From 3720de10d2ab7d0e647335fa148b96bd3bd5bdc0 Mon Sep 17 00:00:00 2001 From: un-pogaz <46523284+un-pogaz@users.noreply.github.com> Date: Fri, 24 Jan 2025 11:14:20 +0100 Subject: [PATCH] always use raw-string for regex (manual) ruff 'RUF039' --- recipes/android_com_pl.recipe | 2 +- recipes/benchmark_pl.recipe | 4 +- recipes/blic.recipe | 2 +- recipes/cvecezla.recipe | 2 +- recipes/daum_net.recipe | 2 +- recipes/dnevnik_cro.recipe | 2 +- recipes/dziennik_wschodni.recipe | 4 +- recipes/esenja.recipe | 4 +- recipes/esensja_(rss).recipe | 4 +- recipes/film_web.recipe | 2 +- recipes/gazeta_pl_krakow.recipe | 2 +- recipes/gazeta_pl_warszawa.recipe | 2 +- recipes/granta.recipe | 10 ++--- recipes/in4_pl.recipe | 2 +- recipes/kopalniawiedzy.recipe | 4 +- recipes/le_monde_sub_paper.recipe | 2 +- recipes/nacional_cro.recipe | 2 +- recipes/natemat_pl.recipe | 4 +- recipes/njuz_net.recipe | 2 +- recipes/novilist_novine_hr.recipe | 2 +- recipes/novosti.recipe | 2 +- recipes/nspm.recipe | 2 +- recipes/observatorul_cultural.recipe | 3 +- recipes/pescanik.recipe | 2 +- recipes/root.recipe | 4 +- recipes/rts.recipe | 2 +- recipes/swiatkindle.recipe | 2 +- recipes/tablety_pl.recipe | 4 +- recipes/thecultofghoul.recipe | 2 +- recipes/vecernji_list.recipe | 2 +- recipes/vreme.recipe | 2 +- recipes/wnp.recipe | 4 +- recipes/zeitde_sub.recipe | 26 ++++++------- .../generators/pagebreak_page_generator.py | 2 +- src/calibre/ebooks/compression/tcr.py | 6 +-- .../ebooks/conversion/plugins/epub_input.py | 2 +- .../ebooks/conversion/plugins/epub_output.py | 2 +- .../ebooks/conversion/plugins/rtf_input.py | 2 +- src/calibre/ebooks/conversion/preprocess.py | 2 +- src/calibre/ebooks/conversion/utils.py | 38 +++++++++---------- src/calibre/ebooks/docx/writer/from_html.py | 2 +- src/calibre/ebooks/metadata/pml.py | 10 ++--- src/calibre/ebooks/metadata/txt.py | 2 +- src/calibre/ebooks/mobi/reader/mobi6.py | 3 +- src/calibre/ebooks/oeb/polish/container.py | 2 +- src/calibre/ebooks/pdb/ereader/reader132.py | 8 ++-- src/calibre/ebooks/pdb/header.py | 4 +- src/calibre/ebooks/pdf/pdftohtml.py | 2 +- src/calibre/ebooks/pml/pmlml.py | 8 ++-- src/calibre/ebooks/readability/readability.py | 4 +- src/calibre/ebooks/rtf/rtfml.py | 2 +- src/calibre/ebooks/rtf2xml/process_tokens.py | 2 +- src/calibre/ebooks/snb/snbml.py | 6 +-- src/calibre/ebooks/txt/markdownml.py | 4 +- src/calibre/ebooks/txt/processor.py | 6 +-- src/calibre/ebooks/txt/textileml.py | 6 +-- src/calibre/ebooks/txt/txtml.py | 8 ++-- src/calibre/ebooks/unihandecode/jadecoder.py | 2 +- src/calibre/ebooks/unihandecode/unidecoder.py | 2 +- src/calibre/gui2/fts/search.py | 2 +- src/calibre/gui2/main.py | 2 +- .../gui2/tweak_book/editor/syntax/html.py | 2 +- src/calibre/library/catalogs/utils.py | 4 +- src/calibre/library/comments.py | 2 +- src/calibre/library/custom_columns.py | 2 +- src/calibre/spell/dictionary.py | 2 +- src/calibre/utils/bibtex.py | 2 +- src/calibre/utils/cleantext.py | 2 +- src/calibre/web/fetch/simple.py | 2 +- src/odf/easyliststyle.py | 2 +- 70 files changed, 136 insertions(+), 142 deletions(-) diff --git a/recipes/android_com_pl.recipe b/recipes/android_com_pl.recipe index c62f1ceef4..6265f25011 100644 --- a/recipes/android_com_pl.recipe +++ b/recipes/android_com_pl.recipe @@ -16,5 +16,5 @@ class Android_com_pl(BasicNewsRecipe): remove_tags_after = [{'class': 'post-content'}] remove_tags = [dict(name='ul', attrs={'class': 'tags small-tags'}), dict(name='a', attrs={'onclick': 'return ss_plugin_loadpopup_js(this);'})] preprocess_regexps = [ - (re.compile(u'

.{,1}

', re.DOTALL), lambda match: '')] + (re.compile(r'

.{,1}

', re.DOTALL), lambda match: '')] feeds = [(u'Android', u'http://android.com.pl/feed/')] diff --git a/recipes/benchmark_pl.recipe b/recipes/benchmark_pl.recipe index f96f3364aa..e3e0aef637 100644 --- a/recipes/benchmark_pl.recipe +++ b/recipes/benchmark_pl.recipe @@ -17,8 +17,8 @@ class BenchmarkPl(BasicNewsRecipe): extra_css = 'ul {list-style-type: none;}' no_stylesheets = True use_embedded_content = False - preprocess_regexps = [(re.compile(u'

 Zobacz poprzednie Opinie dnia:.*', # noqa: E501 - re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(u'Więcej o .*?', re.DOTALL | re.IGNORECASE), lambda match: '')] + preprocess_regexps = [(re.compile(u'

 Zobacz poprzednie Opinie dnia:.*', # noqa: E501, RUF039 + re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(u'Więcej o .*?', re.DOTALL | re.IGNORECASE), lambda match: '')] # noqa: RUF039 keep_only_tags = [dict(id=['articleHeader', 'articleGallery']), dict( name='div', attrs={'class': ['m_zwykly', 'gallery']}), dict(id='article')] diff --git a/recipes/blic.recipe b/recipes/blic.recipe index fbd2e463bd..ec44e53123 100644 --- a/recipes/blic.recipe +++ b/recipes/blic.recipe @@ -41,7 +41,7 @@ class Blic(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 remove_tags_before = dict(name='div', attrs={'id': 'article_info'}) remove_tags = [ dict(name=['object', 'link', 'meta', 'base', 'object', 'embed'])] diff --git a/recipes/cvecezla.recipe b/recipes/cvecezla.recipe index 0ae2f8f60e..6a330cb194 100644 --- a/recipes/cvecezla.recipe +++ b/recipes/cvecezla.recipe @@ -27,7 +27,7 @@ class CveceZla(BasicNewsRecipe): 'comment': description, 'tags': 'igre, muzika, film, blog, Srbija', 'publisher': 'Mehmet Krljic', 'language': language } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 remove_tags_before = dict(attrs={'class': 'navigation'}) remove_tags_after = dict(attrs={'class': 'commentlist'}) diff --git a/recipes/daum_net.recipe b/recipes/daum_net.recipe index c1adb61c21..be4b3f15b6 100644 --- a/recipes/daum_net.recipe +++ b/recipes/daum_net.recipe @@ -61,7 +61,7 @@ class MediaDaumRecipe(BasicNewsRecipe): lambda match: ''), (re.compile(r'(]*>[ \t\r\n]*)*', re.DOTALL | re.IGNORECASE), lambda match: ''), - (re.compile(u'(]*>[ \t\r\n]*)*(\u25B6|\u25CF|\u261E|\u24D2|\\(c\\))*\\[[^\\]]*(\u24D2|\\(c\\)|\uAE30\uC0AC|\uC778\uAE30[^\\]]*\uB274\uC2A4)[^\\]]*\\].*', re.DOTALL | re.IGNORECASE), # noqa: E501 + (re.compile(u'(]*>[ \t\r\n]*)*(\u25B6|\u25CF|\u261E|\u24D2|\\(c\\))*\\[[^\\]]*(\u24D2|\\(c\\)|\uAE30\uC0AC|\uC778\uAE30[^\\]]*\uB274\uC2A4)[^\\]]*\\].*', re.DOTALL | re.IGNORECASE), # noqa: E501, RUF039 lambda match: ''), ] diff --git a/recipes/dnevnik_cro.recipe b/recipes/dnevnik_cro.recipe index d2e3303763..6ace469209 100644 --- a/recipes/dnevnik_cro.recipe +++ b/recipes/dnevnik_cro.recipe @@ -42,7 +42,7 @@ class DnevnikCro(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 keep_only_tags = [dict(name='div', attrs={'id': 'article'})] diff --git a/recipes/dziennik_wschodni.recipe b/recipes/dziennik_wschodni.recipe index 9c6c04a214..18cd71d6aa 100644 --- a/recipes/dziennik_wschodni.recipe +++ b/recipes/dziennik_wschodni.recipe @@ -20,8 +20,8 @@ class DziennikWschodni(BasicNewsRecipe): no_stylesheets = True ignore_duplicate_articles = {'title', 'url'} - preprocess_regexps = [(re.compile(u'Czytaj:.*?', re.DOTALL), lambda match: ''), (re.compile(u'Przeczytaj także:.*?', re.DOTALL | re.IGNORECASE), lambda match: ''), # noqa: E501 - (re.compile(u'Przeczytaj również:.*?', re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(u'Zobacz też:.*?', re.DOTALL | re.IGNORECASE), lambda match: '')] # noqa: E501 + preprocess_regexps = [(re.compile(u'Czytaj:.*?', re.DOTALL), lambda match: ''), (re.compile(u'Przeczytaj także:.*?', re.DOTALL | re.IGNORECASE), lambda match: ''), # noqa: E501, RUF039 + (re.compile(u'Przeczytaj również:.*?', re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(u'Zobacz też:.*?', re.DOTALL | re.IGNORECASE), lambda match: '')] # noqa: E501, RUF039 keep_only_tags = [dict(id=['article', 'cover', 'photostory'])] remove_tags = [dict(id=['articleTags', 'articleMeta', 'boxReadIt', 'articleGalleries', 'articleConnections', diff --git a/recipes/esenja.recipe b/recipes/esenja.recipe index 42f43f7192..0417b5d05f 100644 --- a/recipes/esenja.recipe +++ b/recipes/esenja.recipe @@ -45,9 +45,7 @@ class Esensja(BasicNewsRecipe): ''' preprocess_regexps = [(re.compile(r'alt="[^"]*"'), lambda match: ''), - (re.compile( - u'(title|alt)="[^"]*?"', re.DOTALL), lambda match: ''), - ] + (re.compile(r'(title|alt)="[^"]*?"', re.DOTALL), lambda match: '')] def parse_index(self): soup = self.index_to_soup('http://www.esensja.pl/magazyn/') diff --git a/recipes/esensja_(rss).recipe b/recipes/esensja_(rss).recipe index 6ce8b697e1..55630cf6a7 100644 --- a/recipes/esensja_(rss).recipe +++ b/recipes/esensja_(rss).recipe @@ -23,9 +23,7 @@ class EsensjaRSS(BasicNewsRecipe): remove_javascript = True ignore_duplicate_articles = {'title', 'url'} preprocess_regexps = [(re.compile(r'alt="[^"]*"'), lambda match: ''), - (re.compile( - u'(title|alt)="[^"]*?"', re.DOTALL), lambda match: ''), - ] + (re.compile(r'(title|alt)="[^"]*?"', re.DOTALL), lambda match: '')] remove_attributes = ['style', 'bgcolor', 'alt', 'color'] keep_only_tags = [dict(attrs={'class': 'sekcja'}), ] remove_tags_after = dict(id='tekst') diff --git a/recipes/film_web.recipe b/recipes/film_web.recipe index 77c57458be..da8eede0b3 100644 --- a/recipes/film_web.recipe +++ b/recipes/film_web.recipe @@ -23,7 +23,7 @@ class FilmWebPl(BasicNewsRecipe): 'ul.sep-line > li + li::before {content: " | "} ' 'ul.inline {padding:0px;} .vertical-align {display: inline-block;}') preprocess_regexps = [(re.compile(r'', re.DOTALL), lambda match: ''), # fix malformed HTML with 2 body tags... - (re.compile(u'(?:)?\\(kliknij\\,\\ aby powiększyć\\)(?:)?', re.IGNORECASE), lambda m: ''), + (re.compile(u'(?:)?\\(kliknij\\,\\ aby powiększyć\\)(?:)?', re.IGNORECASE), lambda m: ''), # noqa: RUF039 (re.compile(type(u'')(r'(
\s*?
\s*?)+'), re.IGNORECASE), lambda m: '
') ] remove_tags = [dict(attrs={'class':['infoParent', 'likeBar', diff --git a/recipes/gazeta_pl_krakow.recipe b/recipes/gazeta_pl_krakow.recipe index 2469536fd2..cc3067dec3 100644 --- a/recipes/gazeta_pl_krakow.recipe +++ b/recipes/gazeta_pl_krakow.recipe @@ -34,7 +34,7 @@ class gw_krakow(BasicNewsRecipe): # rules for gazeta.pl preprocess_regexps = [ - (re.compile(u'Czytaj więcej.*', re.DOTALL), lambda m: '')] + (re.compile(u'Czytaj więcej.*', re.DOTALL), lambda m: '')] # noqa: RUF039 keep_only_tags = [dict(id='gazeta_article')] remove_tags = [dict(id=['gazeta_article_tools', 'gazeta_article_miniatures']), dict( attrs={'class': ['mod mod_sociallist', 'c0', 'fb', 'voteNeedLogin']})] diff --git a/recipes/gazeta_pl_warszawa.recipe b/recipes/gazeta_pl_warszawa.recipe index a0fa38e851..df3dcd3b40 100644 --- a/recipes/gazeta_pl_warszawa.recipe +++ b/recipes/gazeta_pl_warszawa.recipe @@ -33,7 +33,7 @@ class gw_wawa(BasicNewsRecipe): # rules for gazeta.pl preprocess_regexps = [ - (re.compile(u'Czytaj więcej.*', re.DOTALL), lambda m: '')] + (re.compile(u'Czytaj więcej.*', re.DOTALL), lambda m: '')] # noqa: RUF039 keep_only_tags = [dict(id='gazeta_article')] remove_tags = [dict(id=['gazeta_article_tools', 'gazeta_article_miniatures']), dict( attrs={'class': ['mod mod_sociallist', 'c0', 'fb', 'voteNeedLogin']})] diff --git a/recipes/granta.recipe b/recipes/granta.recipe index 989d4d9700..a0597bdc4e 100644 --- a/recipes/granta.recipe +++ b/recipes/granta.recipe @@ -54,11 +54,11 @@ def solve_captcha(captcha): # Parse into parts pattern = re.compile( - u'(?P[0-9]+)?' - u'\\s*(?P[+×−])\\s*' - u'(?P[0-9]+)' - u'\\s*(=)\\s*' - u'(?P[0-9]+)?', re.UNICODE) + r'(?P[0-9]+)?' + u'\\s*(?P[+×−])\\s*' # noqa: RUF039 + r'(?P[0-9]+)' + r'\s*(=)\s*' + r'(?P[0-9]+)?', re.UNICODE) calculationParts = re.search(pattern, numeric_problem) if calculationParts is None: diff --git a/recipes/in4_pl.recipe b/recipes/in4_pl.recipe index b80b1255a9..b4b8331b35 100644 --- a/recipes/in4_pl.recipe +++ b/recipes/in4_pl.recipe @@ -16,7 +16,7 @@ class in4(BasicNewsRecipe): no_stylesheets = True remove_empty_feeds = True preprocess_regexps = [ - (re.compile(u'', re.DOTALL), lambda match: '')] keep_only_tags = [dict(name='div', attrs={'class': 'left_alone'})] remove_tags_after = dict(name='img', attrs={'title': 'komentarze'}) remove_tags = [dict(name='img', attrs={'title': 'komentarze'})] diff --git a/recipes/kopalniawiedzy.recipe b/recipes/kopalniawiedzy.recipe index f0e8ce9354..5b67df334b 100644 --- a/recipes/kopalniawiedzy.recipe +++ b/recipes/kopalniawiedzy.recipe @@ -29,9 +29,9 @@ class KopalniaWiedzy(BasicNewsRecipe): extra_css = '.topimage {margin-top: 30px}' preprocess_regexps = [ - (re.compile(u''), + (re.compile(r''), lambda match: ''), - (re.compile(u'

'), + (re.compile(r'

'), lambda match: '
') ] diff --git a/recipes/le_monde_sub_paper.recipe b/recipes/le_monde_sub_paper.recipe index e2651ab6d0..698f36e33f 100644 --- a/recipes/le_monde_sub_paper.recipe +++ b/recipes/le_monde_sub_paper.recipe @@ -66,7 +66,7 @@ class LeMondeAbonne(BasicNewsRecipe): dict(name='div', attrs={'class': 'po-copy'}) ] - article_id_pattern = re.compile('[0-9]+\\.html') + article_id_pattern = re.compile(r'[0-9]+\.html') article_url_format = 'http://www.lemonde.fr/journalelectronique/donnees/protege/%Y%m%d/html/' def get_browser(self): diff --git a/recipes/nacional_cro.recipe b/recipes/nacional_cro.recipe index 97333d6c9b..6dd5f6d9ac 100644 --- a/recipes/nacional_cro.recipe +++ b/recipes/nacional_cro.recipe @@ -43,7 +43,7 @@ class NacionalCro(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 remove_tags = [dict(name=['object', 'link', 'embed'])] diff --git a/recipes/natemat_pl.recipe b/recipes/natemat_pl.recipe index ebb69ed476..8ecb9c6c16 100644 --- a/recipes/natemat_pl.recipe +++ b/recipes/natemat_pl.recipe @@ -11,8 +11,8 @@ class NaTemat(BasicNewsRecipe): description = u'informacje, komentarze, opinie' category = 'news' language = 'pl' - preprocess_regexps = [(re.compile(u'Czytaj też\\:.*?', re.IGNORECASE), lambda m: ''), (re.compile(u'Zobacz też\\:.*?', re.IGNORECASE), lambda m: ''), # noqa: E501 - (re.compile(u'Czytaj więcej\\:.*?', re.IGNORECASE), lambda m: ''), (re.compile(u'Czytaj również\\:.*?', re.IGNORECASE), lambda m: '')] # noqa: E501 + preprocess_regexps = [(re.compile(u'Czytaj też\\:.*?', re.IGNORECASE), lambda m: ''), (re.compile(u'Zobacz też\\:.*?', re.IGNORECASE), lambda m: ''), # noqa: E501, RUF039 + (re.compile(u'Czytaj więcej\\:.*?', re.IGNORECASE), lambda m: ''), (re.compile(u'Czytaj również\\:.*?', re.IGNORECASE), lambda m: '')] # noqa: E501, RUF039 cover_url = 'http://blog.plona.pl/wp-content/uploads/2012/05/natemat.png' no_stylesheets = True keep_only_tags = [dict(id='main')] diff --git a/recipes/njuz_net.recipe b/recipes/njuz_net.recipe index bd9ae24395..4977ea42a4 100644 --- a/recipes/njuz_net.recipe +++ b/recipes/njuz_net.recipe @@ -34,7 +34,7 @@ class NjuzNet(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 keep_only_tags = [ dict(attrs={'id': 'entryMeta'}), dict(attrs={'class': 'post'}) diff --git a/recipes/novilist_novine_hr.recipe b/recipes/novilist_novine_hr.recipe index eeb3c1e6f6..61e6f78e71 100644 --- a/recipes/novilist_novine_hr.recipe +++ b/recipes/novilist_novine_hr.recipe @@ -36,7 +36,7 @@ class NoviList_hr(BasicNewsRecipe): p{display: block} ''' - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True diff --git a/recipes/novosti.recipe b/recipes/novosti.recipe index 2c926ab51b..442b2b4c5c 100644 --- a/recipes/novosti.recipe +++ b/recipes/novosti.recipe @@ -35,7 +35,7 @@ class Novosti(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'pretty_print': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 keep_only_tags = [dict(attrs={'class': [ 'articleTitle', 'articleInfo', 'articleLead', 'singlePhoto fl', 'articleBody']})] diff --git a/recipes/nspm.recipe b/recipes/nspm.recipe index f533f4e5fc..a05107c411 100644 --- a/recipes/nspm.recipe +++ b/recipes/nspm.recipe @@ -45,7 +45,7 @@ class Nspm(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'pretty_print': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 remove_tags = [dict(name=['link', 'script', 'meta', 'base', 'img'])] remove_attributes = ['width', 'height', 'lang', 'xmlns:fb', 'xmlns:og', 'vspace', 'hspace', 'type', 'start', 'size'] diff --git a/recipes/observatorul_cultural.recipe b/recipes/observatorul_cultural.recipe index 304024a53c..07aa0d3635 100644 --- a/recipes/observatorul_cultural.recipe +++ b/recipes/observatorul_cultural.recipe @@ -31,8 +31,7 @@ class ObservatorulCultural(BasicNewsRecipe): def parse_index(self): soup = self.index_to_soup( 'http://www.observatorcultural.ro/Arhiva*-archive.html') - issueTag = soup.find('a', href=re.compile( - 'observatorcultural.ro\\/Numarul')) + issueTag = soup.find('a', href=re.compile(r'observatorcultural.ro/Numarul')) issueURL = issueTag['href'] print(issueURL) issueSoup = self.index_to_soup(issueURL) diff --git a/recipes/pescanik.recipe b/recipes/pescanik.recipe index 157bb4b7e2..b5978c82a6 100644 --- a/recipes/pescanik.recipe +++ b/recipes/pescanik.recipe @@ -34,7 +34,7 @@ class Pescanik(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 remove_tags = [ dict(name=['object', 'link', 'meta', 'script', 'iframe', 'embed'])] keep_only_tags = [ diff --git a/recipes/root.recipe b/recipes/root.recipe index 61a2f2c025..d3b129ab7c 100644 --- a/recipes/root.recipe +++ b/recipes/root.recipe @@ -31,9 +31,9 @@ class AdvancedUserRecipe1289939440(BasicNewsRecipe): ] preprocess_regexps = [ - (re.compile(u'

[^<]*]*>', + (re.compile(r'

[^<]*]*>', re.DOTALL), lambda match: '

'), - (re.compile(u'

Tričko tučňák.*', + (re.compile(u'

Tričko tučňák.*', # noqa: RUF039 re.DOTALL), lambda match: '') ] diff --git a/recipes/rts.recipe b/recipes/rts.recipe index 3ed5fba7d6..310feba470 100644 --- a/recipes/rts.recipe +++ b/recipes/rts.recipe @@ -38,7 +38,7 @@ class RTS(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 feeds = [ diff --git a/recipes/swiatkindle.recipe b/recipes/swiatkindle.recipe index 0616e4ff83..95e289f81f 100644 --- a/recipes/swiatkindle.recipe +++ b/recipes/swiatkindle.recipe @@ -25,4 +25,4 @@ class swiatczytnikow(BasicNewsRecipe): dict(name='div', attrs={'class': 'feedflare'})] preprocess_regexps = [ - (re.compile(u'

Czytaj dalej:

'), lambda match: '')] + (re.compile(u'

Czytaj dalej:

'), lambda match: '')] # noqa: RUF039 diff --git a/recipes/tablety_pl.recipe b/recipes/tablety_pl.recipe index 43781dc3a1..76c363a87f 100644 --- a/recipes/tablety_pl.recipe +++ b/recipes/tablety_pl.recipe @@ -15,8 +15,8 @@ class Tablety_pl(BasicNewsRecipe): no_stylesheets = True oldest_article = 8 max_articles_per_feed = 100 - preprocess_regexps = [(re.compile(u'

Przeczytaj także.*?

', re.DOTALL), lambda match: ''), - (re.compile(u'

Przeczytaj koniecznie.*?

', re.DOTALL), lambda match: '')] + preprocess_regexps = [(re.compile(u'

Przeczytaj także.*?

', re.DOTALL), lambda match: ''), # noqa: RUF039 + (re.compile(u'

Przeczytaj koniecznie.*?

', re.DOTALL), lambda match: '')] # noqa: RUF039 keep_only_tags = [dict(attrs={'class': ['featured-image', 'article-content clearfix']})] remove_tags = [dict(attrs={'class': ['comments_icon', 'wp-polls', 'entry-comments', 'wp-polls-loading', 'ts-fab-wrapper', 'entry-footer', 'social-custom']})] diff --git a/recipes/thecultofghoul.recipe b/recipes/thecultofghoul.recipe index 77da5d4299..72a30a9ee2 100644 --- a/recipes/thecultofghoul.recipe +++ b/recipes/thecultofghoul.recipe @@ -27,7 +27,7 @@ class TheCultOfGhoul(BasicNewsRecipe): 'comment': description, 'tags': 'film, blog, srbija, strava, uzas', 'publisher': 'Dejan Ognjanovic', 'language': language } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 feeds = [(u'Posts', u'http://cultofghoul.blogspot.com/feeds/posts/default')] diff --git a/recipes/vecernji_list.recipe b/recipes/vecernji_list.recipe index 5bcd540f18..3f39424eb4 100644 --- a/recipes/vecernji_list.recipe +++ b/recipes/vecernji_list.recipe @@ -43,7 +43,7 @@ class VecernjiList(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': lang, 'pretty_print': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 remove_tags = [ dict(name=['object', 'link', 'embed']), dict( diff --git a/recipes/vreme.recipe b/recipes/vreme.recipe index fc83944a97..febbabf1bb 100644 --- a/recipes/vreme.recipe +++ b/recipes/vreme.recipe @@ -41,7 +41,7 @@ class Vreme(BasicNewsRecipe): 'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True } - preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] # noqa: RUF039 remove_tags_before = dict(attrs={'class': 'toc-heading'}) remove_tags_after = dict(attrs={'class': 'footer'}) diff --git a/recipes/wnp.recipe b/recipes/wnp.recipe index c4ddbf0cca..7cba0290e3 100644 --- a/recipes/wnp.recipe +++ b/recipes/wnp.recipe @@ -10,8 +10,8 @@ class WNP(BasicNewsRecipe): description = u'Wirtualny Nowy Przemysł' category = 'economy' language = 'pl' - preprocess_regexps = [(re.compile(u'Czytaj też:.*?', re.DOTALL), lambda match: ''), - (re.compile(u'Czytaj więcej:.*?', re.DOTALL), lambda match: '')] + preprocess_regexps = [(re.compile(u'Czytaj też:.*?', re.DOTALL), lambda match: ''), # noqa: RUF039 + (re.compile(u'Czytaj więcej:.*?', re.DOTALL), lambda match: '')] # noqa: RUF039 oldest_article = 8 max_articles_per_feed = 100 no_stylesheets = True diff --git a/recipes/zeitde_sub.recipe b/recipes/zeitde_sub.recipe index 3895c3fe8d..f3b044fa32 100644 --- a/recipes/zeitde_sub.recipe +++ b/recipes/zeitde_sub.recipe @@ -48,7 +48,7 @@ class ZeitEPUBAbo(BasicNewsRecipe): preprocess_regexps = [ # filtering for correct dashes ("Gedankenstrich" and "bis") - (re.compile(u' (-|\u2212)(?=[ ,])'), lambda match: u' \u2013'), + (re.compile(u' (-|\u2212)(?=[ ,])'), lambda match: u' \u2013'), # noqa: RUF039 (re.compile(r'(?<=\d)-(?=\d)'), lambda match: u'\u2013'), # number-number (re.compile(r'(?<=\d,)-(?= ?\u20AC)'), lambda match: u'\u2013'), # ,- Euro # fix the number dash number dash for the title image that was broken @@ -130,9 +130,9 @@ class ZeitEPUBAbo(BasicNewsRecipe): (re.compile( r'(?<=

[A-ZÄÖÜ]) (?=[a-zäöü\-])'), lambda match: ''), # before closing quotation - (re.compile(u' \u00AB'), lambda match: u'\u00AB '), + (re.compile(u' \u00AB'), lambda match: u'\u00AB '), # noqa: RUF039 # after opening quotation - (re.compile(u'\u00BB '), lambda match: u' \u00BB'), + (re.compile(u'\u00BB '), lambda match: u' \u00BB'), # noqa: RUF039 # filtering for spaces in large numbers for better readability # end of the number with some character following (re.compile(r'(?<=\d\d)(?=\d\d\d[ ,;\)<\?!-])'), @@ -151,25 +151,25 @@ class ZeitEPUBAbo(BasicNewsRecipe): # filtering for unicode characters that are missing on the Kindle, # try to replace them with meaningful work-arounds # subscript-0 - (re.compile(u'\u2080'), lambda match: '0'), + (re.compile(u'\u2080'), lambda match: '0'), # noqa: RUF039 # subscript-1 - (re.compile(u'\u2081'), lambda match: '1'), + (re.compile(u'\u2081'), lambda match: '1'), # noqa: RUF039 # subscript-2 - (re.compile(u'\u2082'), lambda match: '2'), + (re.compile(u'\u2082'), lambda match: '2'), # noqa: RUF039 # subscript-3 - (re.compile(u'\u2083'), lambda match: '3'), + (re.compile(u'\u2083'), lambda match: '3'), # noqa: RUF039 # subscript-4 - (re.compile(u'\u2084'), lambda match: '4'), + (re.compile(u'\u2084'), lambda match: '4'), # noqa: RUF039 # subscript-5 - (re.compile(u'\u2085'), lambda match: '5'), + (re.compile(u'\u2085'), lambda match: '5'), # noqa: RUF039 # subscript-6 - (re.compile(u'\u2086'), lambda match: '6'), + (re.compile(u'\u2086'), lambda match: '6'), # noqa: RUF039 # subscript-7 - (re.compile(u'\u2087'), lambda match: '7'), + (re.compile(u'\u2087'), lambda match: '7'), # noqa: RUF039 # subscript-8 - (re.compile(u'\u2088'), lambda match: '8'), + (re.compile(u'\u2088'), lambda match: '8'), # noqa: RUF039 # subscript-9 - (re.compile(u'\u2089'), lambda match: '9'), + (re.compile(u'\u2089'), lambda match: '9'), # noqa: RUF039 # always chance CO2 (re.compile(r'CO2'), lambda match: 'CO2'), # CO2 # remove *** paragraphs diff --git a/src/calibre/devices/kindle/apnx_page_generator/generators/pagebreak_page_generator.py b/src/calibre/devices/kindle/apnx_page_generator/generators/pagebreak_page_generator.py index 433961b1eb..0d8870ebb7 100644 --- a/src/calibre/devices/kindle/apnx_page_generator/generators/pagebreak_page_generator.py +++ b/src/calibre/devices/kindle/apnx_page_generator/generators/pagebreak_page_generator.py @@ -21,7 +21,7 @@ class PagebreakPageGenerator(IPageGenerator): ''' Determine pages based on the presence of <*pagebreak*/>. ''' html = mobi_html(mobi_file_path) pages = [] - for m in re.finditer(b'<[^>]*pagebreak[^>]*>', html): + for m in re.finditer(br'<[^>]*pagebreak[^>]*>', html): pages.append(m.end()) return Pages(pages) diff --git a/src/calibre/ebooks/compression/tcr.py b/src/calibre/ebooks/compression/tcr.py index 76e63e958e..e509e19d69 100644 --- a/src/calibre/ebooks/compression/tcr.py +++ b/src/calibre/ebooks/compression/tcr.py @@ -32,7 +32,7 @@ class TCRCompressor: The intent is to create more unused codes. ''' possible_codes = [] - a_code = set(re.findall(b'(?ms).', self.coded_txt)) + a_code = set(re.findall(br'(?ms).', self.coded_txt)) for code in a_code: single_code = set(re.findall(b'(?ms)%s.' % re.escape(code), self.coded_txt)) @@ -57,7 +57,7 @@ class TCRCompressor: ''' Create new codes from codes that occur in pairs often. ''' - possible_new_codes = list(set(re.findall(b'(?ms)..', self.coded_txt))) + possible_new_codes = list(set(re.findall(br'(?ms)..', self.coded_txt))) new_codes_count = [] for c in possible_new_codes: @@ -74,7 +74,7 @@ class TCRCompressor: def compress(self, txt): self._reset() - self.codes = list(set(re.findall(b'(?ms).', txt))) + self.codes = list(set(re.findall(br'(?ms).', txt))) # Replace the text with their corresponding code # FIXME: python3 is native bytearray, but all we want are bytes diff --git a/src/calibre/ebooks/conversion/plugins/epub_input.py b/src/calibre/ebooks/conversion/plugins/epub_input.py index a2404dfd8c..a3222e685f 100644 --- a/src/calibre/ebooks/conversion/plugins/epub_input.py +++ b/src/calibre/ebooks/conversion/plugins/epub_input.py @@ -46,7 +46,7 @@ class EPUBInput(InputFormatPlugin): from lxml import etree idpf_key = opf.raw_unique_identifier if idpf_key: - idpf_key = re.sub('[\u0020\u0009\u000d\u000a]', '', idpf_key) + idpf_key = re.sub(r'[\u0020\u0009\u000d\u000a]', '', idpf_key) idpf_key = hashlib.sha1(idpf_key.encode('utf-8')).digest() key = None for item in opf.identifier_iter(): diff --git a/src/calibre/ebooks/conversion/plugins/epub_output.py b/src/calibre/ebooks/conversion/plugins/epub_output.py index 6a41d42858..5f06404363 100644 --- a/src/calibre/ebooks/conversion/plugins/epub_output.py +++ b/src/calibre/ebooks/conversion/plugins/epub_output.py @@ -503,7 +503,7 @@ class EPUBOutput(OutputFormatPlugin): tag.tag = XHTML('div') # ADE fails to render non breaking hyphens/soft hyphens/zero width spaces - special_chars = re.compile('[\u200b\u00ad]') + special_chars = re.compile(r'[\u200b\u00ad]') for elem in root.iterdescendants('*'): if elem.text: elem.text = special_chars.sub('', elem.text) diff --git a/src/calibre/ebooks/conversion/plugins/rtf_input.py b/src/calibre/ebooks/conversion/plugins/rtf_input.py index 5809e6fc7a..fdf0052022 100644 --- a/src/calibre/ebooks/conversion/plugins/rtf_input.py +++ b/src/calibre/ebooks/conversion/plugins/rtf_input.py @@ -296,7 +296,7 @@ class RTFInput(InputFormatPlugin): res = as_bytes(transform.tostring(result)) # res = res[:100].replace('xmlns:html', 'xmlns') + res[100:] # clean multiple \n - res = re.sub(b'\n+', b'\n', res) + res = re.sub(br'\n+', b'\n', res) # Replace newlines inserted by the 'empty_paragraphs' option in rtf2xml with html blank lines # res = re.sub('\s*', '', res) # res = re.sub('(?<=\n)\n{2}', diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py index 54cc9afb99..f76c70b04b 100644 --- a/src/calibre/ebooks/conversion/preprocess.py +++ b/src/calibre/ebooks/conversion/preprocess.py @@ -94,7 +94,7 @@ class DocAnalysis: elif format == 'spanned_html': linere = re.compile(r'(?<=)', re.DOTALL) elif format == 'txt': - linere = re.compile('.*?\n') + linere = re.compile(r'.*?\n') self.lines = linere.findall(raw) def line_length(self, percent): diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py index fbb626f069..ac1fb1daf1 100644 --- a/src/calibre/ebooks/conversion/utils.py +++ b/src/calibre/ebooks/conversion/utils.py @@ -57,8 +57,8 @@ class HeuristicProcessor: ' chapters. - ' + str(chap)) return '

'+chap+'

\n' else: - delete_whitespace = re.compile('^\\s*(?P.*?)\\s*$') - delete_quotes = re.compile('\'"') + delete_whitespace = re.compile(r'^\s*(?P.*?)\s*$') + delete_quotes = re.compile(r'\'"') txt_chap = delete_quotes.sub('', delete_whitespace.sub('\\g', html2text(chap))) txt_title = delete_quotes.sub('', delete_whitespace.sub('\\g', html2text(title))) self.html_preprocess_sections = self.html_preprocess_sections + 1 @@ -109,7 +109,7 @@ class HeuristicProcessor: be marked up to return true. ''' htm_end_ere = re.compile(r'', re.DOTALL) - line_end_ere = re.compile('(\n|\r|\r\n)', re.DOTALL) + line_end_ere = re.compile(r'(\n|\r|\r\n)', re.DOTALL) htm_end = htm_end_ere.findall(raw) line_end = line_end_ere.findall(raw) tot_htm_ends = len(htm_end) @@ -417,7 +417,7 @@ class HeuristicProcessor: # Add markup naively # TODO - find out if there are cases where there are more than one 
 tag or
             # other types of unmarked html and handle them in some better fashion
-            add_markup = re.compile('(?)(\n)')
+            add_markup = re.compile(r'(?)(\n)')
             html = add_markup.sub('
\n
', html)
         return html
 
@@ -440,7 +440,7 @@ class HeuristicProcessor:
         # Get rid of empty  tags to simplify other processing
         html = re.sub(r'\s*\s*', ' ', html)
         # Delete microsoft 'smart' tags
-        html = re.sub('(?i)', '', html)
+        html = re.sub(r'(?i)', '', html)
         # Re-open self closing paragraph tags
         html = re.sub(r'/]*/>', '
 
', html)
         # Get rid of empty span, bold, font, em, & italics tags
@@ -451,7 +451,7 @@ class HeuristicProcessor:
             html = re.sub(
                 r'\s*{open}\s*({open}\s*{close}\s*){{0,2}}\s*{close}'.format(open=open_fmt_pat, close=close_fmt_pat) , ' ', html)
         # delete surrounding divs from empty paragraphs
-        html = re.sub(']*>\\s*]*>\\s*
\\s*', '
 
', html)
+        html = re.sub(r']*>\s*]*>\s*
\s*', '
 
', html)
         # Empty heading tags
         html = re.sub(r'(?i)\s*', '', html)
         self.deleted_nbsps = True
@@ -538,7 +538,7 @@ class HeuristicProcessor:
             elif content.find('scenebreak') != -1:
                 return content
             else:
-                content = re.sub('(?i)\\d+)[^>]*>', '\n\n'+' style="'+top_margin+bottom_margin+'">', content)
+                content = re.sub(r'(?i)\d+)[^>]*>', r'\n\n style="'+top_margin+bottom_margin+'">', content)
             return content
 
         html = blanks_around_headings.sub(merge_header_whitespace, html)
@@ -551,7 +551,7 @@ class HeuristicProcessor:
 
         html = blanks_n_nopunct.sub(markup_whitespaces, html)
         if self.html_preprocess_sections > self.min_chapters:
-            html = re.sub('(?si)^.*?(?=\\d+).*', '\\g', replacement_break))
+                        width = int(re.sub(r'.*?width(:|=)(?P\d+).*', r'\g', replacement_break))
                     except:
                         scene_break = hr_open+'
'
                         self.log.warn('Invalid replacement scene break'
                                 ' expression, using default')
                     else:
-                        replacement_break = re.sub('(?i)(width=\\d+\\%?|width:\\s*\\d+(\\%|px|pt|em)?;?)', '', replacement_break)
+                        replacement_break = re.sub(r'(?i)(width=\d+\\%?|width:\s*\d+(\%|px|pt|em)?;?)', '', replacement_break)
                         divpercent = (100 - width) // 2
                         hr_open = re.sub(r'45', str(divpercent), hr_open)
                         scene_break = hr_open+replacement_break+''
@@ -617,24 +617,24 @@ class HeuristicProcessor:
             else:
                 from calibre.utils.html2text import html2text
                 replacement_break = html2text(replacement_break)
-                replacement_break = re.sub('\\s', ' ', replacement_break)
+                replacement_break = re.sub(r'\s', ' ', replacement_break)
                 scene_break = self.scene_break_open+replacement_break+'
'
         else:
-            replacement_break = re.sub('\\s', ' ', replacement_break)
+            replacement_break = re.sub(r'\s', ' ', replacement_break)
             scene_break = self.scene_break_open+replacement_break+'
'
 
         return scene_break
 
     def check_paragraph(self, content):
-        content = re.sub('\\s*]*>\\s*', '', content)
-        if re.match('.*["\'.!?:]$', content):
+        content = re.sub(r'\s*]*>\s*', '', content)
+        if re.match(r'.*["\'.!?:]$', content):
             # print('detected this as a paragraph')
             return True
         else:
             return False
 
     def abbyy_processor(self, html):
-        abbyy_line = re.compile('((?P[^"]*?);?">)(?P.*?)(?P
)|(?P]*>))', re.IGNORECASE)
+        abbyy_line = re.compile(r'((?P[^"]*?);?">)(?P.*?)(?P
)|(?P]*>))', re.IGNORECASE)
         empty_paragraph = '\n
 
\n'
         self.in_blockquote = False
         self.previous_was_paragraph = False
@@ -680,7 +680,7 @@ class HeuristicProcessor:
                     if style == 'text-align' and setting != 'left':
                         text_align = style+':'+setting+';'
                     if style == 'text-indent':
-                        setting = int(re.sub('\\s*pt\\s*', '', setting))
+                        setting = int(re.sub(r'\s*pt\s*', '', setting))
                         if 9 < setting < 14:
                             text_indent = indented_text
                         else:
@@ -853,7 +853,7 @@ class HeuristicProcessor:
         # If non-blank scene breaks exist they are center aligned and styled with appropriate margins.
         if getattr(self.extra_opts, 'format_scene_breaks', False):
             self.log.debug('Formatting scene breaks')
-            html = re.sub('(?i)]*>\\s*\\s*', '
', html)
+            html = re.sub(r'(?i)]*>\s*\s*', '
', html)
             html = self.detect_scene_breaks(html)
             html = self.detect_whitespace(html)
             html = self.detect_soft_breaks(html)
@@ -870,9 +870,9 @@ class HeuristicProcessor:
                 replacement_break = self.markup_user_break(replacement_break)
                 if scene_break_count >= 1:
                     html = detected_scene_break.sub(replacement_break, html)
-                    html = re.sub(']*>\\s*
', replacement_break, html)
+                    html = re.sub(r']*>\s*
', replacement_break, html)
                 else:
-                    html = re.sub(']*>\\s*
', replacement_break, html)
+                    html = re.sub(r']*>\s*
', replacement_break, html)
 
         if self.deleted_nbsps:
             # put back non-breaking spaces in empty paragraphs so they render correctly
diff --git a/src/calibre/ebooks/docx/writer/from_html.py b/src/calibre/ebooks/docx/writer/from_html.py
index b82e6ca7aa..c0b53ad756 100644
--- a/src/calibre/ebooks/docx/writer/from_html.py
+++ b/src/calibre/ebooks/docx/writer/from_html.py
@@ -62,7 +62,7 @@ class TextRun:
         self.first_html_parent = first_html_parent
         if self.ws_pat is None:
             TextRun.ws_pat = self.ws_pat = re.compile(r'\s+')
-            TextRun.soft_hyphen_pat = self.soft_hyphen_pat = re.compile('(\u00ad)')
+            TextRun.soft_hyphen_pat = self.soft_hyphen_pat = re.compile(r'(\u00ad)')
         self.style = style
         self.texts = []
         self.link = None
diff --git a/src/calibre/ebooks/metadata/pml.py b/src/calibre/ebooks/metadata/pml.py
index 0fa91dc071..e0df26a905 100644
--- a/src/calibre/ebooks/metadata/pml.py
+++ b/src/calibre/ebooks/metadata/pml.py
@@ -42,21 +42,21 @@ def get_metadata(stream, extract_cover=True):
     for comment in re.findall(br'(?ms)\\v.*?\\v', pml):
         m = re.search(br'TITLE="(.*?)"', comment)
         if m:
-            mi.title = re.sub('[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
+            mi.title = re.sub(r'[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
         m = re.search(br'AUTHOR="(.*?)"', comment)
         if m:
             if mi.authors == [_('Unknown')]:
                 mi.authors = []
-            mi.authors.append(re.sub('[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace'))))
+            mi.authors.append(re.sub(r'[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace'))))
         m = re.search(br'PUBLISHER="(.*?)"', comment)
         if m:
-            mi.publisher = re.sub('[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
+            mi.publisher = re.sub(r'[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
         m = re.search(br'COPYRIGHT="(.*?)"', comment)
         if m:
-            mi.rights = re.sub('[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
+            mi.rights = re.sub(r'[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
         m = re.search(br'ISBN="(.*?)"', comment)
         if m:
-            mi.isbn = re.sub('[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
+            mi.isbn = re.sub(r'[\x00-\x1f]', '', prepare_string_for_xml(m.group(1).strip().decode('cp1252', 'replace')))
 
     return mi
 
diff --git a/src/calibre/ebooks/metadata/txt.py b/src/calibre/ebooks/metadata/txt.py
index 496ee9c03f..de0421cb74 100644
--- a/src/calibre/ebooks/metadata/txt.py
+++ b/src/calibre/ebooks/metadata/txt.py
@@ -31,7 +31,7 @@ def get_metadata(stream, extract_cover=True):
 
     mdata = mdata[:1024]
 
-    mo = re.search('(?u)^[ ]*(?P.+)[ ]*(\n{3}|(\r\n){3}|\r{3})[ ]*(?P<author>.+)[ ]*(\n|\r\n|\r)$', mdata)
+    mo = re.search(r'(?u)^[ ]*(?P<title>.+)[ ]*(\n{3}|(\r\n){3}|\r{3})[ ]*(?P<author>.+)[ ]*(\n|\r\n|\r)$', mdata)
     if mo is not None:
         mi.title = mo.group('title')
         mi.authors = mo.group('author').split(',')
diff --git a/src/calibre/ebooks/mobi/reader/mobi6.py b/src/calibre/ebooks/mobi/reader/mobi6.py
index dfdc3af089..f81fee5cc2 100644
--- a/src/calibre/ebooks/mobi/reader/mobi6.py
+++ b/src/calibre/ebooks/mobi/reader/mobi6.py
@@ -393,8 +393,7 @@ class MobiReader:
             self.processed_html = self.processed_html.replace('</html>', '')
 
     def remove_random_bytes(self, html):
-        return re.sub('\x14|\x15|\x19|\x1c|\x1d|\xef|\x12|\x13|\xec|\x08|\x01|\x02|\x03|\x04|\x05|\x06|\x07',
-                    '', html)
+        return re.sub(r'\x14|\x15|\x19|\x1c|\x1d|\xef|\x12|\x13|\xec|\x08|\x01|\x02|\x03|\x04|\x05|\x06|\x07', '', html)
 
     def ensure_unit(self, raw, unit='px'):
         if re.search(r'\d+$', raw) is not None:
diff --git a/src/calibre/ebooks/oeb/polish/container.py b/src/calibre/ebooks/oeb/polish/container.py
index 0bc2f598fa..3734ed1c21 100644
--- a/src/calibre/ebooks/oeb/polish/container.py
+++ b/src/calibre/ebooks/oeb/polish/container.py
@@ -1340,7 +1340,7 @@ class EpubContainer(Container):
                     break
         if raw_unique_identifier is not None:
             idpf_key = raw_unique_identifier
-            idpf_key = re.sub('[\u0020\u0009\u000d\u000a]', '', idpf_key)
+            idpf_key = re.sub(r'[\u0020\u0009\u000d\u000a]', '', idpf_key)
             idpf_key = hashlib.sha1(idpf_key.encode('utf-8')).digest()
         return package_id, raw_unique_identifier, idpf_key
 
diff --git a/src/calibre/ebooks/pdb/ereader/reader132.py b/src/calibre/ebooks/pdb/ereader/reader132.py
index f479862ad5..c57225dbac 100644
--- a/src/calibre/ebooks/pdb/ereader/reader132.py
+++ b/src/calibre/ebooks/pdb/ereader/reader132.py
@@ -124,8 +124,8 @@ class Reader132(FormatReader):
 
         if self.header_record.footnote_count > 0:
             html += '<br /><h1>%s</h1>' % _('Footnotes')
-            footnoteids = re.findall(
-                '\\w+(?=\x00)', self.section_data(self.header_record.footnote_offset).decode('cp1252' if self.encoding is None else self.encoding))
+            footnoteids = re.findall(r'\w+(?=\x00)',
+                self.section_data(self.header_record.footnote_offset).decode('cp1252' if self.encoding is None else self.encoding))
             for fid, i in enumerate(range(self.header_record.footnote_offset + 1, self.header_record.footnote_offset + self.header_record.footnote_count)):
                 self.log.debug('Extracting footnote page %i' % i)
                 if fid < len(footnoteids):
@@ -136,8 +136,8 @@ class Reader132(FormatReader):
 
         if self.header_record.sidebar_count > 0:
             html += '<br /><h1>%s</h1>' % _('Sidebar')
-            sidebarids = re.findall(
-                '\\w+(?=\x00)', self.section_data(self.header_record.sidebar_offset).decode('cp1252' if self.encoding is None else self.encoding))
+            sidebarids = re.findall(r'\w+(?=\x00)',
+                self.section_data(self.header_record.sidebar_offset).decode('cp1252' if self.encoding is None else self.encoding))
             for sid, i in enumerate(range(self.header_record.sidebar_offset + 1, self.header_record.sidebar_offset + self.header_record.sidebar_count)):
                 self.log.debug('Extracting sidebar page %i' % i)
                 if sid < len(sidebarids):
diff --git a/src/calibre/ebooks/pdb/header.py b/src/calibre/ebooks/pdb/header.py
index 4c990abeae..e6252210e9 100644
--- a/src/calibre/ebooks/pdb/header.py
+++ b/src/calibre/ebooks/pdb/header.py
@@ -32,7 +32,7 @@ class PdbHeaderReader:
 
     def name(self):
         self.stream.seek(0)
-        return re.sub(b'[^-A-Za-z0-9 ]+', b'_', self.stream.read(32).replace(b'\x00', b''))
+        return re.sub(br'[^-A-Za-z0-9 ]+', b'_', self.stream.read(32).replace(b'\x00', b''))
 
     def full_section_info(self, number):
         if not (0 <= number < self.num_sections):
@@ -70,7 +70,7 @@ class PdbHeaderBuilder:
         self.identity = identity.ljust(3, '\x00')[:8].encode('utf-8')
         if isinstance(title, str):
             title = title.encode('ascii', 'replace')
-        self.title = b'%s\x00' % re.sub(b'[^-A-Za-z0-9 ]+', b'_', title).ljust(31, b'\x00')[:31]
+        self.title = b'%s\x00' % re.sub(br'[^-A-Za-z0-9 ]+', b'_', title).ljust(31, b'\x00')[:31]
 
     def build_header(self, section_lengths, out_stream):
         '''
diff --git a/src/calibre/ebooks/pdf/pdftohtml.py b/src/calibre/ebooks/pdf/pdftohtml.py
index 7f0aa9d12f..9324d3fb24 100644
--- a/src/calibre/ebooks/pdf/pdftohtml.py
+++ b/src/calibre/ebooks/pdf/pdftohtml.py
@@ -94,7 +94,7 @@ def pdftohtml(output_dir, pdf_path, no_images, as_xml=False):
                 raw = re.sub(r'<a id="(\d+)"', r'<a id="p\1"', raw, flags=re.I)
                 raw = re.sub(r'<a href="index.html#(\d+)"', r'<a href="#p\1"', raw, flags=re.I)
                 raw = xml_replace_entities(raw)
-                raw = re.sub('[\u00a0\u2029]', ' ', raw)
+                raw = re.sub(r'[\u00a0\u2029]', ' ', raw)
 
                 i.write(raw.encode('utf-8'))
 
diff --git a/src/calibre/ebooks/pml/pmlml.py b/src/calibre/ebooks/pml/pmlml.py
index b787010ba4..37bda0735a 100644
--- a/src/calibre/ebooks/pml/pmlml.py
+++ b/src/calibre/ebooks/pml/pmlml.py
@@ -196,7 +196,7 @@ class PMLMLizer:
 
         # Turn all characters that cannot be represented by themself into their
         # PML code equivalent
-        text = re.sub('[^\x00-\x7f]', lambda x: unipmlcode(x.group()), text)
+        text = re.sub(r'[^\x00-\x7f]', lambda x: unipmlcode(x.group()), text)
 
         # Remove excess spaces at beginning and end of lines
         text = re.sub(r'(?m)^[ ]+', '', text)
@@ -209,14 +209,14 @@ class PMLMLizer:
         text = re.sub(r'(\\c\s*\\c\s*){2,}', r'\\c \n\\c\n', text)
 
         # Remove excessive newlines.
-        text = re.sub('\n[ ]+\n', '\n\n', text)
+        text = re.sub(r'\n[ ]+\n', '\n\n', text)
         if self.opts.remove_paragraph_spacing:
-            text = re.sub('\n{2,}', '\n', text)
+            text = re.sub(r'\n{2,}', '\n', text)
             # Only indent lines that don't have special formatting
             text = re.sub(r'(?imu)^(?P<text>.+)$', lambda mo: mo.group('text')
                           if re.search(r'\\[XxCmrctTp]', mo.group('text')) else '        %s' % mo.group('text'), text)
         else:
-            text = re.sub('\n{3,}', '\n\n', text)
+            text = re.sub(r'\n{3,}', '\n\n', text)
 
         return text
 
diff --git a/src/calibre/ebooks/readability/readability.py b/src/calibre/ebooks/readability/readability.py
index dc4e7f0225..38760af55d 100644
--- a/src/calibre/ebooks/readability/readability.py
+++ b/src/calibre/ebooks/readability/readability.py
@@ -61,8 +61,8 @@ def to_int(x):
 
 
 def clean(text):
-    text = re.sub('\\s*\n\\s*', '\n', text)
-    text = re.sub('[ \t]{2,}', ' ', text)
+    text = re.sub(r'\s*\n\s*', '\n', text)
+    text = re.sub(r'[ \t]{2,}', ' ', text)
     return text.strip()
 
 
diff --git a/src/calibre/ebooks/rtf/rtfml.py b/src/calibre/ebooks/rtf/rtfml.py
index 2559fb516a..73e872d046 100644
--- a/src/calibre/ebooks/rtf/rtfml.py
+++ b/src/calibre/ebooks/rtf/rtfml.py
@@ -199,7 +199,7 @@ class RTFMLizer:
 
         # Remove excessive spaces
         text = re.sub(r'[ ]{2,}', ' ', text)
-        text = re.sub('\t{2,}', '\t', text)
+        text = re.sub(r'\t{2,}', '\t', text)
         text = text.replace('\t ', '\t')
 
         # Remove excessive line breaks
diff --git a/src/calibre/ebooks/rtf2xml/process_tokens.py b/src/calibre/ebooks/rtf2xml/process_tokens.py
index 26b6dfe799..884e589033 100644
--- a/src/calibre/ebooks/rtf2xml/process_tokens.py
+++ b/src/calibre/ebooks/rtf2xml/process_tokens.py
@@ -719,7 +719,7 @@ class ProcessTokens:
     def divide_num(self, numerator, denominator):
         try:
             # calibre why ignore negative number? Wrong in case of \fi
-            numerator = float(re.search('[0-9.\\-]+', numerator).group())
+            numerator = float(re.search(r'[0-9.\-]+', numerator).group())
         except TypeError:
             if self.__run_level > 3:
                 msg = ('No number to process?\nthis indicates that the token \\(\\li\\) \
diff --git a/src/calibre/ebooks/snb/snbml.py b/src/calibre/ebooks/snb/snbml.py
index 54da31fcbb..43534bddb3 100644
--- a/src/calibre/ebooks/snb/snbml.py
+++ b/src/calibre/ebooks/snb/snbml.py
@@ -162,12 +162,12 @@ class SNBMLizer:
         # text = re.sub('[ ]{2,}', ' ', text)
 
         # Remove excessive newlines.
-        text = re.sub('\n[ ]+\n', '\n\n', text)
+        text = re.sub(r'\n[ ]+\n', '\n\n', text)
         if self.opts.remove_paragraph_spacing:
-            text = re.sub('\n{2,}', '\n', text)
+            text = re.sub(r'\n{2,}', '\n', text)
             text = re.sub(r'(?imu)^(?=.)', '\t', text)
         else:
-            text = re.sub('\n{3,}', '\n\n', text)
+            text = re.sub(r'\n{3,}', '\n\n', text)
 
         # Replace spaces at the beginning and end of lines
         text = re.sub(r'(?imu)^[ ]+', '', text)
diff --git a/src/calibre/ebooks/txt/markdownml.py b/src/calibre/ebooks/txt/markdownml.py
index 0e8d7512c8..65684a9e20 100644
--- a/src/calibre/ebooks/txt/markdownml.py
+++ b/src/calibre/ebooks/txt/markdownml.py
@@ -58,7 +58,7 @@ class MarkdownMLizer(OEB2HTML):
         # Remove tabs that aren't at the beginning of a line
         new_text = []
         for l in text.splitlines():
-            start = re.match('\t+', l)
+            start = re.match(r'\t+', l)
             if start:
                 start = start.group()
             else:
@@ -71,7 +71,7 @@ class MarkdownMLizer(OEB2HTML):
         text = re.sub(r'(?msu)^[ ]+$', '', text)
 
         # Reduce blank lines
-        text = re.sub('(?msu)\n{7,}', '\n' * 6, text)
+        text = re.sub(r'(?msu)\n{7,}', '\n' * 6, text)
 
         # Remove blank lines at beginning and end of document.
         text = re.sub(r'^\s*', '', text)
diff --git a/src/calibre/ebooks/txt/processor.py b/src/calibre/ebooks/txt/processor.py
index c818cfe2f2..5af1171685 100644
--- a/src/calibre/ebooks/txt/processor.py
+++ b/src/calibre/ebooks/txt/processor.py
@@ -31,7 +31,7 @@ def clean_txt(txt):
     txt = '\n'.join([line.rstrip() for line in txt.splitlines()])
 
     # Replace whitespace at the beginning of the line with  
-    txt = re.sub('(?m)(?<=^)([ ]{2,}|\t+)(?=.)', ' ' * 4, txt)
+    txt = re.sub(r'(?m)(?<=^)([ ]{2,}|\t+)(?=.)', ' ' * 4, txt)
 
     # Condense redundant spaces
     txt = re.sub(r'[ ]{2,}', ' ', txt)
@@ -40,7 +40,7 @@ def clean_txt(txt):
     txt = re.sub(r'^\s+(?=.)', '', txt)
     txt = re.sub(r'(?<=.)\s+$', '', txt)
     # Remove excessive line breaks.
-    txt = re.sub('\n{5,}', '\n\n\n\n', txt)
+    txt = re.sub(r'\n{5,}', '\n\n\n\n', txt)
     # remove ASCII invalid chars : 0 to 8 and 11-14 to 24
     txt = clean_ascii_chars(txt)
 
@@ -190,7 +190,7 @@ def separate_paragraphs_single_line(txt):
 
 
 def separate_paragraphs_print_formatted(txt):
-    txt = re.sub('(?miu)^(?P<indent>\t+|[ ]{2,})(?=.)', lambda mo: '\n%s' % mo.group('indent'), txt)
+    txt = re.sub(r'(?miu)^(?P<indent>\t+|[ ]{2,})(?=.)', lambda mo: '\n%s' % mo.group('indent'), txt)
     return txt
 
 
diff --git a/src/calibre/ebooks/txt/textileml.py b/src/calibre/ebooks/txt/textileml.py
index 36a27366e2..b795f0116e 100644
--- a/src/calibre/ebooks/txt/textileml.py
+++ b/src/calibre/ebooks/txt/textileml.py
@@ -109,16 +109,16 @@ class TextileMLizer(OEB2HTML):
 
         # reduce blank lines
         text = re.sub(r'\n{3}', r'\n\np. \n\n', text)
-        text = re.sub('%\n(p[<>=]{1,2}\\.|p\\.)', r'%\n\n\1', text)
+        text = re.sub(r'%\n(p[<>=]{1,2}\.|p\.)', r'%\n\n\1', text)
         # Check span following blank para
         text = re.sub(r'\n+ +%', r' %', text)
-        text = re.sub('p[<>=]{1,2}\\.\n\n?', r'', text)
+        text = re.sub(r'p[<>=]{1,2}\.\n\n?', '', text)
         # blank paragraph
         text = re.sub(r'\n(p.*\.)\n', r'\n\1 \n\n', text)
         # blank paragraph
         text = text.replace('\n\xa0', '\np. ')
         # blank paragraph
-        text = re.sub('\np[<>=]{1,2}?\\. \xa0', r'\np. ', text)
+        text = re.sub(r'\np[<>=]{1,2}?\\. \xa0', r'\np. ', text)
         text = re.sub(r'(^|\n)(p.*\. ?\n)(p.*\.)', r'\1\3', text)
         text = re.sub(r'\n(p\. \n)(p.*\.|h.*\.)', r'\n\2', text)
         # sort out spaces in tables
diff --git a/src/calibre/ebooks/txt/txtml.py b/src/calibre/ebooks/txt/txtml.py
index 9c811f2d77..2209ae495d 100644
--- a/src/calibre/ebooks/txt/txtml.py
+++ b/src/calibre/ebooks/txt/txtml.py
@@ -123,19 +123,19 @@ class TXTMLizer:
         text = text.replace('\f+', ' ')
 
         # Single line paragraph.
-        text = re.sub('(?<=.)\n(?=.)', ' ', text)
+        text = re.sub(r'(?<=.)\n(?=.)', ' ', text)
 
         # Remove multiple spaces.
         text = re.sub(r'[ ]{2,}', ' ', text)
 
         # Remove excessive newlines.
-        text = re.sub('\n[ ]+\n', '\n\n', text)
+        text = re.sub(r'\n[ ]+\n', '\n\n', text)
         if self.opts.remove_paragraph_spacing:
-            text = re.sub('\n{2,}', '\n', text)
+            text = re.sub(r'\n{2,}', '\n', text)
             text = re.sub(r'(?msu)^(?P<t>[^\t\n]+?)$', lambda mo: '%s\n\n' % mo.group('t'), text)
             text = re.sub(r'(?msu)(?P<b>[^\n])\n+(?P<t>[^\t\n]+?)(?=\n)', lambda mo: '{}\n\n\n\n\n\n{}'.format(mo.group('b'), mo.group('t')), text)
         else:
-            text = re.sub('\n{7,}', '\n\n\n\n\n\n', text)
+            text = re.sub(r'\n{7,}', '\n\n\n\n\n\n', text)
 
         # Replace spaces at the beginning and end of lines
         # We don't replace tabs because those are only added
diff --git a/src/calibre/ebooks/unihandecode/jadecoder.py b/src/calibre/ebooks/unihandecode/jadecoder.py
index 31fcc11ad5..ed1e05798e 100644
--- a/src/calibre/ebooks/unihandecode/jadecoder.py
+++ b/src/calibre/ebooks/unihandecode/jadecoder.py
@@ -87,4 +87,4 @@ class Jadecoder(Unidecoder):
                 text = self.conv.do(text)
         except Exception:
             pass
-        return re.sub('[^\x00-\x7f]', lambda x: self.replace_point(x.group()), text)
+        return re.sub(r'[^\x00-\x7f]', lambda x: self.replace_point(x.group()), text)
diff --git a/src/calibre/ebooks/unihandecode/unidecoder.py b/src/calibre/ebooks/unihandecode/unidecoder.py
index 6d7c9f16f7..aba5069030 100644
--- a/src/calibre/ebooks/unihandecode/unidecoder.py
+++ b/src/calibre/ebooks/unihandecode/unidecoder.py
@@ -73,7 +73,7 @@ class Unidecoder:
 
     def decode(self, text):
         # Replace characters larger than 127 with their ASCII equivalent.
-        return re.sub('[^\x00-\x7f]',lambda x: self.replace_point(x.group()), text)
+        return re.sub(r'[^\x00-\x7f]', lambda x: self.replace_point(x.group()), text)
 
     def replace_point(self, codepoint):
         '''
diff --git a/src/calibre/gui2/fts/search.py b/src/calibre/gui2/fts/search.py
index 078d97f5aa..83655a5a74 100644
--- a/src/calibre/gui2/fts/search.py
+++ b/src/calibre/gui2/fts/search.py
@@ -733,7 +733,7 @@ class ResultDetails(QWidget):
     def render_results(self, results, individual_match=None):
         html = []
         space_pat = re.compile(r'\s+')
-        markup_pat = re.compile('\x1d')
+        markup_pat = re.compile(r'\x1d')
 
         def markup_text(text):
             count = 0
diff --git a/src/calibre/gui2/main.py b/src/calibre/gui2/main.py
index 7166f6d792..707c31ec25 100644
--- a/src/calibre/gui2/main.py
+++ b/src/calibre/gui2/main.py
@@ -433,7 +433,7 @@ def run_gui_(opts, args, app, gui_debug=None):
             winutil.prepare_for_restart()
             with open(debugfile, 'r+b') as f:
                 raw = f.read()
-                raw = re.sub(b'(?<!\r)\n', b'\r\n', raw)
+                raw = re.sub(br'(?<!\r)\n', br'\r\n', raw)
                 f.seek(0)
                 f.truncate()
                 f.write(raw)
diff --git a/src/calibre/gui2/tweak_book/editor/syntax/html.py b/src/calibre/gui2/tweak_book/editor/syntax/html.py
index 9ac523474c..ea88c3dfde 100644
--- a/src/calibre/gui2/tweak_book/editor/syntax/html.py
+++ b/src/calibre/gui2/tweak_book/editor/syntax/html.py
@@ -39,7 +39,7 @@ attribute_name_pat = re.compile(r'''[^%s"'/><=]+''' % space_chars)
 self_closing_pat = re.compile(r'/\s*>')
 unquoted_val_pat = re.compile(r'''[^%s'"=<>`]+''' % space_chars)
 cdata_close_pats = {x:re.compile(r'</%s' % x, flags=re.I) for x in cdata_tags}
-nbsp_pat = re.compile('[\xa0\u2000-\u200A\u202F\u205F\u3000\u2011-\u2015\uFE58\uFE63\uFF0D]+')  # special spaces and hyphens
+nbsp_pat = re.compile(r'[\xa0\u2000-\u200A\u202F\u205F\u3000\u2011-\u2015\uFE58\uFE63\uFF0D]+')  # special spaces and hyphens
 
 NORMAL = 0
 IN_OPENING_TAG = 1
diff --git a/src/calibre/library/catalogs/utils.py b/src/calibre/library/catalogs/utils.py
index b297db3cf9..9a3a2b6ae8 100644
--- a/src/calibre/library/catalogs/utils.py
+++ b/src/calibre/library/catalogs/utils.py
@@ -119,7 +119,7 @@ class NumberToText:  # {{{
             self.text = NumberToText(self.number.replace('%',' percent')).text
 
         # Test for decimal
-        elif re.search('\\.',self.number):
+        elif '.' in self.number:
             if self.verbose:
                 self.log('Decimal: %s' % self.number)
             self.number_as_float = self.number
@@ -150,7 +150,7 @@ class NumberToText:  # {{{
             self.text = NumberToText(self.number_as_float).text
 
         # Test for hybrid e.g., 'K2, 2nd, 10@10'
-        elif re.search('[\\D]+', self.number):
+        elif re.search(r'[\D]+', self.number):
             if self.verbose:
                 self.log('Hybrid: %s' % self.number)
             # Split the token into number/text
diff --git a/src/calibre/library/comments.py b/src/calibre/library/comments.py
index 661fe829de..a896928a8b 100644
--- a/src/calibre/library/comments.py
+++ b/src/calibre/library/comments.py
@@ -11,7 +11,7 @@ from calibre.utils.html2text import html2text
 
 # Hackish - ignoring sentences ending or beginning in numbers to avoid
 # confusion with decimal points.
-lost_cr_pat = re.compile('([a-z])([\\.\\?!])([A-Z])')
+lost_cr_pat = re.compile(r'([a-z])([\.\?!])([A-Z])')
 lost_cr_exception_pat = re.compile(r'(Ph\.D)|(D\.Phil)|((Dr|Mr|Mrs|Ms)\.[A-Z])')
 sanitize_pat = re.compile(r'<script|<table|<tr|<td|<th|<style|<iframe',
         re.IGNORECASE)
diff --git a/src/calibre/library/custom_columns.py b/src/calibre/library/custom_columns.py
index 7d6fe96593..85043bc0f4 100644
--- a/src/calibre/library/custom_columns.py
+++ b/src/calibre/library/custom_columns.py
@@ -674,7 +674,7 @@ class CustomColumns:
             editable=True, display={}):
         if not label:
             raise ValueError(_('No label was provided'))
-        if re.match('^\\w*$', label) is None or not label[0].isalpha() or label.lower() != label:
+        if re.match(r'^\w*$', label) is None or not label[0].isalpha() or label.lower() != label:
             raise ValueError(_('The label must contain only lower case letters, digits and underscores, and start with a letter'))
         if datatype not in self.CUSTOM_DATA_TYPES:
             raise ValueError('%r is not a supported data type'%datatype)
diff --git a/src/calibre/spell/dictionary.py b/src/calibre/spell/dictionary.py
index a26f57e7f6..27dff56061 100644
--- a/src/calibre/spell/dictionary.py
+++ b/src/calibre/spell/dictionary.py
@@ -193,7 +193,7 @@ def load_dictionary(dictionary):
 class Dictionaries:
 
     def __init__(self):
-        self.remove_hyphenation = re.compile('[\u2010-]+')
+        self.remove_hyphenation = re.compile(r'[\u2010-]+')
         self.negative_pat = re.compile(r'-[.\d+]')
         self.fix_punctuation_pat = re.compile(r'''[:.]''')
         self.dictionaries = {}
diff --git a/src/calibre/utils/bibtex.py b/src/calibre/utils/bibtex.py
index e3f48f84c4..71a2076d39 100644
--- a/src/calibre/utils/bibtex.py
+++ b/src/calibre/utils/bibtex.py
@@ -2553,7 +2553,7 @@ class BibTeX:
         self.ascii_bibtex = True
         # This substitution is based on the description of cite key restrictions at
         # http://bibdesk.sourceforge.net/manual/BibDesk%20Help_2.html
-        self.invalid_cit = re.compile('[ "@\',\\#}{~%&$^]')
+        self.invalid_cit = re.compile(r'[ "@\',\#}{~%&$^]')
         self.upper = re.compile('[' +
             string.ascii_uppercase + ']')
         self.escape = re.compile(r'[#&%_]')
diff --git a/src/calibre/utils/cleantext.py b/src/calibre/utils/cleantext.py
index 394ca9eeba..47b2f4d745 100644
--- a/src/calibre/utils/cleantext.py
+++ b/src/calibre/utils/cleantext.py
@@ -94,4 +94,4 @@ def unescape(text, rm=False, rchar=''):
         if rm:
             return rchar  # replace by char
         return text  # leave as is
-    return re.sub('&#?\\w+;', fixup, text)
+    return re.sub(r'&#?\w+;', fixup, text)
diff --git a/src/calibre/web/fetch/simple.py b/src/calibre/web/fetch/simple.py
index 82e9da36fa..518040f610 100644
--- a/src/calibre/web/fetch/simple.py
+++ b/src/calibre/web/fetch/simple.py
@@ -545,7 +545,7 @@ class RecursiveFetcher:
                     dsrc = self.fetch_url(iurl)
                     newbaseurl = dsrc.newurl
                     if len(dsrc) == 0 or \
-                       len(re.compile(b'<!--.*?-->', re.DOTALL).sub(b'', dsrc).strip()) == 0:
+                       len(re.compile(br'<!--.*?-->', re.DOTALL).sub(b'', dsrc).strip()) == 0:
                         raise ValueError('No content at URL %r'%iurl)
                     if callable(self.encoding):
                         dsrc = self.encoding(dsrc)
diff --git a/src/odf/easyliststyle.py b/src/odf/easyliststyle.py
index 81dcc2cc7a..9b23d1cf17 100644
--- a/src/odf/easyliststyle.py
+++ b/src/odf/easyliststyle.py
@@ -60,7 +60,7 @@ def styleFromList(styleName, specArray, spacing, showAllLevels):
     displayLevels = 0
     listStyle = ListStyle(name=styleName)
     numFormatPattern = re.compile(r'([1IiAa])')
-    cssLengthPattern = re.compile('([^a-z]+)\\s*([a-z]+)?')
+    cssLengthPattern = re.compile(r'([^a-z]+)\s*([a-z]+)?')
     m = cssLengthPattern.search(spacing)
     if (m is not None):
         cssLengthNum = float(m.group(1))