diff --git a/constants/bad_data.php b/constants/bad_data.php
index 7ad055c57a..c078536927 100644
--- a/constants/bad_data.php
+++ b/constants/bad_data.php
@@ -5,56 +5,56 @@
 // Some data we get from outside sources is bad or at least mis-defined
 // Use lower case for all of these, and then compare to a lower cased version
 const HAS_NO_VOLUME = [
-    'zookeys',
-    'studia hibernica',
+    'american museum novitates',
     'analecta hibernica',
+    'balcanica',
     'british art studies',
-    'der spiegel',
-    'international astronomical union circular',
-    'yale french studies',
-    'capjournal',
     'cap journal',
-    'phytokeys',
-    'starinar',
-    'balcanica',
-    'american museum novitates',
+    'capjournal',
+    'der spiegel',
     'european journal of taxonomy',
+    'international astronomical union circular',
     'international journal of the sociology of language',
     'mycokeys',
     'past & present',
     'past and present',
+    'phytokeys',
+    'starinar',
+    'studia hibernica',
+    'yale french studies',
+    'zookeys',
 ]; // Some journals have issues only, no volume numbers
 // oceanic linguistics special publications has the problem that issues will not show up within temlpates
 const HAS_NO_ISSUE = [
-    'special papers in palaeontology',
-    'oceanic linguistics special publications',
+    'archaeological reports',
+    'ars orientalis',
     'cahiers balkaniques',
+    'oceanic linguistics special publications',
     'res historica',
-    'archaeological reports',
-    "cahiers d'extrême-asie",
+    'special papers in palaeontology',
     "bulletin de l'ecole française d'extrême-orient",
-    'ars orientalis',
+    "cahiers d'extrême-asie",
 ]; // Some journals have volumes only, no issue numbers
 const PREFER_VOLUMES = ['illinois classical studies']; // When issue=volume, drop issue.  JSTOR calls volumes issues
 const PREFER_ISSUES = [
-    'mammalian species',
     'bulletin of the united states national museum',
+    'mammalian species',
 ];
 const CONFERENCE_LIST = [
-    'Proceedings of Advancing Astrophysics',
-    'International Cosmic Ray Conference',
+    ' of the Association for ',
     'Annual Meeting of the Association',
+    'International Cosmic Ray Conference',
+    'Proceedings of Advancing Astrophysics',
     'Proceedings of the ',
-    ' of the Association for ',
 ];
 const BAD_ACCEPTED_MANUSCRIPT_TITLES = [
+    '[placeholder]',
+    'article not found',
     'oup accepted manuscript',
+    'placeholder for arabic language transliteration',
     'placeholder for bad pdf file',
     'placeholder',
     'symbolic placeholder',
-    '[placeholder]',
-    'placeholder for arabic language transliteration',
-    'article not found',
 ];
 const BAD_AUTHORS = [
     '- -.',
@@ -158,140 +158,140 @@
 ];
 
 const ARE_WORKS = [
-    'medrxiv',
     'ietf datatracker',
+    'medrxiv',
 ]; // Things with dois that should be {{cite document|work=THIS}}
 
 const PUBLISHERS_ARE_WORKS = [
-    'the san diego union-tribune',
-    'forbes',
-    'salon',
-    'san jose mercury news',
-    'san jose mercury-news',
-    'new york times',
-    'the new york times',
+    '[[forbes]] (Russia)',
+    'anchorage daily news',
+    'arizona daily star',
+    'belmontstakes.com',
+    'birmingham post',
+    'cbs sports',
+    'daily news (new york)',
+    'daily news & analysis',
+    'daily news and analysis',
+    'daily news egypt',
+    'daily news latino',
     'daily news online',
+    'daily news, sri lanka',
     'daily news',
-    'the sun',
-    'the times',
-    'the star',
-    'washington post',
-    'the washington post',
-    'the tribune',
-    'los angeles times',
-    'la times',
-    'the la times',
-    'htmlgiant',
-    'the los angeles times',
-    'sandiegouniontribune.com',
-    'forbes.com',
-    'salon.com',
-    'mercurynews.com',
-    'nytimes.com',
-    'thedailynewsonline.com',
-    'thesun.com',
-    'thetimes.com',
-    'thestar.com',
-    'washingtonpost.com',
-    'thetribune.com',
-    'latimes.com',
-    'htmlgiant.com',
-    'the guardian',
-    'fox sports',
-    'mlb.com',
     'espn.com',
+    'findlaw.com',
+    'findlaw',
+    'fixtures live',
+    'forbes afrique',
+    'forbes asia',
+    'forbes china',
+    'forbes contributor blogs',
+    'forbes global 2000',
+    'forbes india',
+    'forbes israel',
+    'forbes magazine',
     'forbes media',
+    'forbes mexico',
+    'forbes méxico',
+    'forbes middle east',
     'forbes online',
-    'cbs sports',
-    'national journal',
+    'forbes russia',
+    'forbes viet nam',
+    'forbes việt nam',
+    'forbes vietnam',
+    'forbes.com',
+    'forbes.ru',
+    'forbes',
+    'forbesmiddleeast',
+    'fox sports',
     'foxnews',
-    'the hill',
+    'foxsports.com',
+    'htmlgiant.com',
+    'htmlgiant',
+    'india glitz',
+    'indiaglitz.com',
+    'indiaglitz',
+    'international business times',
+    'la times',
+    'latimes.com',
+    'los angeles times',
+    'mercurynews.com',
+    'mlb.com',
+    'national journal',
     'nationaljournal.com',
-    'the huffington post',
-    'the times digital archive',
-    'belmontstakes.com',
-    'the times archives',
+    'nba.com',
+    'new york daily news',
+    'new york daily news',
+    'new york times magazine',
     'new york times.com',
+    'new york times',
     'news shopper',
-    'birmingham post',
-    'the independent',
+    'newsmax',
+    'nfl.com',
+    'nytimes.com',
+    'oneindia',
+    'palm beach daily news',
+    'philippine information agency',
+    'philippine news agency',
+    'pia.gov.ph',
     'rediff.com',
+    'salon.com',
+    'salon',
+    'san diego union tribune',
+    'san jose mercury news',
+    'san jose mercury-news',
+    'sandiegouniontribune.com',
     'squashplayer.co.uk',
-    'fixtures live',
-    'the star online',
-    'oneindia',
-    'international business times',
+    'stripes',
+    'the baltimore sun',
+    'the daily news egypt',
+    'the guardian',
+    'the hill',
     'the hindu',
-    'daily news and analysis',
-    'nfl.com',
-    'foxsports.com',
+    'the huffington post',
+    'the independent',
+    'the la times',
+    'the los angeles times',
+    'the new york times',
     'the new yorker',
-    'findlaw.com',
-    'newsmax',
-    'washtimes.com',
-    'washington times',
-    'findlaw',
-    'new york times magazine',
-    'stripes',
-    'arizona daily star',
+    'the san diego union-tribune',
+    'the star (malaysia)',
+    'the star online',
+    'the star',
+    'the sun',
+    'the times archives',
+    'the times digital archive',
     'the times of india',
     'the times-news',
-    'san diego union tribune',
-    'the star (malaysia)',
+    'the times',
+    'the tribune',
+    'the washington post',
+    'thedailynewsonline.com',
+    'thestar.com',
+    'thesun.com',
+    'thetimes.com',
+    'thetribune.com',
     'utusan malaysia',
-    'daily news, sri lanka',
-    'daily news & analysis',
-    'new york daily news',
-    'new york daily news',
-    'daily news (new york)',
-    'anchorage daily news',
-    'palm beach daily news',
-    'daily news egypt',
-    'the daily news egypt',
-    'daily news latino',
-    'forbes méxico',
-    'forbes mexico',
-    'forbes india',
-    'forbesmiddleeast',
-    'forbes middle east',
-    'forbes russia',
-    'forbes.ru',
-    'forbes afrique',
-    'forbes magazine',
-    'forbes asia',
-    'forbes israel',
-    'forbes global 2000',
-    'forbes china',
-    '[[forbes]] (Russia)',
-    'forbes việt nam',
-    'forbes vietnam',
-    'forbes viet nam',
-    'forbes contributor blogs',
-    'the baltimore sun',
-    'nba.com',
-    'philippine news agency',
+    'washington post',
+    'washington times',
+    'washingtonpost.com',
+    'washtimes.com',
     'www.pna.gov.ph',
-    'pia.gov.ph',
-    'philippine information agency',
-    'indiaglitz',
-    'india glitz',
-    'indiaglitz.com',
     // WP:CITALICSRFC and MOS:ITALICWEBCITE  ?????    'abc news'  'nbc news', 'cbs news', 'bbc news'
 ]; // LOWER CASE!  WWW not there too!
 
 const WORKS_ARE_PUBLISHERS = ['united states census bureau']; // LOWER CASE!
 
 const DUBIOUS_JOURNALS = [
-    'oup academic',
-    'fda',
-    'reuters',
-    'associated press',
-    'ap',
     'ap wire',
-    'report',
+    'ap',
+    'associated press',
+    'fda',
+    'national institute of standards and technology',
     'nist',
+    'oup academic',
+    'report',
+    'reuters',
     'tumblr',
-    'national institute of standards and technology',
 ]; // Things we add, but only if publisher and agency are both blank
 
 // Catch so-called authors such as hearst magazines, time inc, nielsen business media, inc
@@ -312,186 +312,229 @@
     'science',
 ];
 const BAD_TITLES = [
-    'unknown',
-    'missing',
-    'arxiv e-prints',
-    'arxiv mathematics e-prints',
-    'ssrn electronic journal',
+    '403 unauthorized',
+    '404 not found',
+    '404',
+    '404错误',
+    '404页面',
+    'arxiv e-prints',
+    'arxiv mathematics e-prints',
+    'bloomberg - are you a robot?',
+    'breaking news, analysis, politics, blogs, news photos, video, tech reviews - time.com',
+    'breaking news, analysis, politics, blogs, news photos, video, tech reviews',
+    'cur_title',
+    'digital library - pdf document',
     'dissertations available from proquest',
+    'download limit exceeded',
     'ebscohost login',
-    'library login',
+    'economics working paper archive',
+    'error - lexisnexis® publisher',
+    'error',
+    'explore census data',
+    'free live sex cams',
+    'google book',
+    'google books',
     'google groups',
-    'sciencedirect',
-    'cur_title',
-    'wordpress › error',
-    'ssrn temporarily unavailable',
+    'index of /home',
+    'internal server error',
+    'just a moment',
+    'library login',
+    'loading',
     'log in - proquest',
-    'shibboleth authentication request',
+    'missing',
+    'msn',
     'nookmarkable url intermediate page',
-    'google books',
-    'rte.ie',
-    'loading',
-    'google book',
-    'just a moment',
-    'the article you have been looking for has expired and is not longer available on our system. this is due to newswire licensing terms.',
     'openid transaction in progress',
-    'download limit exceeded',
+    'optica publishing group',
+    'oxford music online',
+    'page not found',
+    'pagina inicia',
     'privacy settings',
-    'untitled-1',
-    'untitled-2',
     'professional paper',
-    'zbmath',
-    'economics working paper archive',
-    'theses and dissertations available from proquest',
     'proquest ebook central',
-    'report',
-    'bloomberg - are you a robot?',
-    'page not found',
-    'free live sex cams',
-    'breaking news, analysis, politics, blogs, news photos, video, tech reviews',
-    'breaking news, analysis, politics, blogs, news photos, video, tech reviews - time.com',
     'redirect notice',
-    'oxford music online',
-    'trove - archived webpage',
-    'pagina inicia',
-    '404 not found',
-    '404页面',
+    'redirecting',
+    'report',
+    'request rejected',
+    'rte.ie',
+    'sciencedirect',
+    'shibboleth authentication request',
     'sign up ',
-    'index of /home',
+    'ssrn electronic journal',
+    'ssrn temporarily unavailable',
+    'the article you have been looking for has expired and is not longer available on our system. this is due to newswire licensing terms.',
+    'theses and dissertations available from proquest',
+    'trove - archived webpage',
+    'unknown',
+    'untitled-1',
+    'untitled-2',
     'usa today - today\'s breaking news, us & world news',
-    '403 unauthorized',
-    '404错误',
-    'internal server error',
-    'error',
-    '404',
-    'error - lexisnexis® publisher',
-    'optica publishing group',
-    'digital library - pdf document',
-    'explore census data',
-    'msn',
-    'request rejected',
-    'redirecting',
+    'wordpress › error',
+    'zbmath',
 ];
 const IN_PRESS_ALIASES = [
+    'forthcoming',
     'in press',
+    'in the press',
     'inpress',
-    'pending',
-    'published',
-    'published online',
-    'no-no',
+    'missing',
     'n/a',
-    'online ahead of print',
-    'unpublished',
-    'unknown',
-    'tba',
-    'forthcoming',
-    'in the press',
     'na',
+    'no-no',
+    'online ahead of print',
+    'pending',
+    'published online',
+    'published',
     'submitted',
+    'tba',
     'tbd',
-    'missing',
+    'unknown',
+    'unpublished',
 ];
 const NON_JOURNAL_BIBCODES = [
+    'alg.geom',
     'arXiv',
+    'astro.ph',
+    'cond.mat',
+    'cs.',
+    'econ.',
+    'eess.',
     'gr.qc',
     'hep.ex',
     'hep.lat',
     'hep.ph',
     'hep.th',
-    'astro.ph',
     'math',
+    'nlin.',
     'nucl.ex',
     'nucl.th',
     'physics',
     'quant.ph',
-    'alg.geom',
-    'cond.mat',
-    'cs.',
-    'econ.',
-    'eess.',
-    'nlin.',
 ];
 const NON_PUBLISHERS = [
+    'archive.fo',
+    'archive.org',
+    'archive.today',
     'books.google',
+    'citeseerx.ist.psu.edu',
+    'google book',
     'google books',
     'google news',
     'google.co',
-    'google book',
-    'zenodo',
-    'archive.org',
-    'citeseerx.ist.psu.edu',
-    'archive.fo',
-    'archive.today',
     'hdl.handle.net',
     'pub med',
     'researchgate',
+    'zenodo',
 ]; // Google Inc is a valid publisher, however.
 const BAD_ZOTERO_TITLES = [
-    'Browse publications',
-    'Central Authentication Service',
-    'http://',
-    'https://',
-    'ZbMATH - the first resource for mathematics',
-    'MR: Matches for:',
+    ' has expired',
     ' Log In',
-    'Log In ',
-    'Sign in',
-    'Bookmarkable URL intermediate page',
-    'Shibboleth Authentication Request',
-    'domain for sale',
-    'website for sale',
-    'domain is for sale',
-    'website is for sale',
-    'lease this domain',
-    'domain available',
-    'metaTags',
-    'An Error Occurred',
-    'User Cookie',
-    'Cookies Disabled',
-    'page not found',
-    '411 error',
-    'url not found',
-    'limit exceeded',
-    'Error Page',
-    '}}',
-    '{{',
-    'EU Login',
-    'bad gateway',
-    'Captcha',
+    ' Stranica nije pronađena',
+    '..::.. Error',
     '.com',
     '.gov',
     '.org',
-    'View PDF',
-    'Wayback Machine',
-    'does not exist',
-    'Subscribe to read',
-    'Wiley Online Library',
-    'pagina is niet gevonden',
-    'Zoeken in over NA',
-    'na een 404',
+    '{{',
+    '}}',
+    '404 - - ',
+    '404 - ',
+    '404 - File or directory not found',
+    '404 - Not Found',
+    '404 - Page Not Found',
+    '404 - URL invalid',
+    '404 | ',
+    '404 | ',
     '404 error',
+    '404 ERROR',
+    '404 Error',
+    '404 Not Found',
+    '404 Page - ',
+    '404 Page',
+    '404: Page Not Found ',
+    '404: PAGE NOT FOUND',
+    '404!',
+    '404. That\'s an error',
+    '404. The page',
+    '404. The URL',
+    '404エラ',
+    '404页面',
+    '411 error',
+    '500 Internal Server Error',
+    'Aanmelden bij Facebook',
+    'Aanmelden of registreren om te bekijken',
     'Account Suspended',
+    'An Error Has Occured',
+    'an error has occurred',
+    'An error occured',
+    'An Error Occurred',
+    'Are you a robot',
+    'Article expired',
+    'bad gateway',
+    'being redirected',
+    'bluehost.com',
+    'Bookmarkable URL intermediate page',
+    'Browse publications',
+    'Captcha',
+    'Central Authentication Service',
+    'Compare Payday Loans',
+    'Connecting to the iTunes Store',
+    'cookie settings',
+    'Cookies Disabled',
+    'De pagina is niet gevonden',
+    'Document unavailable',
+    'does not exist',
+    'domain available',
+    'domain for sale',
+    'domain is for sale',
+    'DomainMarket.com',
+    'Download Limit Exceeded',
+    'DPG Media Privacy Gate',
+    'EBSCOhost Login',
+    'Einloggen',
     'Error 404',
+    'Error Page',
+    'EU Login',
     'EZProxy',
-    'EBSCOhost Login',
-    '404 - Not Found',
-    '404!',
-    'Temporarily Unavailable',
-    ' has expired',
+    'Find the Best Loan Deal',
+    'has been registered',
+    'has now officially closed',
+    'Help Center - The Arizona Republic',
+    'http://',
+    'https://',
+    'Internet Archive Wayback Machine',
+    'lease this domain',
+    'limit exceeded',
+    'Log In ',
+    'Login • Instagram',
+    'metaTags',
+    'Missing page',
+    'MR: Matches for:',
+    'na een 404',
     'not longer available',
-    'Article expired',
-    'This is due to newswire licensing terms',
-    'DPG Media Privacy Gate',
     'OpenId transaction in progress',
-    'Download Limit Exceeded',
-    'Internet Archive Wayback Machine',
-    'Url（アドレス）が変わりました',
-    '404エラ',
-    'お探しのページは見つかりませんでした',
+    'Page non trouvée',
+    'page not found',
+    'Page Not Found',
+    'Pagina inicia',
+    'pagina is niet gevonden',
+    'Página não existe',
+    'Página no encontrada',
+    'Preview unavailable',
     'privacy settings',
-    'cookie settings',
-    'WebCite query',
-    'Ой!',
+    'register to view',
+    'Seite nicht gefunden',
+    'sex cams',
+    'Shibboleth Authentication Request',
+    'ShieldSquare',
+    'Sign in',
+    'Sign up | LinkedIn',
+    'Subscribe to read',
+    'subscriber to read',
+    'Temporarily Unavailable',
+    'The Times & the Sunday Times',
+    'The-star.co.kr',
+    'This is due to newswire licensing terms',
+    'This is not the page you requested',
     'Untitled-1',
     'Untitled-2',
     'Untitled-3',
@@ -501,92 +544,50 @@
     'Untitled-7',
     'Untitled-8',
     'Untitled-9',
-    'Are you a robot',
-    'Aanmelden of registreren om te bekijken',
-    'register to view',
-    'being redirected',
-    'has been registered',
-    'Aanmelden bij Facebook',
-    'Einloggen',
-    'The Times & the Sunday Times',
-    'Login • Instagram',
-    'subscriber to read',
-    'has now officially closed',
-    'An Error Has Occured',
-    'an error has occurred',
+    'url not found',
+    'Url（アドレス）が変わりました',
+    'User Cookie',
+    'Validate User',
+    'View PDF',
+    'wasn\'t found on this server',
+    'Wayback Machine',
+    'WebCite query',
+    'website for sale',
+    'website is for sale',
+    'Wiley Online Library',
     'YouTube, a Google company',
-    'Seite nicht gefunden',
-    'Página no encontrada',
+    'ZbMATH - the first resource for mathematics',
+    'Zoeken in over NA',
+    'Ой!',
+    'страница не найдена',
     'الصفحة غير موجودة',
+    'お探しのページは見つかりませんでした',
     '找不到网页',
-    'страница не найдена',
-    'Page non trouvée',
-    'An error occured',
-    'Compare Payday Loans',
-    'Find the Best Loan Deal',
-    '..::.. Error',
-    'Pagina inicia',
-    'Help Center - The Arizona Republic',
-    '404 ERROR',
-    '404 - URL invalid',
-    '404. That\'s an error',
-    '404 - Page Not Found',
-    'Página não existe',
-    'This is not the page you requested',
-    'Page Not Found',
-    '404 - - ',
-    'sex cams',
-    '404 | ',
-    'Missing page',
-    '404 - File or directory not found',
     '错误页面',
-    '404 Page - ',
-    '404: Page Not Found ',
-    '404: PAGE NOT FOUND',
-    '404 Error',
-    '404 | ',
     '页面不存在',
-    'De pagina is niet gevonden',
-    '404 - ',
-    ' Stranica nije pronađena',
-    '404 Page',
-    '404. The page',
-    'wasn\'t found on this server',
-    '404. The URL',
-    'ShieldSquare',
-    '404 Not Found',
-    '404页面',
-    'Sign up | LinkedIn',
-    'The-star.co.kr',
-    'Connecting to the iTunes Store',
-    '500 Internal Server Error',
-    'DomainMarket.com',
-    'bluehost.com',
-    'Validate User',
-    'Document unavailable',
-    'Preview unavailable',
 ];
 
 const CANONICAL_PUBLISHER_URLS = [
+    '-ezproxy.',
     '.acm.org',
-    'archivespp.pl',
-    'radicalphilosophy.com',
+    '.ebscohost.com',
     '.erudit.org',
-    'metropolitics.org',
-    'metropolitiques.eu',
-    'revistas.upr.edu',
-    '.tci-thaijo.org',
-    'tidsskrift.dk',
-    'observatoria.rsl.ru',
-    'britishartstudies.ac.uk',
+    '.ezproxy.',
     '.oup.com',
+    '.serialssolutions.com',
+    '.tci-thaijo.org',
+    '/ezproxy.',
     'academic.oup.com',
     'aeaweb.org',
     'aip.scitation.org',
     'amjbot.org',
     'annualreviews.org',
+    'arc.aiaa.org',
+    'archivespp.pl',
     'biomedcentral.com',
+    'bmcr.brynmawr.edu',
     'bmj.com/cgi/pmidlookup',
+    'britishartstudies.ac.uk',
     'cambridge.org',
     'cell.com',
     'chestjournal.org',
@@ -618,22 +619,27 @@
     'jwildlifedis.org',
     'macmillan.com',
     'mdpi.com',
+    'metropolitics.org',
+    'metropolitiques.eu',
     'msptm.org',
+    'muse.jhu.edu',
     'nature.com',
     'nrcresearchpress.',
+    'observatoria.rsl.ru',
     'pnas.org',
+    'proxy.lib.',
+    'proxy.libraries',
     'psyche.entclub.org',
     'psycnet.apa.org',
     'publications.aap.org',
     'pubs.geoscienceworld.org',
-    'muse.jhu.edu',
     'pubs.rsc.org',
-    'xlink.rsc.org',
+    'pyglobal.com',
+    'radicalphilosophy.com',
+    'revistas.upr.edu',
     'sagepub.com',
     'sagepublications.com',
     'scholarpedia.org',
-    'arc.aiaa.org',
-    'bmcr.brynmawr.edu',
     'schweizerbart.de',
     'scielo.br',
     'scielo.org',
@@ -641,22 +647,16 @@
     'sciencemag.org',
     'springer.com',
     'tandfonline.com',
-    'pyglobal.com',
     'taylorandfrancis.com',
     'thelancet.com',
+    'tidsskrift.dk',
     'vertpala.ac.cn',
     'wiley.com',
     'wjgnet.com',
     'worldscientific.com',
+    'xlink.rsc.org',
     //  Below are journal search engines
-    '.serialssolutions.com',
-    '.ebscohost.com',
     //  Below are proxys
-    'proxy.libraries',
-    'proxy.lib.',
-    '.ezproxy.',
-    '-ezproxy.',
-    '/ezproxy.',
     //  Below are sites that are simply DOI resolvers, like dx.doi.org
     'doi.library.ubc.ca',
 ];
@@ -665,359 +665,359 @@
     'digitalcommons.colby.edu',
     'ecommons.luc.edu',
     'hal.science',
+    'numdam.org',
     'perspectivia.net',
     'shs.cairn.info',
-    'zaguan.unizar.es',
-    'numdam.org',
     'works.bepress.com',
+    'zaguan.unizar.es',
 ];
 
 const PROXY_HOSTS_TO_ALWAYS_DROP = [
-    'proxy.libraries',
-    'proxy.lib.',
-    '.ezproxy.',
     '-ezproxy.',
-    '/ezproxy.',
+    '.ezproxy.',
+    '.idm.oclc.org',
     '.serialssolutions.com',
-    'search.ebscohost.com',
+    '/ezproxy.',
     'findarticles.com',
     'journals.royalsociety.org',
-    '.idm.oclc.org',
+    'proxy.lib.',
+    'proxy.libraries',
+    'search.ebscohost.com',
 ]; // Drop these if there is a valid DOI
 
 const PROXY_HOSTS_TO_DROP = [
-    'proxy.libraries',
-    'proxy.lib.',
-    '.ezproxy.',
     '-ezproxy.',
-    '/ezproxy.',
-    '.serialssolutions.com',
     '.ebscohost.com',
-    'linkinghub.elsevier.com',
-    'doi.library.ubc.ca',
-    'ingentaconnect.com/content',
-    'sciencedirect.com/science?_ob',
-    'informaworld.com/smpp',
+    '.ezproxy.',
     '.search.serialssolutions.com',
+    '.serialssolutions.com',
+    '/ezproxy.',
+    'delivery.acm.org',
     'doi.apa.org',
-    'onlinelibrary.wiley.com/resolve/openurl',
+    'doi.library.ubc.ca',
     'findarticles.com',
+    'informaworld.com/smpp',
+    'ingentaconnect.com/content',
+    'linkinghub.elsevier.com',
+    'onlinelibrary.wiley.com/resolve/openurl',
+    'proxy.lib.',
+    'proxy.libraries',
     'psycnet.apa.org',
-    'delivery.acm.org',
+    'sciencedirect.com/science?_ob',
 ]; // Drop these if there is a valid FREE DOI
 
 const WEB_NEWSPAPERS = [
+    'abante',
+    'argus leader',
+    'austin daily herald',
+    'balita (newspaper)',
+    'balita.net.ph',
+    'bandera.inquirer.net',
     'bbc news',
-    'bbc',
-    'news.bbc.co.uk',
-    'bbc sports',
     'bbc sport',
-    'www.bbc.co.uk',
-    'the economist',
-    'washington post',
-    'philippine daily inquirer',
-    'www.inquirer.net',
+    'bbc sports',
+    'bbc',
+    'bozeman daily chronicle',
+    'businessmirror.com.ph',
+    'businessmirror',
+    'businessworld',
+    'chicago tribune',
+    'christian science monitor',
+    'csm',
+    'csmonitor.com',
+    'daily tribune (philippines)',
+    'inquirer bandera',
+    'irishtimes.com',
+    'journal.com.ph',
+    'la crosse tribune',
+    'malaya (newspaper)',
+    'malaya.com.ph',
     'manila bulletin',
-    'mb.com.ph',
-    'the philippine star',
-    'www.philstar.com',
-    'the manila times',
-    'www.manilatimes.net',
     'manila standard',
     'manilastandard.net',
-    'sunstar',
-    'www.sunstar.com.ph',
-    'malaya (newspaper)',
-    'malaya.com.ph',
-    'daily tribune (philippines)',
-    'tribune.net.ph',
-    'businessworld',
-    'www.bworldonline.com',
-    'businessmirror',
-    'businessmirror.com.ph',
-    'united news',
-    'www.unitednews.net.ph',
+    'mb.com.ph',
     'mindanao gold star daily',
     'mindanaogoldstardaily.com',
-    'tempo (newspaper)',
-    'www.tempo.com.ph',
+    'news.bbc.co.uk',
     'people\'s journal',
-    'journal.com.ph',
-    'abante',
-    'www.abante.com.ph',
-    'balita (newspaper)',
-    'balita.net.ph',
-    'inquirer bandera',
-    'bandera.inquirer.net',
+    'philippine daily inquirer',
     'pilipino star ngayon',
-    'irishtimes.com',
+    'rapid city journal',
+    'rochester democrat and chronicle',
+    'sunstar',
+    'tempo (newspaper)',
+    'the boston globe',
+    'the economist',
+    'the indianapolis news',
     'the irish times',
-    'the seattle times',
+    'the manila times',
+    'the missoulian',
+    'the montana standard',
+    'the new york times',
     'the news tribune',
+    'the philippine star',
+    'the seattle times',
     'the spokesman-review',
-    'the montana standard',
-    'the missoulian',
     'the spokesman-review',
-    'bozeman daily chronicle',
-    'the new york times',
-    'argus leader',
     'the washington post',
-    'rapid city journal',
-    'austin daily herald',
-    'la crosse tribune',
-    'chicago tribune',
-    'christian science monitor',
-    'csm',
-    'csmonitor.com',
-    'rochester democrat and chronicle',
-    'the boston globe',
-    'the indianapolis news',
+    'tribune.net.ph',
+    'united news',
+    'washington post',
+    'www.abante.com.ph',
+    'www.bbc.co.uk',
+    'www.bworldonline.com',
+    'www.inquirer.net',
+    'www.manilatimes.net',
+    'www.philstar.com',
+    'www.sunstar.com.ph',
+    'www.tempo.com.ph',
+    'www.unitednews.net.ph',
 ];
 
 const HOSTS_TO_NOT_ADD = [
+    'doi.org',
+    'dx.doi.org',
     'this.fails',
     'www.ncbi.nlm.nih.gov',
-    'dx.doi.org',
-    'doi.org',
+    'hdl.handle.net',
 ];
 
 const HOSTNAME_MAP = [
-    'moviecrow.com' => 'MovieCrow',
-    'public.ebookcentral.proquest.com' => '[[ProQuest]]',
-    'proquest.com' => '[[ProQuest]]',
-    'search.proquest.com' => '[[ProQuest]]',
-    'cnn.com' => '[[CNN]]',
-    'foxnews.com' => '[[Fox News]]',
-    'msnbc.com' => '[[MSNBC]]',
-    'nbcnews.com' => '[[NBC News]]',
-    'cbsnews.com' => '[[CBS News]]',
-    'cbs.com' => '[[CBS]]',
+    'abante.com.ph' => '[[Abante]]',
     'abc.com' => '[[American Broadcasting Company]]',
-    'nytimes.com' => '[[The New York Times]]',
-    'newyorker.com' => '[[The New Yorker]]',
-    'independent.co.uk' => '[[Independent.co.uk]]',
-    'cnbc.com' => '[[CNBC]]',
-    'theatlantic.com' => '[[The Atlantic]]',
-    'jpl.nasa.gov' => '[[Jet Propulsion Laboratory]]',
-    'latimes.com' => '[[Los Angeles Times]]',
-    'reuters.com' => '[[Reuters]]',
-    'dailynews.com' => '[[Los Angeles Daily News]]',
-    'gsfc.nasa.gov' => '[[Goddard Space Flight Center]]',
-    'newsweek.com' => '[[Newsweek]]',
-    'observer.com' => '[[The New York Observer]]',
-    'pbs.org' => '[[PBS]]',
-    'mediaincanada.com' => '[[Media of Canada]]',
-    'zap2it.com' => '[[Zap2it]]',
-    'fda.gov' => '[[Food and Drug Administration]]',
-    'rte.ie' => '[[RTÉ.ie]]',
-    'rockpapershotgun.com' => '[[Rock Paper Shotgun]]',
-    'gameinformer.com' => '[[Game Informer]]',
-    'lemonde.fr' => '[[Le Monde]]',
-    'pcgamer.com' => '[[PC Gamer]]',
-    'metacritic.com' => '[[Metacritic]]',
-    'redbull.com' => '[[Red Bull]]',
+    'abc.net.au' => '[[Australian Broadcasting Corporation]]',
     'abcnews.com' => '[[ABC News (United States)|ABC News]]',
     'abcnews.go.com' => '[[ABC News (United States)|ABC News]]',
+    'acharts.us' => 'αCharts',
+    'alfred.com' => 'Alfred Music',
     'allmusic.com' => '[[AllMusic]]',
+    'altpress.com' => '[[Alternative Press (magazine)|Alternative Press]]',
+    'amazon.co.uk' => 'Amazon UK',
+    'amazon.com' => 'Amazon',
+    'amazon.de' => 'Amazon Germany',
     'ancestry.com' => '[[Ancestry.com]]',
+    'animaldiversity.org' => '[[Animal Diversity Web]]',
     'answers.com' => '[[Answers.com]]',
+    'antena3.com' => '[[Antena 3 (Spanish TV channel)|Antena 3]]',
     'ap.org' => '[[Associated Press]]',
     'apnews.com' => '[[Associated Press News]]',
+    'articles.latimes.com' => '[[Los Angeles Times]]',
     'avclub.com' => '[[The A.V. Club]]',
+    'bac-lac.gc.ca' => '[[Library and Archives Canada]]',
     'baidu.com' => '[[Baidu]]',
-    'sohu.com' => '[[Sohu]]',
+    'balita.net.ph' => '[[Balita (newspaper)|Balita]]',
+    'bandera.inquirer.net' => '[[Inquirer Bandera|Bandera]]',
+    'beatport.com' => '[[Beatport]]',
+    'bet.com' => '[[BET]]',
+    'billboard.com' => '[[Billboard (magazine)|Billboard]]',
+    'bleacherreport.com' => '[[Bleacher Report]]',
     'bloomberg.com' => '[[Bloomberg News]]',
+    'bollywoodhungama.com' => '[[Bollywood Hungama]]',
+    'bostonglobe.com' => '[[The Boston Globe]]',
+    'boxlifemagazine.com' => 'BoxLife',
     'breitbart.com' => '[[Breitbart News]]',
     'businessinsider.com' => '[[Business Insider]]',
+    'businessmirror.com.ph' => '[[BusinessMirror]]',
     'buzzfeed.com' => '[[BuzzFeed]]',
     'buzzfeednews.com' => '[[BuzzFeed News]]',
+    'buzzjack.com' => 'BuzzJack',
+    'bworldonline.com' => '[[BusinessWorld]]',
+    'capitalxtra.com' => 'Capital XTRA',
+    'cbs.com' => '[[CBS]]',
+    'cbsnews.com' => '[[CBS News]]',
+    'cdjapan.co.jp' => 'CDJapan',
+    'chicagotribune.com' => '[[Chicago Tribune]]',
+    'cinemaexpress.com' => '[[Cinema Express]]',
+    'classicbands.com' => 'ClassicBands.com',
+    'cnbc.com' => '[[CNBC]]',
+    'cnn.com' => '[[CNN]]',
+    'collider.com' => '[[Collider (website)|Collider]]',
+    'comedy.co.uk' => '[[British Comedy Guide]]',
+    'complex.com' => '[[Complex Networks]]',
     'csmonitor.com' => '[[The Christian Science Monitor]]',
-    'rollingstone.com' => '[[Rolling Stone]]',
     'dailydot.com' => '[[The Daily Dot]]',
-    'dailymail.com' => '[[Daily Mail]]',
     'dailymail.co.uk' => '[[Daily Mail]]',
-    'deseretnews.com' => '[[Deseret News]]',
+    'dailymail.com' => '[[Daily Mail]]',
+    'dailynews.com' => '[[Los Angeles Daily News]]',
+    'dailysabah.com' => '[[Daily Sabah]]',
     'dailywire.com' => '[[The Daily Wire]]',
     'democracynow.org' => '[[Democracy Now!]]',
+    'deseretnews.com' => '[[Deseret News]]',
+    'desmoinesregister.com' => '[[The Des Moines Register]]',
+    'digitalspy.co.uk' => '[[Digital Spy]]',
+    'digitalspy.com' => '[[Digital Spy]]',
+    'discogs.com' => '[[Discogs]]',
+    'dtnext.in' => '[[DT Next]]',
+    'dw.com' => '[[Deutsche Welle]]',
     'economist.com' => '[[The Economist]]',
-    'facebook.com' => '[[Facebook]]',
+    'edge-online.com' => 'Edge',
+    'edweek.org' => '[[Education Week]]',
+    'elitefts.com' => 'elitefts',
     'epochtimes.com' => '[[The Epoch Times]]',
+    'espnscrum.com' => '[[ESPNscrum]]',
+    'eurogamer.net' => '[[Eurogamer]]',
+    'eurokdj.com' => 'Eurodance Encyclopaedia',
+    'ew.com' => '[[Entertainment Weekly]]',
     'examiner.com' => '[[Examiner.com]]',
+    'facebook.com' => '[[Facebook]]',
     'familysearch.org' => '[[FamilySearch]]',
+    'fda.gov' => '[[Food and Drug Administration]]',
     'findagrave.com' => '[[Find a Grave]]',
     'forbes.com' => '[[Forbes]]',
     'foxbusiness.com' => '[[Fox Business]]',
+    'foxnews.com' => '[[Fox News]]',
+    'fuse.tv' => '[[Fuse (TV channel)|Fuse]]',
+    'gameinformer.com' => '[[Game Informer]]',
+    'github.com' => '[[GitHub]]',
+    'gsfc.nasa.gov' => '[[Goddard Space Flight Center]]',
+    'happygamer.com' => 'Happy Gamer',
     'hollywoodreporter.com' => '[[The Hollywood Reporter]]',
-    'screenrant.com' => '[[Screen Rant]]',
+    'hotnewhiphop.com' => 'HNHH',
+    'hroarr.com' => 'HROARR',
     'huffingtonpost.com' => '[[HuffPost]]',
+    'ibm.com' => '[[IBM]]',
     'ibtimes.co.in' => '[[International Business Times]]',
     'ibtimes.com' => '[[International Business Times]]',
+    'ieee.org' => '[[Institute of Electrical and Electronics Engineers]] (IEEE)',
     'imdb.com' => '[[IMDb]]',
+    'independent.co.uk' => '[[Independent.co.uk]]',
+    'inquirer.net' => '[[Philippine Daily Inquirer]]',
+    'insider.com' => '[[Insider.com]]',
+    'irishtimes.com' => '[[The Irish Times]]',
+    'itunes.apple.com' => '[[iTunes]]',
+    'jewishweek.timesofisrael.com' => '[[The Jewish Week]]',
+    'journal.com.ph' => '[[People\'s Journal]]',
+    'jpl.nasa.gov' => '[[Jet Propulsion Laboratory]]',
+    'latimes.com' => '[[Los Angeles Times]]',
+    'latino.foxnews.com' => '[[Fox News]]',
+    'legacy.com' => '[[Legacy.com]]',
+    'lemonde.fr' => '[[Le Monde]]',
+    'livescience.com' => '[[Live Science]]',
+    'loc.gov' => '[[Library of Congress]]',
+    'loudwire.com' => '[[Loudwire]]',
+    'malaya.com.ph' => '[[Malaya (newspaper)|Malaya]]',
+    'manilastandard.net' => '[[Manila Standard]]',
+    'manilatimes.net' => '[[The Manila Times]]',
     'mashable.com' => '[[Mashable]]',
+    'mayoclinic.org' => '[[Mayo Clinic]]',
+    'mb.com.ph' => '[[Manila Bulletin]]',
+    'mediaincanada.com' => '[[Media of Canada]]',
     'mediamatters.org' => '[[Media Matters for America]]',
+    'mensfitness.co.uk' => 'Men\'s Fitness',
+    'metacritic.com' => '[[Metacritic]]',
+    'miamiherald.com' => '[[Miami Herald]]',
+    'microsoft.com' => '[[Microsoft]]',
+    'mindanaogoldstardaily.com' => '[[Mindanao Gold Star Daily]]',
     'mirror.co.uk' => '[[Daily Mirror]]',
+    'mlb.com' => '[[MLB.com]]',
+    'moviecrow.com' => 'MovieCrow',
+    'msn.com' => '[[MSN]]',
+    'msnbc.com' => '[[MSNBC]]',
+    'mtv.com' => '[[MTV]]',
+    'mtv.de' => 'MTV Germany',
+    'musicnotes.com' => 'Musicnotes',
     'nationalgeographic.com' => '[[National Geographic Society]]',
     'nationalreview.com' => '[[National Review]]',
+    'nba.com' => '[[NBA.com]]',
+    'nbcnews.com' => '[[NBC News]]',
+    'netflix.com' => '[[Netflix]]',
     'newrepublic.com' => '[[The New Republic]]',
+    'newsweek.com' => '[[Newsweek]]',
+    'newyorker.com' => '[[The New Yorker]]',
+    'nfl.com' => '[[NFL.com]]',
+    'nme.com' => '[[NME]]',
+    'noise11.com' => 'noise11.com',
     'npr.org' => '[[NPR]]',
     'nydailynews.com' => '[[New York Daily News]]',
+    'nytimes.com' => '[[The New York Times]]',
+    'observer.com' => '[[The New York Observer]]',
+    'officialcharts.com' => '[[Official Charts Company|Official Charts]]',
+    'open.spotify.com' => '[[Spotify]]',
+    'pbs.org' => '[[PBS]]',
+    'pcgamer.com' => '[[PC Gamer]]',
+    'philstar.com' => '[[The Philippine STAR]]',
+    'philstar.com/pilipino-star-ngayon' => '[[Pilipino Star Ngayon]]',
+    'pia.gov.ph' => 'Philippine Information Agency',
+    'pitchfork.com' => '[[Pitchfork (website)|Pitchfork]]',
+    'pna.gov.ph' => 'Philippine News Agency',
     'politico.com' => '[[Politico]]',
+    'polygon.com' => '[[Polygon (website)|Polygon]]',
+    'pro-football-reference.com' => '[[Pro-Football-Reference.com]]',
+    'proquest.com' => '[[ProQuest]]',
+    'providencephoenix.com' => 'Providence Phoenix',
+    'public.ebookcentral.proquest.com' => '[[ProQuest]]',
+    'queenvault.com' => 'Queen Vault',
+    'ratingsryan.com' => 'Ratings Ryan',
+    'redbull.com' => '[[Red Bull]]',
+    'reuters.com' => '[[Reuters]]',
+    'riaa.com' => '[[Recording Industry Association of America]]',
+    'rnz.co.nz' => '[[Radio New Zealand]]',
+    'rockpapershotgun.com' => '[[Rock Paper Shotgun]]',
+    'rocksmith.ubi.com' => 'Rocksmith+',
+    'rollingstone.com' => '[[Rolling Stone]]',
     'rottentomatoes.com' => '[[Rotten Tomatoes]]',
+    'royal.uk' => 'The Royal Family',
+    'rte.ie' => '[[RTÉ.ie]]',
     'scientificamerican.com' => '[[Scientific American]]',
+    'screenrant.com' => '[[Screen Rant]]',
+    'search.proquest.com' => '[[ProQuest]]',
+    'secondhandsongs.com' => 'SecondHandSongs',
+    'seenews.com' => 'SeeNews',
+    'setlist.fm' => 'setlist.fm',
+    'sheetmusicnow.com' => 'Sheet Music Now',
+    'showbuzzdaily.com' => '[[Showbuzzdaily.com]]',
+    'sify.com' => '[[Sify]]',
+    'slantmagazine.com' => '[[Slant Magazine]]',
+    'sohu.com' => '[[Sohu]]',
+    'songlines.co.uk' => '[[Songlines (magazine)|Songlines]]',
+    'space.com' => '[[Space.com]]',
+    'startribune.com' => '[[Star Tribune]]',
+    'strategicmanagementinsight.com' => 'StrategicManagementInsight.com',
+    'sunstar.com.ph' => '[[SunStar]]',
+    'tempo.com.ph' => '[[Tempo (newspaper)|Tempo]]',
+    'tennessean.com' => '[[The Tennessean]]',
+    'theathletic.com' => '[[The Athletic]]',
+    'theatlantic.com' => '[[The Atlantic]]',
+    'theboot.com' => 'The Boot',
     'thedailybeast.com' => '[[The Daily Beast]]',
     'theepochtimes.com' => '[[The Epoch Times]]',
     'theglobeandmail.com' => '[[The Globe and Mail]]',
     'theguardian.com' => '[[TheGuardian.com]]',
     'thehindu.com' => '[[The Hindu]]',
     'theonion.com' => '[[The Onion]]',
+    'theprint.in' => '[[ThePrint]]',
     'theregister.co.uk' => '[[The Register]]',
-    'thetimes.co.uk' => '[[The Times]]',
+    'thestar.com' => '[[Toronto Star]]',
+    'thestatesman.com' => '[[The Statesman (India)|The Statesman]]',
     'thesundaytimes.co.uk' => '[[The Sunday Times]]',
+    'thetimes.co.uk' => '[[The Times]]',
+    'theweek.co.uk' => '[[The Week]]',
+    'theweek.com' => '[[The Week]]',
+    'theweek.in' => '[[The Week (Indian magazine)|The Week]]',
     'thinkprogress.org' => '[[ThinkProgress]]',
     'timesofindia.com' => '[[The Times of India]]',
     'timesofindia.indiatimes.com' => '[[The Times of India]]',
-    'usatoday.com' => '[[USA Today]]',
-    'urbandictionary.com' => '[[Urban Dictionary]]',
-    'washingtonpost.com' => '[[The Washington Post]]',
-    'washingtontimes.com' => '[[The Washington Times]]',
-    'msn.com' => '[[MSN]]',
-    'microsoft.com' => '[[Microsoft]]',
-    'youtube.com' => '[[YouTube]]',
-    'zdnet.com' => '[[ZDNet]]',
-    'netflix.com' => '[[Netflix]]',
-    'chicagotribune.com' => '[[Chicago Tribune]]',
-    'bostonglobe.com' => '[[The Boston Globe]]',
-    'bleacherreport.com' => '[[Bleacher Report]]',
     'timesofisrael.com' => '[[The Times of Israel]]',
-    'jewishweek.timesofisrael.com' => '[[The Jewish Week]]',
-    'miamiherald.com' => '[[Miami Herald]]',
-    'desmoinesregister.com' => '[[The Des Moines Register]]',
-    'thestar.com' => '[[Toronto Star]]',
-    'tennessean.com' => '[[The Tennessean]]',
-    'startribune.com' => '[[Star Tribune]]',
-    'comedy.co.uk' => '[[British Comedy Guide]]',
-    'legacy.com' => '[[Legacy.com]]',
-    'slantmagazine.com' => '[[Slant Magazine]]',
-    'nme.com' => '[[NME]]',
-    'eurokdj.com' => 'Eurodance Encyclopaedia',
-    'videostatic.com' => 'VideoStatic',
-    'discogs.com' => '[[Discogs]]',
-    'musicnotes.com' => 'Musicnotes',
-    'amazon.com' => 'Amazon',
-    'amazon.de' => 'Amazon Germany',
-    'amazon.co.uk' => 'Amazon UK',
     'tophit.ru' => '[[Tophit]]',
-    'acharts.us' => 'αCharts',
-    'bet.com' => '[[BET]]',
-    'mtv.com' => '[[MTV]]',
-    'ultratop.be' => '[[Ultratop]]',
-    'billboard.com' => '[[Billboard (magazine)|Billboard]]',
-    'officialcharts.com' => '[[Official Charts Company|Official Charts]]',
-    'loudwire.com' => '[[Loudwire]]',
-    'altpress.com' => '[[Alternative Press (magazine)|Alternative Press]]',
-    'noise11.com' => 'noise11.com',
-    'bac-lac.gc.ca' => '[[Library and Archives Canada]]',
-    'itunes.apple.com' => '[[iTunes]]',
-    'cdjapan.co.jp' => 'CDJapan',
-    'rocksmith.ubi.com' => 'Rocksmith+',
-    'setlist.fm' => 'setlist.fm',
-    'digitalspy.co.uk' => '[[Digital Spy]]',
-    'digitalspy.com' => '[[Digital Spy]]',
-    'buzzjack.com' => 'BuzzJack',
-    'open.spotify.com' => '[[Spotify]]',
-    'whosampled.com' => '[[WhoSampled]]',
-    'fuse.tv' => '[[Fuse (TV channel)|Fuse]]',
-    'collider.com' => '[[Collider (website)|Collider]]',
-    'space.com' => '[[Space.com]]',
-    'github.com' => '[[GitHub]]',
-    'strategicmanagementinsight.com' => 'StrategicManagementInsight.com',
-    'edge-online.com' => 'Edge',
-    'boxlifemagazine.com' => 'BoxLife',
-    'hroarr.com' => 'HROARR',
-    'mensfitness.co.uk' => 'Men\'s Fitness',
-    'riaa.com' => '[[Recording Industry Association of America]]',
-    'secondhandsongs.com' => 'SecondHandSongs',
-    'alfred.com' => 'Alfred Music',
-    'capitalxtra.com' => 'Capital XTRA',
-    'theboot.com' => 'The Boot',
-    'ew.com' => '[[Entertainment Weekly]]',
-    'antena3.com' => '[[Antena 3 (Spanish TV channel)|Antena 3]]',
-    'complex.com' => '[[Complex Networks]]',
-    'articles.latimes.com' => '[[Los Angeles Times]]',
-    'providencephoenix.com' => 'Providence Phoenix',
-    'queenvault.com' => 'Queen Vault',
-    'classicbands.com' => 'ClassicBands.com',
-    'seenews.com' => 'SeeNews',
-    'mtv.de' => 'MTV Germany',
-    'eurogamer.net' => '[[Eurogamer]]',
-    'happygamer.com' => 'Happy Gamer',
-    'polygon.com' => '[[Polygon (website)|Polygon]]',
-    'edweek.org' => '[[Education Week]]',
-    'hotnewhiphop.com' => 'HNHH',
-    'beatport.com' => '[[Beatport]]',
-    'pitchfork.com' => '[[Pitchfork (website)|Pitchfork]]',
-    'sheetmusicnow.com' => 'Sheet Music Now',
-    'mayoclinic.org' => '[[Mayo Clinic]]',
-    'elitefts.com' => 'elitefts',
-    'loc.gov' => '[[Library of Congress]]',
-    'livescience.com' => '[[Live Science]]',
-    'insider.com' => '[[Insider.com]]',
-    'latino.foxnews.com' => '[[Fox News]]',
-    'dw.com' => '[[Deutsche Welle]]',
-    'rnz.co.nz' => '[[Radio New Zealand]]',
-    'pro-football-reference.com' => '[[Pro-Football-Reference.com]]',
-    'nba.com' => '[[NBA.com]]',
-    'mlb.com' => '[[MLB.com]]',
-    'nfl.com' => '[[NFL.com]]',
-    'showbuzzdaily.com' => '[[Showbuzzdaily.com]]',
-    'ratingsryan.com' => 'Ratings Ryan',
-    'vanityfair.com' => '[[Vanity Fair (magazine)|Vanity Fair]]',
-    'songlines.co.uk' => '[[Songlines (magazine)|Songlines]]',
-    'abc.net.au' => '[[Australian Broadcasting Corporation]]',
-    'espnscrum.com' => '[[ESPNscrum]]',
-    'thestatesman.com' => '[[The Statesman (India)|The Statesman]]',
-    'dailysabah.com' => '[[Daily Sabah]]',
-    'ibm.com' => '[[IBM]]',
-    'ieee.org' => '[[Institute of Electrical and Electronics Engineers]] (IEEE)',
-    'bandera.inquirer.net' => '[[Inquirer Bandera|Bandera]]',
-    'inquirer.net' => '[[Philippine Daily Inquirer]]',
-    'mb.com.ph' => '[[Manila Bulletin]]',
-    'philstar.com/pilipino-star-ngayon' => '[[Pilipino Star Ngayon]]',
-    'philstar.com' => '[[The Philippine STAR]]',
-    'manilatimes.net' => '[[The Manila Times]]',
-    'manilastandard.net' => '[[Manila Standard]]',
-    'sunstar.com.ph' => '[[SunStar]]',
-    'malaya.com.ph' => '[[Malaya (newspaper)|Malaya]]',
     'tribune.net.ph' => '[[Daily Tribune (Philippines)|Daily Tribune]]',
-    'bworldonline.com' => '[[BusinessWorld]]',
-    'businessmirror.com.ph' => '[[BusinessMirror]]',
+    'ultratop.be' => '[[Ultratop]]',
     'unitednews.net.ph' => '[[United News]]',
-    'mindanaogoldstardaily.com' => '[[Mindanao Gold Star Daily]]',
-    'tempo.com.ph' => '[[Tempo (newspaper)|Tempo]]',
-    'journal.com.ph' => '[[People\'s Journal]]',
-    'abante.com.ph' => '[[Abante]]',
-    'balita.net.ph' => '[[Balita (newspaper)|Balita]]',
-    'pna.gov.ph' => 'Philippine News Agency',
-    'pia.gov.ph' => 'Philippine Information Agency',
-    'irishtimes.com' => '[[The Irish Times]]',
+    'urbandictionary.com' => '[[Urban Dictionary]]',
+    'usatoday.com' => '[[USA Today]]',
+    'vanityfair.com' => '[[Vanity Fair (magazine)|Vanity Fair]]',
+    'videostatic.com' => 'VideoStatic',
+    'washingtonpost.com' => '[[The Washington Post]]',
+    'washingtontimes.com' => '[[The Washington Times]]',
+    'whosampled.com' => '[[WhoSampled]]',
     'wikinews.org' => '[[Wikinews]]',
-    'royal.uk' => 'The Royal Family',
-    'cinemaexpress.com' => '[[Cinema Express]]',
-    'sify.com' => '[[Sify]]',
-    'animaldiversity.org' => '[[Animal Diversity Web]]',
-    'bollywoodhungama.com' => '[[Bollywood Hungama]]',
-    'dtnext.in' => '[[DT Next]]',
-    'theweek.co.uk' => '[[The Week]]',
-    'theweek.com' => '[[The Week]]',
-    'theweek.in' => '[[The Week (Indian magazine)|The Week]]',
-    'theathletic.com' => '[[The Athletic]]',
-    'theprint.in' => '[[ThePrint]]',
+    'youtube.com' => '[[YouTube]]',
+    'zap2it.com' => '[[Zap2it]]',
+    'zdnet.com' => '[[ZDNet]]',
 ]; // Be warned, some website host a seperate sunday edition, etc.  Be careful and when in doubt link to hostname
 
 const NO_DATE_WEBSITES = [
-    'chairs-chaires.gc.ca',
-    'apopo.org',
     'allmusic.com',
+    'apopo.org',
     'apps.des.qld.gov.au',
     'archive-it.org',
     'archive.fo',
@@ -1033,6 +1033,7 @@
     'brema.suub.uni-bremen.de',
     'britannica.com',
     'catalogue.bnf.fr',
+    'chairs-chaires.gc.ca',
     'chinesefilmclassics.org',
     'chroniclingamerica.loc.gov',
     'collections.louvre.fr',
@@ -1084,74 +1085,72 @@
 ];
 
 const ZOTERO_AVOID_REGEX = [
-    'twitter\.', // This should be {{cite tweet}}
-    // Zotero seems to be doing better now 'youtube\.', 'youtu\.be',
+    'arkive\.org',
+    'australian-charts\.com', // Fails 100%
+    'biodiversity\.org\.au', // Zotero gives bad data
+    'bloomberg\.com/tosv2.html', // Junk
     'books\.google\.', // We have special google books code
+    'britishnewspaperarchive\.co\.uk', // Requires registration
+    'cagematch\.net', // Fails 100%
+    'censusindia\.gov\.in', // Fails 100%
+    'charts\.nz', // Fails 100%
+    'ebooks\.adelaide\.edu\.au', // Dead
+    'elonet\.finna\.fi', // Zotero cannot handle this data-base well at all
+    'explore\.bl\.uk/primo_library', // Fails 100%
+    'ezproxy',
+    'facebook\.com', // login and junk
+    'findarticles\.com', // Gone
     'google\.com/search', // Google search results
+    'info\.hazu\.hr', // Fails 100%
     'jstor\.org/stable/', // We have special jstor code
-    'ned\.ipac\.caltech\.edu', // Gives no real title
-    'pep\-web\.org', // Does not parse very well at all
-    'ezproxy',
-    'arkive\.org',
-    'bloomberg\.com/tosv2.html', // Junk
-    'worldcat\.org', // Should use parameters and google instead
+    'kijkcijferanalyse\.nl/', // highjacked
     'kyobobook\.co\.kr', // Bookstore that give junk
-    'facebook\.com', // login and junk
     'leighrayment\.com', // highjacked
-    'seapower\-digital\.com', // highjacked
-    'scholarlycommons\.pacific\.edu\/euler\-works', // returns journal reference to works, not the actual work
+    'lincstothepast\.com',
     'miar\.ub\.edu\/issn', // ISSN description, not actually the journal
-    'britishnewspaperarchive\.co\.uk', // Requires registration
+    'myprivacy\.dpgmedia\.nl', // blocker
+    'ned\.ipac\.caltech\.edu', // Gives no real title
+    'olympics\.com', // Fails 100%
+    'pep\-web\.org', // Does not parse very well at all
     'pressreader\.com', // Bad titles
-    'ebooks\.adelaide\.edu\.au', // Dead
+    'radiomap\.eu', // Fails 100%
+    'scholarlycommons\.pacific\.edu\/euler\-works', // returns journal reference to works, not the actual work
+    'seapower\-digital\.com', // highjacked
+    'startribune\.newspapers\.com', // Fails 100%
+    'stats\.espncricinfo\.com', // Fails 100%
+    'steubencourier\.com', // USA Today highjakced
+    'swedishcharts\.com', // Fails 100%
+    'timea\.rice\.edu', // gone
     'tnmaps\.tn\.nic\.in', // maps
-    'lincstothepast\.com',
-    'elonet\.finna\.fi', // Zotero cannot handle this data-base well at all
-    'washingtonpost\.com', // Fails 100%
-    'cagematch\.net', // Fails 100%
-    'www\.cbc\.ca', // Fails 100%
-    'www\.emporis\.com', // Fails 100%
+    'twitter\.', // This should be {{cite tweet}}
     'usnews\.com', // Fails 100%
-    'www\.ascap\.com', // Fails 100%
-    'www\.thefutoncritic\.com', // Fails 100%
-    'www\.bom\.gov\.au', // Fails 100%
-    'www\.dailytelegraph\.com\.au', // Fails 100%
-    'www\.pwinsider\.com', // Fails 100%
-    'www\.wrecksite\.eu', // Fails 100%
-    'www\.heraldsun\.com\.au', // Fails 100%
-    'www\.neighbourhood\.statistics\.gov\.uk', // Fails 100%
-    'www\.playbill\.com', // Fails 100%
-    'olympics\.com', // Fails 100%
-    'www\.legislation\.gov\.uk', // Fails 100%
-    'stats\.espncricinfo\.com', // Fails 100%
+    'washingtonpost\.com', // Fails 100%
+    'weblio\.jp/', // just scrapes other website like wiki and has bogus issue and volume numbers
+    'worldcat\.org', // Should use parameters and google instead
     'www\.almasdarnews\.com', // Fails 100%
-    'www\.encyclopedia\.com', // Fails 100%
-    'swedishcharts\.com', // Fails 100%
-    'www\.teamusa\.org', // Fails 100%
+    'www\.ascap\.com', // Fails 100%
+    'www\.billboard-japan\.com', // Fails 100%
+    'www\.bom\.gov\.au', // Fails 100%
+    'www\.cbc\.ca', // Fails 100%
+    'www\.censusindia\.gov\.in', // Fails 100%
     'www\.couriermail\.com\.au', // Fails 100%
+    'www\.dailytelegraph\.com\.au', // Fails 100%
+    'www\.emporis\.com', // Fails 100%
+    'www\.encyclopedia\.com', // Fails 100%
     'www\.faa\.gov', // Fails 100%
+    'www\.heraldsun\.com\.au', // Fails 100%
     'www\.hockeydb\.com', // Fails 100%
-    'info\.hazu\.hr', // Fails 100%
-    'australian-charts\.com', // Fails 100%
-    'startribune\.newspapers\.com', // Fails 100%
+    'www\.legislation\.gov\.uk', // Fails 100%
+    'www\.neighbourhood\.statistics\.gov\.uk', // Fails 100%
     'www\.olympic\.org', // Fails 100%
-    'www\.billboard-japan\.com', // Fails 100%
-    'www\.censusindia\.gov\.in', // Fails 100%
-    'censusindia\.gov\.in', // Fails 100%
-    'charts\.nz', // Fails 100%
-    'radiomap\.eu', // Fails 100%
+    'www\.playbill\.com', // Fails 100%
+    'www\.pwinsider\.com', // Fails 100%
+    'www\.teamusa\.org', // Fails 100%
+    'www\.thefutoncritic\.com', // Fails 100%
     'www\.virtualwall\.org', // Fails 100%
-    'steubencourier\.com', // USA Today highjakced
-    'biodiversity\.org\.au', // Zotero gives bad data
-    'timea\.rice\.edu', // gone
-    'findarticles\.com', // Gone
-    'myprivacy\.dpgmedia\.nl', // blocker
-    'explore\.bl\.uk/primo_library', // Fails 100%
-    'weblio\.jp/', // just scrapes other website like wiki and has bogus issue and volume numbers
-    'kijkcijferanalyse\.nl/', // highjacked
+    'www\.wrecksite\.eu', // Fails 100%
 ];
 const NON_JOURNAL_WEBSITES = [
-    'ourworldindata.org/',
     '-news.co.uk/',
     '.ajc.com/',
     '.al.com/',
@@ -8326,6 +8325,7 @@
     'oursportscentral.com/',
     'ourvmc.org/',
     'ourwarwickshire.org.uk/',
+    'ourworldindata.org/',
     'out.com/',
     'outils-odsef-fss.ulaval.ca/',
     'outlawcountrycruise.com/',
@@ -12234,117 +12234,117 @@
 // bbm.ca is short enough that we add /bbm.ca/ and .bbm.ca/ since we do not want to grab too many sites
 
 const NON_JOURNAL_DOIS = [
-    '10.17487/rfc',
-    '10.5531/db.vz.0001',
     '10.1163/2352-0248',
+    '10.17487/rfc',
+    '10.2139/ssrn',
     '10.3318/dib',
     '10.34667/tind.',
-    '10.2139/ssrn',
+    '10.5531/db.vz.0001',
 ]; // lowercase exact matches
 const NON_JOURNALS = [
     'Amphibian Species of the World',
     'an Online Reference',
     'An Online Reference',
     'Boston Almanac and Guide1',
-    'Includes:reports from Commissioners, Inspectors and Others',
     'Digital Collections',
+    'Includes:reports from Commissioners, Inspectors and Others',
     'X (Formerly Twitter)',
 ]; // Case-sensitive sub-string
 const ARE_MAGAZINES = [
-    'the new yorker',
-    'the new republic',
-    'new republic',
-    'expedition magazine',
-    'wired',
-    'wired uk',
+    'billboard (magazine)',
+    'billboard',
     'computer gaming world',
     'edge (magazine)',
+    'electronic gaming monthly',
+    'entertainment weekly',
+    'expedition magazine',
+    'famitsu',
     'game informer',
-    'pc gamer uk',
-    'wired (magazine)',
-    'time',
-    'life',
-    'time (magazine)',
+    'gamepro',
+    'games radar',
+    'harper\'s bazaar',
+    'harper\'s magazine',
+    'harper\'s',
+    'hyper',
+    'kalki',
     'life (magazine)',
-    'billboard',
-    'billboard (magazine)',
-    'rolling stone',
+    'life',
     'mcv/develop',
-    'vanity fair',
+    'new civil engineer',
+    'new republic',
     'nintendo power',
-    'playthings',
-    'entertainment weekly',
-    'official xbox magazine',
-    'electronic gaming monthly',
     'official u.s. playstation magazine',
-    'playstation: the official magazine',
+    'official xbox magazine',
+    'pc gamer uk',
     'play and silicon mag',
-    'games radar',
-    'hyper',
-    'famitsu',
-    'gamepro',
-    'yachting world',
-    'kalki',
+    'playstation: the official magazine',
+    'playthings',
+    'rolling stone',
     'sports illustrated',
-    'new civil engineer',
-    'harper\'s magazine',
-    'harper\'s bazaar',
-    'harper\'s',
+    'the new republic',
+    'the new yorker',
+    'time (magazine)',
+    'time',
+    'vanity fair',
+    'wired (magazine)',
+    'wired uk',
+    'wired',
+    'yachting world',
 ]; // lowercase axact matches
 const ARE_MANY_THINGS = [
-    'pc gamer',
-    'gamestar',
-    'rock paper shotgun',
-    'mcv',
-    'rock, paper, shotgun',
-    'edge',
-    'ballotpedia',
-    'npr',
+    'audible.com',
+    'audible',
     'ballotpedia.org',
-    'npr.org',
-    'nih.gov',
-    'nih',
-    'eurogamer.it',
+    'ballotpedia',
+    'brema.suub.uni-bremen.de',
     'conceptcarz',
-    'the royal family',
-    'eurogamer.de',
     'east west main line partnership',
-    'national institutes of health',
-    'national institutes of health (nih)',
-    'www.finna.fi',
-    'finna.fi',
+    'edge',
     'elonet',
-    'audible.com',
-    'audible',
+    'eurogamer.de',
+    'eurogamer.it',
+    'finna.fi',
+    'gamestar',
+    'mcv',
+    'national institutes of health (nih)',
+    'national institutes of health',
+    'nih.gov',
+    'nih',
+    'npr.org',
+    'npr',
+    'pc gamer',
+    'rock paper shotgun',
+    'rock, paper, shotgun',
     'staats und universitätsbibliothek bremen',
-    'brema.suub.uni-bremen.de',
+    'the royal family',
     'usdakotawar.org',
+    'www.finna.fi',
 ]; // lowercase axact matches.  These are things that are both websites and newspapers
 const ARE_NEWSPAPERS = [
-    'the economist',
     'la times',
-    'toronto sun',
-    'washington post',
-    'the washington post',
     'philippine daily inquirer',
+    'the economist',
     'the irish times',
-    'wikinews',
+    'the washington post',
+    'toronto sun',
+    'washington post',
     'wikinews.org',
+    'wikinews',
 ]; // lowercase axact matches
 const NO_PUBLISHER_NEEDED = [
+    'forbes magazine',
+    'forbes.com',
+    'huffington post',
     'los angeles times',
     'new york times magazine',
-    'the new york times',
     'new york times',
-    'huffington post',
     'the daily telegraph',
-    'forbes.com',
-    'forbes magazine',
+    'the new york times',
 ]; // lowercase axact matches
 
 const ENCYCLOPEDIA_WEB = [
-    'plato.stanford.edu',
     'britannica.com',
+    'plato.stanford.edu',
 ];
 
 const GOOD_10_1093_DOIS = [
@@ -12799,40 +12799,40 @@
 // List of things to not print links to, since they occur all the time
 const AVOIDED_LINKS = [
     '',
-    'Digital_object_identifier',
-    'JSTOR',
-    'Website',
-    'International_Standard_Book_Number',
-    'Library_of_Congress_Control_Number',
-    'Handle_System',
-    'PubMed_Central',
-    'PubMed',
-    'PubMed_Identifier',
+    'ArXiv_(identifier)',
+    'ArXiv',
+    'Bibcode_(identifier)',
     'Bibcode',
-    'International_Standard_Serial_Number',
     'bioRxiv',
+    'Cf.',
     'CiteSeerX',
-    'Zentralblatt_MATH',
+    'Digital_object_identifier',
+    'Doi_(identifier)',
+    'Handle_System',
+    'International_Standard_Book_Number',
+    'International_Standard_Serial_Number',
+    'ISBN_(identifier)',
+    'ISSN_(identifier)',
     'Jahrbuch_über_die_Fortschritte_der_Mathematik',
+    'JSTOR',
+    'Library_of_Congress_Control_Number',
     'Mathematical_Reviews',
+    'OCLC_(identifier)',
+    'OCLC',
     'Office_of_Scientific_and_Technical_Information',
-    'Request_for_Comments',
-    'Social_Science_Research_Network',
-    'Zentralblatt_MATH',
     'Open_Library',
-    'ArXiv',
-    'OCLC',
-    'Cf.',
-    'Doi_(identifier)',
+    'OSTI_(identifier)',
     'PMC_(identifier)',
     'PMID_(identifier)',
-    'ArXiv_(identifier)',
-    'Bibcode_(identifier)',
+    'PubMed_Central',
+    'PubMed_Identifier',
+    'PubMed',
+    'Request_for_Comments',
     'S2CID_(identifier)',
-    'ISBN_(identifier)',
-    'ISSN_(identifier)',
-    'OCLC_(identifier)',
-    'OSTI_(identifier)',
+    'Social_Science_Research_Network',
+    'Website',
+    'Zentralblatt_MATH',
+    'Zentralblatt_MATH',
 ];
 
 // Lower case, and periods and dashes converted to spaces
@@ -12899,28 +12899,28 @@
 const COMPARE_SERIES_OUT = [' ', ' ', ' ', ' ', ' ', ' ', ' ', '', '', 'adv ', 'exp', 'pharmacol', 'meth ', 'immunol', 'meth ', 'mol', 'med', 'bio', ' ', 'enzymol', 'bio', ' ', ' ', 'embryol', 'anat'];
 
 const ALWAYS_BAD_TITLES = [
+    '{title}',
     'Bloomberg - Are you a robot?',
-    'Page not found',
-    'Breaking News, Analysis, Politics, Blogs, News Photos, Video, Tech Reviews',
     'Breaking News, Analysis, Politics, Blogs, News Photos, Video, Tech Reviews - TIME.com',
-    'Register | British Newspaper Archive',
+    'Breaking News, Analysis, Politics, Blogs, News Photos, Video, Tech Reviews',
+    'DPG Media Privacy Gate',
+    'How to access research remotely',
+    'Log In - ProQuest',
+    'Page not found',
+    'PressReader.com - Connecting People Through News.',
+    'PressReader.com - Connecting People Through News',
+    'PressReader.com - Digital Newspaper & Magazine Subscriptions.',
+    'PressReader.com - Digital Newspaper & Magazine Subscriptions',
     'PressReader.com - Your favorite newspapers and magazines.',
     'PressReader.com - Your favorite newspapers and magazines',
-    'PressReader.com - Connecting People Through News',
-    'PressReader.com - Connecting People Through News.',
-    'PressReader.com – Your favorite newspapers and magazines.',
-    'PressReader.com – Your favorite newspapers and magazines',
-    'PressReader.com – Connecting People Through News',
     'PressReader.com – Connecting People Through News.',
-    'PressReader.com - Digital Newspaper & Magazine Subscriptions',
-    'PressReader.com - Digital Newspaper & Magazine Subscriptions.',
+    'PressReader.com – Connecting People Through News',
     'PressReader.com – Digital Newspaper & Magazine Subscriptions',
-    'How to access research remotely',
-    'Log In - ProQuest',
-    'DPG Media Privacy Gate',
-    'Request Rejected',
-    '{title}',
+    'PressReader.com – Your favorite newspapers and magazines.',
+    'PressReader.com – Your favorite newspapers and magazines',
     'Radware Bot Manager Captcha',
+    'Register | British Newspaper Archive',
+    'Request Rejected',
 ];
 
 const DOI_FREE_PREFIX = [
@@ -13091,11 +13091,11 @@
 ];
 
 const BAD_DOI_ARRAY = [
-    '10.1126/science' => true,
     '' => true,
-    '10.7556/jaoa' => true,
-    '10.1267/science.040579197' => true,
+    '10.0000/Rubbish_bot_failure_test.x' => true,
     '10.0000/Rubbish_bot_failure_test' => true,
     '10.0000/Rubbish_bot_failure_test2' => true,
-    '10.0000/Rubbish_bot_failure_test.x' => true,
+    '10.1126/science' => true,
+    '10.1267/science.040579197' => true,
+    '10.7556/jaoa' => true,
 ];