diff --git a/recipes/noz.recipe b/recipes/noz.recipe new file mode 100644 index 0000000000..521ad2f5c1 --- /dev/null +++ b/recipes/noz.recipe @@ -0,0 +1,29 @@ +from calibre.web.feeds.news import BasicNewsRecipe + +class AdvancedUserRecipe1344926684(BasicNewsRecipe): + title = u'Neue Osnabrücker Zeitung' + __author__ = 'Krittika Goyal' + oldest_article = 7 + max_articles_per_feed = 100 + #auto_cleanup = True + no_stylesheets = True + use_embedded_content = False + language = 'de' + remove_javascript = True + + keep_only_tags = [dict(name='h1', attrs={'class':'enlargeable'}), dict(name='h2', attrs={'class':'enlargeable vorspann'}), dict(name='div', attrs={'id':'largePicContainer'}), dict(name='span', attrs={'id':'articletext'})] + remove_tags = [dict(name='div', attrs={'id':'retresco-title'}),dict(name='div', attrs={'class':'retresco-item s1 relative'}),dict(name='a', attrs={'class':'medium2 largeSpaceTop icon'})] + + feeds = [(u'Lokales', u'http://www.noz.de/rss/Lokales'), +(u'Vermischtes', u'http://www.noz.de/rss/Vermischtes'), +(u'Politik', u'http://www.noz.de/rss/Politik'), +(u'Wirtschaft', u'http://www.noz.de/rss/Wirtschaft'), +(u'Kultur', u'http://www.noz.de/rss/Kultur'), +(u'Medien', u'http://www.noz.de/rss/Medien'), +(u'Wissenschaft', u'http://www.noz.de/rss/wissenschaft'), +(u'Sport', u'http://www.noz.de/rss/Sport'), +(u'Computer', u'http://www.noz.de/rss/Computer'), +(u'Musik', u'http://www.noz.de/rss/Musik'), +(u'Szene', u'http://www.noz.de/rss/Szene'), +(u'Niedersachsen', u'http://www.noz.de/rss/Niedersachsen'), +(u'Kino', u'http://www.noz.de/rss/Kino')] diff --git a/recipes/the_sun.recipe b/recipes/the_sun.recipe index d93ac2c49b..a5c4dbdd10 100644 --- a/recipes/the_sun.recipe +++ b/recipes/the_sun.recipe @@ -8,13 +8,11 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe): title = u'The Sun UK' description = 'Articles from The Sun tabloid UK' __author__ = 'Dave Asbury' - # last updated 25/7/12 + # last updated 6/10/12 added starsons remove article code language = 'en_GB' oldest_article = 1 - max_articles_per_feed = 12 + max_articles_per_feed = 15 remove_empty_feeds = True - no_stylesheets = True - masthead_url = 'http://www.thesun.co.uk/sol/img/global/Sun-logo.gif' encoding = 'UTF-8' @@ -23,13 +21,9 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe): - #preprocess_regexps = [ - # (re.compile(r'
', re.IGNORECASE | re.DOTALL), lambda match: '')] - - extra_css = ''' body{ text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;} - ''' + ''' keep_only_tags = [ dict(name='div',attrs={'class' : 'intro'}), dict(name='h3'), @@ -52,6 +46,15 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe): (u'Showbiz', u'http://www.thesun.co.uk/sol/homepage/showbiz/rss'), (u'Woman', u'http://www.thesun.co.uk/sol/homepage/woman/rss'), ] +# starsons code + def parse_feeds (self): + feeds = BasicNewsRecipe.parse_feeds(self) + for feed in feeds: + for article in feed.articles[:]: + # print 'article.title is: ', article.title + if 'Web porn harms kids' in article.title.upper() or 'The-Sun-says' in article.url: + feed.articles.remove(article) + return feeds def get_cover_url(self): soup = self.index_to_soup('http://www.politicshome.com/uk/latest_frontpage.html') @@ -69,6 +72,7 @@ class AdvancedUserRecipe1325006965(BasicNewsRecipe): cov2 = str(cov) cov2=cov2[27:-18] #cov2 now is pic url, now go back to original function + # print "**** cov2 =",cov2,"****" br = browser() br.set_handle_redirect(False) try: diff --git a/src/calibre/ebooks/metadata/sources/base.py b/src/calibre/ebooks/metadata/sources/base.py index 95aa5a3563..46c6f7a313 100644 --- a/src/calibre/ebooks/metadata/sources/base.py +++ b/src/calibre/ebooks/metadata/sources/base.py @@ -26,6 +26,7 @@ msprefs.defaults['wait_after_first_identify_result'] = 30 # seconds msprefs.defaults['wait_after_first_cover_result'] = 60 # seconds msprefs.defaults['swap_author_names'] = False msprefs.defaults['fewer_tags'] = True +msprefs.defaults['find_first_edition_date'] = False # Google covers are often poor quality (scans/errors) but they have high # resolution, so they trump covers from better sources. So make sure they diff --git a/src/calibre/ebooks/metadata/sources/identify.py b/src/calibre/ebooks/metadata/sources/identify.py index 5113342b83..16aa39d59d 100644 --- a/src/calibre/ebooks/metadata/sources/identify.py +++ b/src/calibre/ebooks/metadata/sources/identify.py @@ -120,6 +120,8 @@ class ISBNMerge(object): self.log.debug(xw.tb) else: isbns, min_year = xw.isbns, xw.min_year + if not msprefs['find_first_edition_date']: + min_year = None if not isbns: isbns = frozenset([isbn]) if isbns in self.pools: diff --git a/src/calibre/gui2/preferences/metadata_sources.py b/src/calibre/gui2/preferences/metadata_sources.py index 541da2e203..db4d4a01e9 100644 --- a/src/calibre/gui2/preferences/metadata_sources.py +++ b/src/calibre/gui2/preferences/metadata_sources.py @@ -296,6 +296,7 @@ class ConfigWidget(ConfigWidgetBase, Ui_Form): r('wait_after_first_cover_result', msprefs) r('swap_author_names', msprefs) r('fewer_tags', msprefs) + r('find_first_edition_date', msprefs) self.configure_plugin_button.clicked.connect(self.configure_plugin) self.sources_model = SourcesModel(self) diff --git a/src/calibre/gui2/preferences/metadata_sources.ui b/src/calibre/gui2/preferences/metadata_sources.ui index 89f6454df7..cfbdb51571 100644 --- a/src/calibre/gui2/preferences/metadata_sources.ui +++ b/src/calibre/gui2/preferences/metadata_sources.ui @@ -7,7 +7,7 @@ 0 0 781 - 394 + 439 @@ -21,7 +21,7 @@ - + Metadata sources @@ -104,22 +104,22 @@ + + Restore your own subset of checked fields that you define using the 'Set as default' button + &Select default - - Restore your own subset of checked fields that you define using the 'Set as default' button - + + Store the currently checked fields as a default you can restore using the 'Select default' button + &Set as default - - Store the currently checked fields as a default you can restore using the 'Select default' button - @@ -139,7 +139,7 @@ - + Max. number of &tags to download: @@ -149,10 +149,10 @@ - + - + Max. &time to wait after first match is found: @@ -162,14 +162,14 @@ - + secs - + Max. time to wait after first &cover is found: @@ -179,14 +179,14 @@ - + secs - + <p>Different metadata sources have different sets of tags for the same book. If this option is checked, then calibre will use the smaller tag sets. These tend to be more like genres, while the larger tag sets tend to describe the books content. @@ -197,6 +197,13 @@ + + + + Use published date of "first edition" (from worldcat.org) + + +