pep8

Changelog.txt

@@ -23,6 +23,37 @@
 # - title by author
 # }}}
 
+{{{ 7.10.0 2024-05-03
+
+:: new features
+
+- Export of calibre data: Ensure individual part files in the exported data are no larger than one gigabyte even
+  if the library contains individual files larger than that size.
+
+  Note that this means that exports created by calibre from this version
+  on will not be importable by earlier versions. However, exports from
+  earlier versions should still be importable.
+
+- Edit book: Spell check: Add options to exclude words in ALL CAPS or with numbers or in camelCase/snake_case from the list of words
+
+- Allow easily inverting the current search via the right click menu on the search box
+
+:: bug fixes
+
+- [2064546] Kobo driver: Fix database unsupported error with newest firmware
+
+- [2063301] DOCX Input: Fix text elements containing only whitespace being incorrectly ignored
+
+- Bulk metadata dialog: Do not fail when setting covers from ebook files and some of the files have invalid covers
+
+:: improved recipes
+- Economist
+- The Week
+- Caravan Magazine
+- Financial Times
+
+}}}
+
 {{{ 7.9.0 2024-04-19
 
 :: new features

recipes/caravan_magazine.recipe

@@ -1,7 +1,7 @@
 import json
-from urllib.parse import urlparse, quote
+from urllib.parse import quote, urlparse
 
-from calibre.web.feeds.news import BasicNewsRecipe, classes
+from calibre.web.feeds.news import BasicNewsRecipe
 from mechanize import Request
 
 
@@ -26,7 +26,7 @@ def parse_body(x):
             yield ''.join(parse_p(p))
         yield '</p>\n'
     elif x.get('type', '') in {'blockquote', 'pullquote'}:
-        yield '<blockquote>' 
+        yield '<blockquote>'
         for p in x.get('content', {}):
             yield from parse_body(p)
         yield '</blockquote>'
@@ -36,7 +36,7 @@ def parse_body(x):
             yield from parse_body(p)
     elif x.get('type', '') in {'caption', 'credit'}:
         yield '<div class="sub">'
-        for div in x.get('content', {}):    
+        for div in x.get('content', {}):
             yield ''.join(parse_p(div))
         yield '</div>\n'
     elif x.get('type', '') != '':
@@ -126,7 +126,7 @@ class CaravanMagazine(BasicNewsRecipe):
         # for past editions
         # inp = json.dumps({"0":{"json":{"month":6,"year":2023}}})
         # api = 'https://api.caravanmagazine.in/api/trpc/magazines.getForMonthAndYear?batch=1&input=' + quote(inp, safe='')
-        
+
         raw = json.loads(self.index_to_soup(api, raw=True))
         if isinstance(raw, list):
             data = raw[0]['result']['data']['json']
@@ -168,7 +168,7 @@ class CaravanMagazine(BasicNewsRecipe):
         art_id = cache_data['result']['data']['json']['articleId']
         prim_data = cache_data['result']['data']['json']['data']
 
-        cat = subhead = desc = lede = auth = ''
+        cat = desc = lede = auth = ''
 
         cat = '<div class="cat">' + safe_dict(prim_data, 'printTitle') + '</div>\n'
         title = '<h1>' + safe_dict(prim_data, 'title') + '</h1>\n'
@@ -179,8 +179,8 @@ class CaravanMagazine(BasicNewsRecipe):
             authors.append(safe_dict(q, 'name'))
         dt = ''
         if prim_data.get('writtenAt', '') != '':
-            from datetime import datetime, timedelta
             import time
+            from datetime import datetime, timedelta
             dt = datetime.fromisoformat(prim_data['writtenAt'][:-1]) + timedelta(seconds=time.timezone)
             dt = dt.strftime('%b %d, %Y, %I:%M %p')
         auth ='<p class="auth">' + ', '.join(authors) + ' | ' + dt + '</p>\n'

recipes/internazionale.recipe

@@ -44,15 +44,18 @@ class Volkskrant(BasicNewsRecipe):
             url = self.home_url + url
         title_parts = []
         tag = article.find('div', {'class': 'abstract-article__tag'})
-        if tag: title_parts.append(self.tag_to_string(tag).upper())
+        if tag:
+            title_parts.append(self.tag_to_string(tag).upper())
         title_parts.append(self.tag_to_string(article.find('div', {'class': 'abstract-article__title'})))
         article_title = ' \u2022 '.join(title_parts)
         pubdate=''
         description_parts = []
         author = article.find('div', {'class': 'abstract-article__author'})
-        if author: description_parts.append(self.tag_to_string(author))
+        if author:
+            description_parts.append(self.tag_to_string(author))
         summary = article.find('div', {'class': 'abstract-article__content'})
-        if summary: description_parts.append(self.tag_to_string(summary))
+        if summary:
+            description_parts.append(self.tag_to_string(summary))
         description = ' \u2022 '.join(description_parts)
         return dict(
             title=article_title,

recipes/parool.recipe

@@ -1,9 +1,11 @@
 #!/usr/bin/env  python
-from calibre.web.feeds.recipes import BasicNewsRecipe
-import uuid
-from mechanize import Request
-from contextlib import closing
 import json
+import uuid
+from contextlib import closing
+
+from calibre.web.feeds.recipes import BasicNewsRecipe
+from mechanize import Request
+
 
 class Parool(BasicNewsRecipe):
     title = 'Het Parool'
@@ -18,7 +20,8 @@ class Parool(BasicNewsRecipe):
     remove_tags_before = dict(id='main-content')
     remove_tags_after  = dict(id='main-content')
     remove_tags = [
-        dict(attrs={'class':['article-footer__sharing', 'artstyle__editorial-tips', 'artstyle__advertisement','artstyle__container__icon','artstyle__disabled-embed','container__title__icon',]}),
+        dict(attrs={'class':['article-footer__sharing', 'artstyle__editorial-tips', 'artstyle__advertisement',
+                             'artstyle__container__icon','artstyle__disabled-embed','container__title__icon',]}),
         dict(attrs={'data-element-id': ['article-element-authors']}),
         dict(name=['script', 'noscript', 'style']),
     ]
@@ -26,7 +29,7 @@ class Parool(BasicNewsRecipe):
     encoding = 'utf-8'
     no_stylesheets = True
     ignore_duplicate_articles = {'url'}
-    
+
     def parse_index(self):
         soup = self.index_to_soup('https://www.parool.nl/privacy-wall/accept?redirectUri=%2Feditie%2Fvandaag%2F&authId=' + str(uuid.uuid4()))
         containers = soup.findAll('section', attrs={'class': 'section--horizontal'})
@@ -34,7 +37,7 @@ class Parool(BasicNewsRecipe):
         for container in containers:
             section_title = self.tag_to_string(container.find('h2')).strip()
             articles = []
-            
+
             for art in container.findAll('article'):
                 a = art.find('a')
                 url = a['href']
@@ -60,7 +63,7 @@ class Parool(BasicNewsRecipe):
                 articles.append(dict(title=article_title,
                                     url=url,
                                     content=''))
-            
+
             sections.append((section_title, articles))
         return sections
 
@@ -82,7 +85,7 @@ class Parool(BasicNewsRecipe):
             for node in soup.find('figure').find_next_siblings():
                 node.extract()
         return soup
-    
+
     def get_cover_url(self):
         headers = {
             'X-Requested-With': 'XMLHttpRequest',
@@ -93,4 +96,4 @@ class Parool(BasicNewsRecipe):
         with closing(self.browser.open(Request(url, None, headers))) as r:
             folders = json.loads(r.read())
             return folders["objects"][0]["teaser_medium"]
-        return None
+        return None

recipes/revista22.recipe

@@ -1,6 +1,7 @@
 #!/usr/bin/env  python
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
+
 class Volkskrant(BasicNewsRecipe):
     title = 'Revista 22'
     __author__ = 'Cristi Ghera'
@@ -71,4 +72,4 @@ class Volkskrant(BasicNewsRecipe):
             )
 
         sections = [('Numărul curent', articles)]
-        return sections
+        return sections

recipes/volksrant.recipe

@@ -1,9 +1,11 @@
 #!/usr/bin/env  python
-from calibre.web.feeds.recipes import BasicNewsRecipe
-import uuid
-from mechanize import Request
-from contextlib import closing
 import json
+import uuid
+from contextlib import closing
+
+from calibre.web.feeds.recipes import BasicNewsRecipe
+from mechanize import Request
+
 
 class Volkskrant(BasicNewsRecipe):
     title = 'Volkskrant'
@@ -96,17 +98,17 @@ class Volkskrant(BasicNewsRecipe):
             if tag.name == 'img':
                 if tag['src'][0] == '/':
                     tag['src'] = 'https://www.volkskrant.nl' + tag['src']
-        
+
         for tag in soup():
             if tag.name == "picture":
                 tag.replaceWith(tag.find("img"))
-        
+
         comic_articles = { "Bas van der Schot", "Poldermodellen", "Gummbah", "Sigmund" }
         if self.tag_to_string(soup.find('h1')).strip() in comic_articles:
             for node in soup.find('figure').find_next_siblings():
                 node.extract()
         return soup
-    
+
     def get_cover_url(self):
         headers = {
             'X-Requested-With': 'XMLHttpRequest',

src/calibre/constants.py

@@ -11,7 +11,7 @@ from functools import lru_cache
 from polyglot.builtins import environ_item, hasenv
 
 __appname__   = 'calibre'
-numeric_version = (7, 9, 100)
+numeric_version = (7, 10, 0)
 __version__   = '.'.join(map(str, numeric_version))
 git_version   = None
 __author__    = "Kovid Goyal <kovid@kovidgoyal.net>"