur\.fr/+(root|tool_runner)':
   title: '#center .portlet-title-text'
   content: '#center .portlet-body .ui-form-title-text, #center .ui-form-help'
-  javascript: 'true'
+  javascript: 'false' # too resource intensive
 
 'emboss\.open-bio\.org/+rel/':
   title: body > :first-child
@@ -130,12 +130,9 @@
 #  javascript: 'true'
 
 'sanger\.ac\.uk':
-  title: '#main-content > .pagetitle'
-  content: '#overview > :not(h4), .view-tool-type a'
-
-'dna\.leeds\.ac\.uk':
-  title: '#content > h1'
-  content: '#content > :not(h1)'
+  title: '#main .panel-outer h2'
+  content: '#main .panel-outer .button-container a, #main .panel-outer .intro'
+  license: '#main .panel-outer label:matchesOwn(^License and Citation$) + div'
 
 'tools\.proteomecenter\.org':
   title: h1.firstHeading
@@ -169,10 +166,6 @@
   title: h1.firstHeading
   content: '#mw-content-text > :not(#toc)'
 
-'uea\.ac\.uk':
-  title: '#breadcrumbs li.last > a'
-  content: .journal-content-article
-
 'rna\.informatik\.uni-freiburg\.de':
   title: .content > h1
   content: .content > :not(h1):not(.footer)
@@ -250,3 +243,9 @@
 # Results in java.lang.StackOverflowError after ~1.5 minutes
 'seltarbase\.org':
   javascript: 'false'
+
+'who\.int':
+  javascript: 'false'
+
+'ncbi\.nlm\.nih\.gov':
+  javascript: 'false'
diff --git a/core/src/main/resources/test/europepmc-xml.csv b/core/src/main/resources/test/europepmc-xml.csv
index a653c5e..648a5fc 100644
--- a/core/src/main/resources/test/europepmc-xml.csv
+++ b/core/src/main/resources/test/europepmc-xml.csv
@@ -3,7 +3,7 @@ id,pmid,pmcid,doi,title,keywords,abstract,fulltext,corresp,journal
 # keywords
 PMC3131510,0,10,25,133,6,1474,74547,70,42
 PMC5123367,0,10,25,110,5,952,34856,40,26
-PMC3608327,8,10,22,57,4,1539,54438,42,38
+PMC3608327,8,10,22,57,4,1539,54439,42,38
 PMC5210299,0,10,25,61,3,1153,31801,86,18
 
 # abstract
@@ -39,7 +39,7 @@ PMC1142402,8,10,18,100,0,1369,48472,54,22
 PMC2730554,0,10,32,105,5,905,50952,45,16
 PMC2784320,8,10,26,89,0,696,34874,36,14
 PMC3775632,0,10,17,85,7,1169,32969,66,5
-PMC4300491,8,10,21,117,4,1595,62121,113,25
+PMC4300491,8,10,21,117,4,1595,62122,113,25
 PMC4829337,8,10,29,109,10,1539,13365,34,11
 PMC5180080,8,10,21,74,0,0,10424,36,30
 
diff --git a/core/src/main/resources/test/oadoi.csv b/core/src/main/resources/test/oadoi.csv
index 7aaf8a2..cf0fc25 100644
--- a/core/src/main/resources/test/oadoi.csv
+++ b/core/src/main/resources/test/oadoi.csv
@@ -13,22 +13,20 @@ doi,oa,links,title,journal
 
 # 1 link
 10.1101/gr.6861907,1,1,139,15
-10.1186/1471-2105-15-S11-S10,1,1,86,18
 10.1107/S0907444910045749,1,1,50,59
-10.3389/fgene.2012.00035,1,1,110,21
 10.6019/tol.eva-w.2016.00001.1,1,1,47,0
+10.1073/pnas.1523899113,1,1,97,47
+
+# 2 links
+10.1186/1471-2105-15-S11-S10,1,2,86,18
+10.1371/journal.pone.0167047,1,2,92,8
+10.1214/10-AOAS338,1,2,89,32
 
 # 3 links
+10.3389/fgene.2012.00035,1,3,110,21
 10.1093/nar/gks1246,1,3,109,22
-10.1073/pnas.1523899113,1,3,97,47
-10.1371/journal.pone.0167047,1,3,92,8
 
-# 4 links
+# 4 or more links
 10.1038/nature12373,1,4,44,6
-10.1214/10-AOAS338,1,4,89,32
-
-# 5 links
 10.3897/BDJ.4.e8740,1,5,104,25
-
-# 8 links
 10.1371/journal.pgen.1002453,1,8,60,13
diff --git a/core/src/main/resources/test/pubmed-html.csv b/core/src/main/resources/test/pubmed-html.csv
index dba5f6f..b330fd8 100644
--- a/core/src/main/resources/test/pubmed-html.csv
+++ b/core/src/main/resources/test/pubmed-html.csv
@@ -1,18 +1,18 @@
 id,pmid,pmcid,doi,title,keywords,mesh,abstract
 
 # subtitle
-11598180,8,8,22,28,0,21,1303
+11598180,8,8,22,27,0,21,1303
 
 # keywords
-27942268,8,10,25,111,5,0,951
-28049428,8,10,25,62,3,6,943
-27140611,8,10,23,100,5,13,930
+27942268,8,10,25,110,5,0,951
+28049428,8,10,25,61,3,6,977
+27140611,8,10,23,99,5,13,930
 
 # abstract
 #27942268
 #28049428
-20161787,8,10,28,78,0,15,1584
-17973982,8,10,23,80,0,7,2305
+20161787,8,10,28,77,0,15,1654
+17973982,8,10,23,79,0,7,2338
 
 # no abstract
-24727771,8,10,16,91,0,10,0
+24727771,8,10,16,90,0,10,0