diff --git a/Changelog.yaml b/Changelog.yaml
index b0c231ce3a..699aa3a531 100644
--- a/Changelog.yaml
+++ b/Changelog.yaml
@@ -4,6 +4,134 @@
# for important features/bug fixes.
# Also, each release can have new and improved recipes.
+- version: 0.7.37
+ date: 2011-01-02
+
+ new features:
+ - title: "This realease is mostly a bug fix release to fix various things that got broken by all the changes in 0.7.36"
+
+ - title: "Tag browser: Move the configuration of the sub-category grouping from tweaks to the Preferences dialog"
+
+ - title: "Tag browser: Allow changing the sub-categorization scheme from the right click menu"
+
+ bug fixes:
+ - title: "Fix regression in 0.7.36 that caused the Tag Browser to break if you have items in it with empty sort values"
+
+ - title: "Catalog generation: Fix various regressions introduced in 0.7.36 on windows"
+ description: >
+ "Database integrity check not working after catalog generation. Catalog generation failing with a file in use error. Spurious question marks appearing in the catalog"
+
+ - title: "Catalog generation: Work on a copy of the library database so as not to lock it"
+
+ - title: "Catalog generation: Handle merge of comments + custom field when custom filed is None"
+
+ - title: "Fix regression that broke sort_columns_at_startup tweak in 0.7.36"
+
+ - title: "Tag Browser: Fix the Manage X items in the right click menu, which broke in 0.7.36"
+
+ - title: "Tag Browser: Fix grouping by name for authors"
+
+ - title: "Nook color: Fix main memory and SD card swapped in calibre"
+ tickets: [8159]
+
+ - title: "Fix regression in 0.7.36 that broke PDF Output when specifying a cover"
+
+ - title: "Catalog generation: Fix regression in MOBI catalog that caused it to not appear as periodical on Kindle"
+
+ - title: "Fix regression in 0.7.36 that broke opening the book details dialog by double clicking on the book details panel"
+
+
+- version: 0.7.36
+ date: 2011-01-01
+
+ new features:
+ - title: "Tag browser: Add subcategories and search"
+ description: "When a category has many items, it will be automatically split up. Also add a search to quickly find an item in the Tag Browser. The sub categories can be controlled via preferences->Tweaks. Also add a button to collapse all categories"
+ type: major
+
+ - title: "Device drivers for the Google Nexus S, Motorola Backflip, Samsung Galaxy Tablet, PocketBook 603/903, EEEReader DR900 and the NextBook"
+
+ - title: "Tag editor dialog now remebers its last used size"
+ tickets: [8063]
+
+ - title: "OS X dmg: Add a symlink pointing to the Applications folder for easy installation"
+ tickets: [8052]
+
+ - title: "Catalog generation: CSV/XML catalogs now support custom fields. Also write UTF-8 BOM to CSV output file."
+ tickets: [8014]
+
+ - title: "EPUB/MOBI catalogs: Various new features"
+ description: "Added a custom field/value for excluding books, OR'd with existing tag list. Added a thumbnail width hint, from 1.0 - 2.0 inches. Deprecated support for special note tag '*', added support for custom column containing note to be inserted in Description header. Added 'Merge with comments' feature, which non-destructively combines Comments with a custom field when generating Descriptions. Moved Description header into a user-editable template file. All fields except thumb and comments accessible to template."
+ tickets: [7820, 5297, 6765]
+
+ - title: "SONY driver: Allow the creation of an All by Something category via the tweaks."
+
+ - title: "Add a tweak to control the delay when sending mails using gmail or hotmail."
+ tickets: [8064]
+
+ - title: "Add output encoding option for TXT/PDB/PMLX output plugins to the GUI"
+
+ - title: "Add an environment variable to control the temporary directory calibre uses"
+
+ - title: "Use the new HTML editor widget for comments custom columns as well"
+
+ - title: "Content server: Fix regression that broke saved searches"
+ tickets: [8047]
+
+ - title: "E-book viewer: Fix regression that broke previous page button"
+
+ - title: "Add a tweak to allow double clicking on the book list to open the edit metadata dialog"
+ tickets: [8032]
+
+ - title: "Add a tweak to use a template for formatting SONY collection names"
+ tickets: [8033]
+
+ - title: "Bulk edit metadata, search and replace: Show all values for multiple fields in the text region, separated by :::"
+ tickets: [8030]
+
+ - title: "Update user agent used by calibre when connecting to websites"
+
+ bug fixes:
+ - title: "FB2 Output: Fix regression that broke images in generated FB2 files"
+ tickets: [8142]
+
+ - title: "When unzipping zip files that contain filenames with unknown character encoding, sanitize the filenames correctly"
+ tickets: [8050]
+
+ - title: "TCR Output: Fix TCR compression adding junk to the end of the text. Remove compression level option."
+
+ - title: "PDF Output: Fix regression that broke the margin options."
+
+ - title: "FB2 Input: Handle non UTF-8 encodings on OS X"
+ tickets: [8115]
+
+ - title: "SNB Input: Better error handling if some metadata is missing in the SNB file. Add Wi-Fi connection support for the Bambook"
+
+ - title: "Allow hyperlinks to be clicked in comments metadata in the book details panel"
+ tickets: [8054]
+
+ improved recipes:
+ - Brand Eins
+ - Volksrant
+ - Smithsonian
+ - Business World
+ - El Universal
+ - Salon
+ - The Week
+ - EL Pais
+ - Wired Magazine
+ - Heraldo de Aragon
+
+ new recipes:
+ - title: "Karlsruhe News"
+ author: "tfeld"
+
+ - title: "El Periodico and Red Aragon"
+ author: "desUBIKado"
+
+ - title: "Business Insider"
+ author: "Darko Miletic"
+
- version: 0.7.35
date: 2010-12-23
diff --git a/resources/catalog/stylesheet.css b/resources/catalog/stylesheet.css
index 057c6c9f42..bf83a4c60b 100644
--- a/resources/catalog/stylesheet.css
+++ b/resources/catalog/stylesheet.css
@@ -2,19 +2,29 @@ body { background-color: white; }
p.title {
margin-top:0em;
- margin-bottom:1em;
+ margin-bottom:0em;
text-align:center;
font-style:italic;
font-size:xx-large;
- border-bottom: solid black 2px;
+ }
+
+p.series_id {
+ margin-top:0em;
+ margin-bottom:0em;
+ text-align:center;
+ }
+
+a.series_id {
+ font-style:normal;
+ font-size:large;
}
p.author {
+ font-size:large;
margin-top:0em;
margin-bottom:0em;
text-align: center;
text-indent: 0em;
- font-size:large;
}
p.author_index {
@@ -26,7 +36,8 @@ p.author_index {
text-indent: 0em;
}
-p.tags {
+p.genres {
+ font-style:normal;
margin-top:0.5em;
margin-bottom:0em;
text-align: left;
@@ -108,6 +119,13 @@ p.date_read {
text-indent:-6em;
}
+hr.annotations_divider {
+ width:50%;
+ margin-left:1em;
+ margin-top:0em;
+ margin-bottom:0em;
+ }
+
hr.description_divider {
width:90%;
margin-left:5%;
@@ -117,20 +135,37 @@ hr.description_divider {
border-left: solid white 0px;
}
-hr.annotations_divider {
- width:50%;
- margin-left:1em;
- margin-top:0em;
- margin-bottom:0em;
+hr.header_divider {
+ width:100%;
+ border-top: solid white 1px;
+ border-right: solid white 0px;
+ border-bottom: solid black 2px;
+ border-left: solid white 0px;
+ }
+
+hr.merged_comments_divider {
+ width:80%;
+ margin-left:10%;
+ border-top: solid white 0px;
+ border-right: solid white 0px;
+ border-bottom: dashed gray 2px;
+ border-left: solid white 0px;
}
td.publisher, td.date {
font-weight:bold;
text-align:center;
}
-td.rating {
- text-align: center;
+
+td.rating{
+ text-align:center;
}
+
+td.notes {
+ font-size: 100%;
+ text-align:center;
+ }
+
td.thumbnail img {
-webkit-box-shadow: 4px 4px 12px #999;
}
\ No newline at end of file
diff --git a/resources/catalog/template.xhtml b/resources/catalog/template.xhtml
new file mode 100644
index 0000000000..97da23243a
--- /dev/null
+++ b/resources/catalog/template.xhtml
@@ -0,0 +1,41 @@
+
+
+ {title_str}
+ {title}
+ {series} [{series_index}]
+
+ {author_prefix}{author}
+ {genres}
+ {formats}
+
+
+ {thumb}
+
+
+
+
+ {publisher}
+
+
+ {pubyear}
+
+
+ {rating}
+
+
+ {note_source}: {note_content}
+
+
+
+
+ {comments}
+
+
diff --git a/resources/default_tweaks.py b/resources/default_tweaks.py
index efa46fa7ae..4ae0278133 100644
--- a/resources/default_tweaks.py
+++ b/resources/default_tweaks.py
@@ -55,6 +55,24 @@ author_sort_copy_method = 'invert'
# categories_use_field_for_author_name = 'author_sort'
categories_use_field_for_author_name = 'author'
+# When partitioning the tags browser, the format of the subcategory label is
+# controlled by a template: categories_collapsed_name_template if sorting by
+# name, categories_collapsed_rating_template if sorting by average rating, and
+# categories_collapsed_popularity_template if sorting by popularity. There are
+# two variables available to the template: first and last. The variable 'first'
+# is the initial item in the subcategory, and the variable 'last' is the final
+# item in the subcategory. Both variables are 'objects'; they each have multiple
+# values that are obtained by using a suffix. For example, first.name for an
+# author category will be the name of the author. The sub-values available are:
+# name: the printable name of the item
+# count: the number of books that references this item
+# avg_rating: the averate rating of all the books referencing this item
+# sort: the sort value. For authors, this is the author_sort for that author
+# category: the category (e.g., authors, series) that the item is in.
+categories_collapsed_name_template = '{first.sort:shorten(4,'',0)} - {last.sort:shorten(4,'',0)}'
+categories_collapsed_rating_template = '{first.avg_rating:4.2f:ifempty(0)} - {last.avg_rating:4.2f:ifempty(0)}'
+categories_collapsed_popularity_template = '{first.count:d} - {last.count:d}'
+
# Set whether boolean custom columns are two- or three-valued.
# Two-values for true booleans
@@ -289,3 +307,11 @@ locale_for_sorting = ''
# metadata one book at a time. If True, then the fields are laid out using two
# columns. If False, one column is used.
metadata_single_use_2_cols_for_custom_fields = True
+
+# The number of seconds to wait before sending emails when using a
+# public email server like gmail or hotmail. Default is: 5 minutes
+# Setting it to lower may cause the server's SPAM controls to kick in,
+# making email sending fail. Changes will take effect only after a restart of
+# calibre.
+public_smtp_relay_delay = 301
+
diff --git a/resources/images/news/business_insider.png b/resources/images/news/business_insider.png
new file mode 100644
index 0000000000..7e86e583e8
Binary files /dev/null and b/resources/images/news/business_insider.png differ
diff --git a/resources/recipes/brand_eins.recipe b/resources/recipes/brand_eins.recipe
index 3d62079716..9b77c7f279 100644
--- a/resources/recipes/brand_eins.recipe
+++ b/resources/recipes/brand_eins.recipe
@@ -1,19 +1,16 @@
#!/usr/bin/env python
# -*- coding: utf-8 mode: python -*-
-# Find the newest version of this recipe here:
-# https://github.com/consti/BrandEins-Recipe/raw/master/brandeins.recipe
-
__license__ = 'GPL v3'
__copyright__ = '2010, Constantin Hofstetter , Steffen Siebert '
-__version__ = '0.96'
+__version__ = '0.97'
''' http://brandeins.de - Wirtschaftsmagazin '''
import re
import string
+from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.recipes import BasicNewsRecipe
-
class BrandEins(BasicNewsRecipe):
title = u'brand eins'
@@ -28,6 +25,8 @@ class BrandEins(BasicNewsRecipe):
language = 'de'
publication_type = 'magazine'
needs_subscription = 'optional'
+ # Prevent that conversion date is appended to title
+ timefmt = ''
# 2 is the last full magazine (default)
# 1 is the newest (but not full)
@@ -66,6 +65,13 @@ class BrandEins(BasicNewsRecipe):
new_p = ""+ content +"
"
p.replaceWith(new_p)
+ # Change to
+ header = soup.find("h3")
+ if header:
+ tag = Tag(soup, "h1")
+ tag.insert(0, header.contents[0])
+ header.replaceWith(tag)
+
return soup
def get_cover(self, soup):
@@ -77,6 +83,7 @@ class BrandEins(BasicNewsRecipe):
def parse_index(self):
feeds = []
+ issue_map = {}
archive = "http://www.brandeins.de/archiv.html"
@@ -88,21 +95,31 @@ class BrandEins(BasicNewsRecipe):
pass
soup = self.index_to_soup(archive)
- latest_jahrgang = soup.findAll('div', attrs={'class': re.compile(r'\bjahrgang-latest\b') })[0].findAll('ul')[0]
- pre_latest_issue = latest_jahrgang.findAll('a')[len(latest_jahrgang.findAll('a'))-issue]
- url = pre_latest_issue.get('href', False)
- # Get month and year of the magazine issue - build it out of the title of the cover
- self.timefmt = " " + re.search(r"(?P\d\d\/\d\d\d\d)", pre_latest_issue.find('img').get('title', False)).group('date')
+ issue_list = soup.findAll('div', attrs={'class': 'tx-brandeinsmagazine-pi1'})[0].findAll('a')
+ issue_list = [i for i in issue_list if i.get('onmouseover', False)]
+ for i in issue_list:
+ issue_number_string = i.get('onmouseover', False)
+ if issue_number_string:
+ match = re.match("^switch_magazine\(([0-9]+), ([0-9]+)\)$", issue_number_string)
+ issue_number = "%04i%02i" % (int(match.group(1)), int(match.group(2)))
+ issue_map[issue_number] = i
+ keys = issue_map.keys()
+ keys.sort()
+ keys.reverse()
+ selected_issue = issue_map[keys[issue-1]]
+ url = selected_issue.get('href', False)
+ # Get the title for the magazin - build it out of the title of the cover - take the issue and year;
+ self.title = "brand eins "+ re.search(r"(?P\d\d\/\d\d\d\d)", selected_issue.find('img').get('title', False)).group('date')
url = 'http://brandeins.de/'+url
# url = "http://www.brandeins.de/archiv/magazin/tierisch.html"
- titles_and_articles = self.brand_eins_parse_latest_issue(url)
+ titles_and_articles = self.brand_eins_parse_issue(url)
if titles_and_articles:
for title, articles in titles_and_articles:
feeds.append((title, articles))
return feeds
- def brand_eins_parse_latest_issue(self, url):
+ def brand_eins_parse_issue(self, url):
soup = self.index_to_soup(url)
self.cover_url = self.get_cover(soup)
article_lists = [soup.find('div', attrs={'class':'subColumnLeft articleList'}), soup.find('div', attrs={'class':'subColumnRight articleList'})]
@@ -145,4 +162,3 @@ class BrandEins(BasicNewsRecipe):
current_articles.append({'title': title, 'url': url, 'description': description, 'date':''})
titles_and_articles.append([chapter_title, current_articles])
return titles_and_articles
-
diff --git a/resources/recipes/business_insider.recipe b/resources/recipes/business_insider.recipe
new file mode 100644
index 0000000000..d7e6a0d59b
--- /dev/null
+++ b/resources/recipes/business_insider.recipe
@@ -0,0 +1,69 @@
+__license__ = 'GPL v3'
+__copyright__ = '2010, Darko Miletic '
+'''
+www.businessinsider.com
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Business_insider(BasicNewsRecipe):
+ title = 'Business Insider'
+ __author__ = 'Darko Miletic'
+ description = 'Noticias de Argentina y el resto del mundo'
+ publisher = 'Business Insider, Inc.'
+ category = 'news, politics, finances, world'
+ oldest_article = 2
+ max_articles_per_feed = 200
+ no_stylesheets = True
+ encoding = 'utf8'
+ use_embedded_content = True
+ language = 'en'
+ remove_empty_feeds = True
+ publication_type = 'newsportal'
+ masthead_url = 'http://static.businessinsider.com/assets/images/logos/tbi_print.jpg'
+ extra_css = """
+ body{font-family: Arial,Helvetica,sans-serif }
+ img{margin-bottom: 0.4em; display:block}
+ """
+
+ conversion_options = {
+ 'comment' : description
+ , 'tags' : category
+ , 'publisher' : publisher
+ , 'language' : language
+ }
+
+ remove_tags = [
+ dict(name=['meta','link'])
+ ,dict(attrs={'class':'feedflare'})
+ ]
+ remove_attributes=['lang','border']
+
+
+ feeds = [
+ (u'Latest' , u'http://feeds2.feedburner.com/businessinsider' )
+ ,(u'Markets' , u'http://feeds.feedburner.com/TheMoneyGame' )
+ ,(u'Wall Street' , u'http://feeds.feedburner.com/clusterstock' )
+ ,(u'Tech' , u'http://feeds.feedburner.com/typepad/alleyinsider/silicon_alley_insider')
+ ,(u'The Wire' , u'http://feeds.feedburner.com/businessinsider/thewire' )
+ ,(u'War Room' , u'http://feeds.feedburner.com/businessinsider/warroom' )
+ ,(u'Sports' , u'http://feeds.feedburner.com/businessinsider/sportspage' )
+ ,(u'Tools' , u'http://feeds.feedburner.com/businessinsider/tools' )
+ ,(u'Travel' , u'http://feeds.feedburner.com/businessinsider/travel' )
+ ]
+
+
+ def preprocess_html(self, soup):
+ for item in soup.findAll(style=True):
+ del item['style']
+ for item in soup.findAll('a'):
+ if item['href'].startswith('http://feedads'):
+ item.extract()
+ else:
+ if item.string is not None:
+ tstr = item.string
+ item.replaceWith(tstr)
+ for item in soup.findAll('img'):
+ if not item.has_key('alt'):
+ item['alt'] = 'image'
+ return soup
diff --git a/resources/recipes/businessworldin.recipe b/resources/recipes/businessworldin.recipe
index 99d56e850f..e44682d7e1 100644
--- a/resources/recipes/businessworldin.recipe
+++ b/resources/recipes/businessworldin.recipe
@@ -1,7 +1,5 @@
-#!/usr/bin/env python
-
__license__ = 'GPL v3'
-__copyright__ = '2009, Darko Miletic '
+__copyright__ = '2009-2010, Darko Miletic '
'''
www.businessworld.in
'''
@@ -22,7 +20,11 @@ class BusinessWorldMagazine(BasicNewsRecipe):
use_embedded_content = False
encoding = 'utf-8'
language = 'en_IN'
-
+ extra_css = """
+ img{display: block; margin-bottom: 0.5em}
+ body{font-family: Arial,Helvetica,sans-serif}
+ h2{color: gray; display: block}
+ """
conversion_options = {
'comment' : description
@@ -42,7 +44,26 @@ class BusinessWorldMagazine(BasicNewsRecipe):
articles = []
linklist = []
soup = self.index_to_soup(self.INDEX)
-
+
+ tough = soup.find('div', attrs={'id':'tough'})
+ if tough:
+ for item in tough.findAll('h1'):
+ description = ''
+ title_prefix = ''
+ feed_link = item.find('a')
+ if feed_link and feed_link.has_key('href'):
+ url = self.ROOT + feed_link['href']
+ if not self.is_in_list(linklist,url):
+ title = title_prefix + self.tag_to_string(feed_link)
+ date = strftime(self.timefmt)
+ articles.append({
+ 'title' :title
+ ,'date' :date
+ ,'url' :url
+ ,'description':description
+ })
+ linklist.append(url)
+
for item in soup.findAll('div', attrs={'class':'nametitle'}):
description = ''
title_prefix = ''
@@ -62,8 +83,8 @@ class BusinessWorldMagazine(BasicNewsRecipe):
return [(soup.head.title.string, articles)]
- keep_only_tags = [dict(name='div', attrs={'id':['register-panel','printwrapper']})]
- remove_tags = [dict(name=['object','link'])]
+ keep_only_tags = [dict(name='div', attrs={'id':'printwrapper'})]
+ remove_tags = [dict(name=['object','link','meta','base','iframe','link','table'])]
def print_version(self, url):
return url.replace('/bw/','/bw/storyContent/')
diff --git a/resources/recipes/el_universal.recipe b/resources/recipes/el_universal.recipe
index 1995d0f932..f053812c05 100644
--- a/resources/recipes/el_universal.recipe
+++ b/resources/recipes/el_universal.recipe
@@ -1,7 +1,5 @@
-#!/usr/bin/env python
-
__license__ = 'GPL v3'
-__copyright__ = '2009, Darko Miletic '
+__copyright__ = '2009-2010, Darko Miletic '
'''
eluniversal.com.mx
'''
@@ -18,75 +16,25 @@ class ElUniversal(BasicNewsRecipe):
category = 'news, politics, Mexico'
no_stylesheets = True
use_embedded_content = False
- encoding = 'cp1252'
+ encoding = 'utf8'
remove_javascript = True
- language = 'es'
+ remove_empty_feeds = True
+ publication_type = 'newspaper'
+ language = 'es'
extra_css = '''
- body{font-family:Arial,Helvetica,sans-serif; font-size:x-small;}
- .geoGris30{font-family:Georgia,"Times New Roman",Times,serif; font-size:large; color:#003366; font-weight:bold;}
- .arnegro16{font-family:Georgia,"Times New Roman",Times,serif; font-weight:bold; font-size:small;}
- .tbazull2{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; color:#336699; font-size:xx-small;}
- .tbgrisf11{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; color: #666666; font-size:xx-small;}
- .verrojo13{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; color: #CC0033; font-size:xx-small;}
- .trnegro13{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; font-size:xx-small;}
- .txt-fotogaleria{font-family:"trebuchet ms",Arial,Helvetica,sans-serif; font-size:xx-small;}
+ body{font-family:Arial,Helvetica,sans-serif}
+ .noteTitle{font-family: Georgia,"Times New Roman",Times,serif; color: #336699; font-size: xx-large; font-weight: bold}
+ .noteInfo{display: block; color: gray}
'''
- keep_only_tags = [ dict(name='table', attrs={'width':"633"}),dict(name='table', attrs={'width':"629"}),]
-
+ keep_only_tags = [ dict(name='div', attrs={'id':'noteContent'})]
+ remove_tags_after = dict(attrs={'class':'noteText'})
remove_tags = [
- dict(name='table', attrs={'bgcolor':"#f5f5f5"}),
- dict(name='td', attrs={'bgcolor':"#f7f8f9"}),
- dict(name='td', attrs={'bgcolor':"#f5f5f5"}),
- dict(name='table', attrs={'width':"302"}),
- dict(name='table', attrs={'width':"214"}),
- dict(name='table', attrs={'width':"112"}),
- dict(name='table', attrs={'width':"980"}),
- dict(name='td', attrs={'height':"1"}),
- dict(name='td', attrs={'height':"4"}),
- dict(name='td', attrs={'height':"20"}),
- dict(name='td', attrs={'height':"10"}),
- dict(name='td', attrs={'class':["trrojo11","trbris11","trrojo12","arrojo12s","tbazul13"]}),
- dict(name='div', attrs={'id':["mapg","ver_off_todosloscom","todosloscom"]}),
- dict(name='span', attrs={'class':["trazul18b","trrojo11","trnaranja11","trbris11","georojo18b","geogris18"]}),
- dict(name='span', attrs={'class':["detalles-opinion"]}),
- dict(name='a', attrs={'class':["arnaranja12b","trbris11","arazul12rel","trrojo10"]}),
- dict(name='img', src = "/img/icono_imprimir.gif"),
- dict(name='img', src = "/img/icono_enviar_mail.gif"),
- dict(name='img', src = "/img/icono_fuente_g.gif"),
- dict(name='img', src = "/img/icono_fuente_m.gif"),
- dict(name='img', src = "/img/icono_fuente_c.gif"),
- dict(name='img', src = "/img/icono_compartir.gif"),
- dict(name='img', src = "/img/icono_enviar_coment.gif"),
- dict(name='img', src = "http://www.eluniversal.com.mx/n_img/bot-notasrel.gif"),
- dict(name='img', src = "http://www.eluniversal.com.mx/n_img/fr.gif"),
- dict(name='img', src = "/img/espiral2.gif"),
- dict(name='img', src = "http://www.eluniversal.com.mx/n_img/b"),
- dict(name='img', src = "/img/icono_enviar_coment.gifot-notasrel.gif"),
- dict(name='img', src = "/n_img/icono_tipo3.gif"),
- dict(name='img', src = "/n_img/icono_tipo2.gif"),
- dict(name='img', src = "/n_img/icono_print.gif"),
- dict(name='img', src = "/n_img/icono_mail2.gif"),
- dict(name='img', src = "/n_img/im-comentarios-2a.gif"),
- dict(name='img', src = "/n_img/im-comentarios-1a.gif"),
- dict(name='img', src = "/img/icono_coment.gif"),
- dict(name='img', src = "http://www.eluniversal.com.mx/n_img/bot-sitiosrel.gif"),
- dict(name='img', src = "/n_img/icono_tipomenos.gif"),
- dict(name='img', src = "/img/futbol/19.jpg"),
- dict(name='img', alt = "Facebook"),
- dict(name='img', alt = "Twitter"),
- dict(name='img', alt = "Google"),
- dict(name='img', alt = "LinkedIn"),
- dict(name='img', alt = "Viadeo"),
- dict(name='img', alt = "Digg"),
- dict(name='img', alt = "Delicious"),
- dict(name='img', alt = "Meneame"),
- dict(name='img', alt = "Yahoo"),
- dict(name='img', alt = "Technorati"),
- dict(name='a',text =["Compartir","Facebook","Twitter","Google","LinkedIn","Viadeo","Digg","Delicious","Meneame","Yahoo","Technorati"]),
- dict(name='select'),
- dict(name='a', attrs={'class':"tbgriscompartir"}),
- ]
+ dict(attrs={'class':'noteExtras'}),
+ dict(name=['meta','iframe','base','embed','object']),
+ dict(attrs={'id':'tm_box'})
+ ]
+ remove_attributes=['lang','onclick']
feeds = [
(u'Minuto por Minuto', u'http://www.eluniversal.com.mx/rss/universalmxm.xml' )
@@ -101,25 +49,3 @@ class ElUniversal(BasicNewsRecipe):
,(u'Computacion' , u'http://www.eluniversal.com.mx/rss/computo.xml' )
,(u'Sociedad' , u'http://www.eluniversal.com.mx/rss/sociedad.xml' )
]
-
- # def print_version(self, url):
- # return url.replace('/notas/','/notas/vi_')
-
- def preprocess_html(self, soup):
- mtag = '")
- tag.insert(2," ")
-
- return soup
-
- def postprocess_html(self, soup,first):
-
- for tag in soup.findAll(name=['table', 'span','i']):
- tag.name = 'div'
- for item in soup.findAll(align = "right"):
- del item['align']
-
- return soup
-
diff --git a/resources/recipes/elpais_impreso.recipe b/resources/recipes/elpais_impreso.recipe
index bba3bda217..130013286c 100644
--- a/resources/recipes/elpais_impreso.recipe
+++ b/resources/recipes/elpais_impreso.recipe
@@ -1,86 +1,95 @@
-# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic '
'''
-www.elpais.com/diario/
+www.elpais.com
'''
-from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
-class ElPaisImpresa(BasicNewsRecipe):
- title = u'El Pa\xeds - edicion impresa'
+class ElPais_RSS(BasicNewsRecipe):
+ title = 'El Pais'
__author__ = 'Darko Miletic'
- description = u'el periodico global en Espa\xf1ol'
+ description = 'el periodico global en Castellano'
publisher = 'EDICIONES EL PAIS, S.L.'
- category = 'news, politics,Spain,actualidad,noticias,informacion,videos,fotografias,audios,graficos,nacional,internacional,deportes,economia,tecnologia,cultura,gente,television,sociedad,opinion,blogs,foros,chats,encuestas,entrevistas,participacion'
+ category = 'news, politics, finances, world, spain'
+ oldest_article = 2
+ max_articles_per_feed = 200
no_stylesheets = True
- encoding = 'latin1'
+ encoding = 'cp1252'
use_embedded_content = False
- language = 'es'
+ language = 'es_ES'
+ remove_empty_feeds = True
publication_type = 'newspaper'
- masthead_url = 'http://www.elpais.com/im/tit_logo_global.gif'
- index = 'http://www.elpais.com/diario/'
- extra_css = ' p{text-align: justify} body{ text-align: left; font-family: Georgia,"Times New Roman",Times,serif } h2{font-family: Arial,Helvetica,sans-serif} img{margin-bottom: 0.4em} '
+ masthead_url = 'http://www.elpais.com/im/tit_logo.gif'
+ extra_css = """
+ body{font-family: Georgia,"Times New Roman",Times,serif }
+ h3{font-family: Arial,Helvetica,sans-serif}
+ img{margin-bottom: 0.4em; display:block}
+ """
conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
+ 'comment' : description
+ , 'tags' : category
+ , 'publisher' : publisher
+ , 'language' : language
}
- feeds = [
- (u'Internacional' , index + u'internacional/' )
- ,(u'Espa\xf1a' , index + u'espana/' )
- ,(u'Economia' , index + u'economia/' )
- ,(u'Opinion' , index + u'opinion/' )
- ,(u'Vi\xf1etas' , index + u'vineta/' )
- ,(u'Sociedad' , index + u'sociedad/' )
- ,(u'Cultura' , index + u'cultura/' )
- ,(u'Tendencias' , index + u'tendencias/' )
- ,(u'Gente' , index + u'gente/' )
- ,(u'Obituarios' , index + u'obituarios/' )
- ,(u'Deportes' , index + u'deportes/' )
- ,(u'Pantallas' , index + u'radioytv/' )
- ,(u'Ultima' , index + u'ultima/' )
- ,(u'Educacion' , index + u'educacion/' )
- ,(u'Saludo' , index + u'salud/' )
- ,(u'Ciberpais' , index + u'ciberpais/' )
- ,(u'EP3' , index + u'ep3/' )
- ,(u'Cine' , index + u'cine/' )
- ,(u'Babelia' , index + u'babelia/' )
- ,(u'El viajero' , index + u'viajero/' )
- ,(u'Negocios' , index + u'negocios/' )
- ,(u'Domingo' , index + u'domingo/' )
- ,(u'El Pais semanal' , index + u'eps/' )
- ,(u'Quadern Catalunya' , index + u'quadern-catalunya/' )
- ]
+ keep_only_tags = [dict(attrs={'class':['cabecera_noticia estirar','cabecera_noticia','','contenido_noticia']})]
+ remove_tags = [
+ dict(name=['meta','link','base','iframe','embed','object'])
+ ,dict(attrs={'class':['info_complementa','estructura_2col_der','votos estirar','votos']})
+ ,dict(attrs={'id':'utilidades'})
+ ]
+ remove_tags_after = dict(attrs={'id':'utilidades'})
+ remove_attributes = ['lang','border','width','height']
- keep_only_tags=[dict(attrs={'class':['cabecera_noticia','contenido_noticia']})]
- remove_attributes=['width','height']
- remove_tags=[dict(name='link')]
-
- def parse_index(self):
- totalfeeds = []
- lfeeds = self.get_feeds()
- for feedobj in lfeeds:
- feedtitle, feedurl = feedobj
- self.report_progress(0, _('Fetching feed')+' %s...'%(feedtitle if feedtitle else feedurl))
- articles = []
- soup = self.index_to_soup(feedurl)
- for item in soup.findAll('a',attrs={'class':['g19r003','g19i003','g17r003','g17i003']}):
- url = 'http://www.elpais.com' + item['href'].rpartition('/')[0]
- title = self.tag_to_string(item)
- date = strftime(self.timefmt)
- articles.append({
- 'title' :title
- ,'date' :date
- ,'url' :url
- ,'description':''
- })
- totalfeeds.append((feedtitle, articles))
- return totalfeeds
+ feeds = [
+ (u'Lo ultimo' , u'http://www.elpais.com/rss/feed.html?feedId=17046')
+ ,(u'America Latina' , u'http://www.elpais.com/rss/feed.html?feedId=17041')
+ ,(u'Mexico' , u'http://www.elpais.com/rss/feed.html?feedId=17042')
+ ,(u'Europa' , u'http://www.elpais.com/rss/feed.html?feedId=17043')
+ ,(u'Estados Unidos' , u'http://www.elpais.com/rss/feed.html?feedId=17044')
+ ,(u'Oriente proximo' , u'http://www.elpais.com/rss/feed.html?feedId=17045')
+ ,(u'Espana' , u'http://www.elpais.com/rss/feed.html?feedId=1002' )
+ ,(u'Andalucia' , u'http://www.elpais.com/rss/feed.html?feedId=17057')
+ ,(u'Catalunia' , u'http://www.elpais.com/rss/feed.html?feedId=17059')
+ ,(u'Comunidad Valenciana' , u'http://www.elpais.com/rss/feed.html?feedId=17061')
+ ,(u'Madrid' , u'http://www.elpais.com/rss/feed.html?feedId=1016' )
+ ,(u'Pais Vasco' , u'http://www.elpais.com/rss/feed.html?feedId=17062')
+ ,(u'Galicia' , u'http://www.elpais.com/rss/feed.html?feedId=17063')
+ ,(u'Opinion' , u'http://www.elpais.com/rss/feed.html?feedId=1003' )
+ ,(u'Sociedad' , u'http://www.elpais.com/rss/feed.html?feedId=1004' )
+ ,(u'Deportes' , u'http://www.elpais.com/rss/feed.html?feedId=1007' )
+ ,(u'Cultura' , u'http://www.elpais.com/rss/feed.html?feedId=1008' )
+ ,(u'Cine' , u'http://www.elpais.com/rss/feed.html?feedId=17052')
+ ,(u'Literatura' , u'http://www.elpais.com/rss/feed.html?feedId=17053')
+ ,(u'Musica' , u'http://www.elpais.com/rss/feed.html?feedId=17051')
+ ,(u'Arte' , u'http://www.elpais.com/rss/feed.html?feedId=17060')
+ ,(u'Tecnologia' , u'http://www.elpais.com/rss/feed.html?feedId=1005' )
+ ,(u'Economia' , u'http://www.elpais.com/rss/feed.html?feedId=1006' )
+ ,(u'Ciencia' , u'http://www.elpais.com/rss/feed.html?feedId=17068')
+ ,(u'Salud' , u'http://www.elpais.com/rss/feed.html?feedId=17074')
+ ,(u'Ocio' , u'http://www.elpais.com/rss/feed.html?feedId=17075')
+ ,(u'Justicia y Leyes' , u'http://www.elpais.com/rss/feed.html?feedId=17069')
+ ,(u'Guerras y conflictos' , u'http://www.elpais.com/rss/feed.html?feedId=17070')
+ ,(u'Politica' , u'http://www.elpais.com/rss/feed.html?feedId=17073')
+ ]
def print_version(self, url):
return url + '?print=1'
+
+ def preprocess_html(self, soup):
+ for item in soup.findAll(style=True):
+ del item['style']
+ for item in soup.findAll('a'):
+ if item.string is not None:
+ tstr = item.string
+ item.replaceWith(tstr)
+ else:
+ item.name='span'
+ for atrs in ['href','target','alt','title']:
+ if item.has_key(atrs):
+ del item[atrs]
+ for item in soup.findAll('img',alt=False):
+ item['alt'] = 'image'
+ return soup
diff --git a/resources/recipes/karlsruhe.recipe b/resources/recipes/karlsruhe.recipe
new file mode 100644
index 0000000000..c0bc5369f1
--- /dev/null
+++ b/resources/recipes/karlsruhe.recipe
@@ -0,0 +1,52 @@
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class KANewsRecipe(BasicNewsRecipe):
+ title = u'KA-News.de'
+ description = u'Nachrichten aus Karlsruhe, Deutschland und der Welt.'
+ __author__ = 'tfeld'
+ lang='de'
+ no_stylesheets = True
+
+ oldest_article = 7
+ max_articles_per_feed = 100
+
+ feeds = [
+ (u'News aus Karlsruhe', 'http://www.ka-news.de/storage/rss/rss/karlsruhe.xml'),
+ (u'Kulturnachrichten aus Karlsruhe', 'http://www.ka-news.de/storage/rss/rss/kultur.xml'),
+ (u'Durlach: News aus Durlach', 'http://www.ka-news.de/storage/rss/rss/durlach.xml'),
+ (u'Stutensee: News aus Stutensee Blankenloch, Büchig, Friedrichstal, Staffort, Spöck', 'http://www.ka-news.de/storage/rss/rss/stutensee.xml'),
+ (u'Bruchsal: News aus Bruchsal', 'http://www.ka-news.de/storage/rss/rss/bruchsal.xml'),
+ (u'Wirtschaftsnews aus Karlsruhe', 'http://www.ka-news.de/storage/rss/rss/wirtschaft.xml'),
+ (u'ka-news.de - Sport', 'http://www.ka-news.de/storage/rss/rss/sport.xml'),
+ (u'KSC-News - News rund um den KSC', 'http://www.ka-news.de/storage/rss/rss/ksc.xml'),
+ (u'ka-news.de - BG Karlsruhe', 'http://www.ka-news.de/storage/rss/rss/basketball.xml')
+ ]
+
+ preprocess_regexps = [
+ (re.compile(r'width:[0-9]*?px', re.DOTALL|re.IGNORECASE), lambda match: ''),
+ ]
+
+ remove_tags_before = dict(id='artdetail_ueberschrift')
+ remove_tags_after = dict(id='artdetail_unterzeile')
+ remove_tags = [dict(name=['div'], attrs={'class': 'lbx_table'}),
+ dict(name=['div'], attrs={'class': 'lk_zumthema'}),
+ dict(name=['div'], attrs={'class': 'lk_thumb'}),
+ dict(name=['div'], attrs={'class': 'lk_trenner'}),
+ dict(name=['div'], attrs={'class': 'lupen_container'}),
+ dict(name=['script']),
+ dict(name=['span'], attrs={'style': 'display:none;'}),
+ dict(name=['span'], attrs={'class': 'comm_info'}),
+ dict(name=['h3'], attrs={'id': 'artdetail_unterzeile'})]
+
+ # removing style attribute _after_ removing specifig tags above
+ remove_attributes = ['width','height','style']
+
+ extra_css = '''
+ h1{ font-size:large; font-weight:bold; }
+ h2{ font-size:medium; font-weight:bold; }
+ '''
+
+ def get_cover_url(self):
+ return 'http://www.ka-news.de/storage/scl/techkanews/logos/434447_m1t1w250q75s1v29681_ka-news-Logo_mit_Schatten_transparent.png'
+
diff --git a/resources/recipes/la_republica.recipe b/resources/recipes/la_republica.recipe
index c74f2d7b05..14dc0d0aef 100644
--- a/resources/recipes/la_republica.recipe
+++ b/resources/recipes/la_republica.recipe
@@ -28,6 +28,8 @@ class LaRepubblica(BasicNewsRecipe):
recursion = 10
remove_javascript = True
+ no_stylesheets = True
+
def get_article_url(self, article):
link = article.get('id', article.get('guid', None))
if link is None:
diff --git a/resources/recipes/salon.recipe b/resources/recipes/salon.recipe
index ed7ec98f10..c421ab094d 100644
--- a/resources/recipes/salon.recipe
+++ b/resources/recipes/salon.recipe
@@ -25,22 +25,20 @@ class Salon_com(BasicNewsRecipe):
feeds = [
('News & Politics', 'http://feeds.salon.com/salon/news'),
- ('War Room', 'http://feeds.salon.com/salon/war_room'),
- ('Arts & Entertainment', 'http://feeds.salon.com/salon/ent'),
- ('I Like to Watch', 'http://feeds.salon.com/salon/iltw'),
- ('Beyond Multiplex', 'http://feeds.salon.com/salon/btm'),
- ('Book Reviews', 'http://feeds.salon.com/salon/books'),
- ('All Life', 'http://feeds.salon.com/salon/mwt'),
- ('All Opinion', 'http://feeds.salon.com/salon/opinion'),
- ('Glenn Greenwald', 'http://feeds.salon.com/salon/greenwald'),
- ('Garrison Keillor', 'http://dir.salon.com/topics/garrison_keillor/index.rss'),
- ('Joan Walsh', 'http://www.salon.com/rss/walsh.rss'),
- ('All Sports', 'http://feeds.salon.com/salon/sports'),
+ ('War Room', 'http://feeds.feedburner.com/salon/war_room'),
+ ('Joan Walsh', 'http://feeds.feedburner.com/Salon_Joan_Walsh'),
+ ('Glenn Greenwald', 'http://feeds.feedburner.com/salon/greenwald'),
('Tech & Business', 'http://feeds.salon.com/salon/tech'),
- ('How World Works', 'http://feeds.salon.com/salon/htww')
+ ('Ask the Pilot', 'http://feeds.feedburner.com/salon/ask_the_pilot'),
+ ('How World Works', 'http://feeds.feedburner.com/salon/htww'),
+ ('Life', 'http://feeds.feedburner.com/salon/mwt'),
+ ('Broadsheet', 'http://feeds.feedburner.com/salon/broadsheet'),
+ ('Movie Reviews', 'http://feeds.feedburner.com/salon/movie_reviews'),
+ ('Film Salon', 'http://feeds.feedburner.com/Salon/Film_Salon'),
+ ('TV', 'http://feeds.feedburner.com/salon/tv'),
+ ('Books', 'http://feeds.feedburner.com/salon/books')
]
def print_version(self, url):
return url.replace('/index.html', '/print.html')
-
diff --git a/resources/recipes/smith.recipe b/resources/recipes/smith.recipe
index e52b2ee709..98f7d98517 100644
--- a/resources/recipes/smith.recipe
+++ b/resources/recipes/smith.recipe
@@ -17,8 +17,8 @@ class SmithsonianMagazine(BasicNewsRecipe):
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':'article_sidebar_border'}),
- dict(name='div', attrs={'id':['article_sidebar_border', 'most-popular_large']}),
- #dict(name='ul', attrs={'class':'article-tools'}),
+ dict(name='div', attrs={'id':['article_sidebar_border', 'most-popular_large', 'most-popular-body_large']}),
+ ##dict(name='ul', attrs={'class':'article-tools'}),
dict(name='ul', attrs={'class':'cat-breadcrumb col three last'}),
]
@@ -37,16 +37,16 @@ class SmithsonianMagazine(BasicNewsRecipe):
]
def preprocess_html(self, soup):
- story = soup.find(name='div', attrs={'id':'article-left'})
- #td = heading.findParent(name='td')
- #td.extract()
+ story = soup.find(name='div', attrs={'id':'article-body'})
+ ##td = heading.findParent(name='td')
+ ##td.extract()
soup = BeautifulSoup('t ')
body = soup.find(name='body')
body.insert(0, story)
return soup
- def postprocess_html(self, soup, first):
- for p in soup.findAll(id='articlePaginationWrapper'): p.extract()
- if not first:
- for div in soup.findAll(id='article-head'): div.extract()
- return soup
+ #def postprocess_html(self, soup, first):
+ #for p in soup.findAll(id='articlePaginationWrapper'): p.extract()
+ #if not first:
+ #for div in soup.findAll(id='article-head'): div.extract()
+ #return soup
diff --git a/resources/recipes/the_week_magazine_free.recipe b/resources/recipes/the_week_magazine_free.recipe
index 1bac4133e7..6e033eaf82 100644
--- a/resources/recipes/the_week_magazine_free.recipe
+++ b/resources/recipes/the_week_magazine_free.recipe
@@ -1,17 +1,19 @@
-
__license__ = 'GPL v3'
-__copyright__ = '2010, Darko Miletic '
+__copyright__ = '2010, JOlo'
'''
www.theweek.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
+import re
-class TheWeekFree(BasicNewsRecipe):
- title = 'The Week Magazine - Free content'
- __author__ = 'Darko Miletic'
+class TheWeek(BasicNewsRecipe):
+ title = 'The Week Magazine'
+ __author__ = 'Jim Olo'
description = "The best of the US and international media. Daily coverage of commentary and analysis of the day's events, as well as arts, entertainment, people and gossip, and political cartoons."
publisher = 'The Week Publications, Inc.'
+ masthead_url = 'http://test.theweek.com/images/logo_theweek.gif'
+ cover_url = masthead_url
category = 'news, politics, USA'
oldest_article = 7
max_articles_per_feed = 100
@@ -19,31 +21,27 @@ class TheWeekFree(BasicNewsRecipe):
encoding = 'utf-8'
use_embedded_content = False
language = 'en'
+ preprocess_regexps = [(re.compile(r' ')]
+ remove_tags_before = dict(name='h1')
+ remove_tags_after = dict(name='div', attrs={'class':'articleSubscribe4free'})
+ remove_tags = [
+ dict(name='div', attrs={'class':['floatLeft','imageCaption','slideshowImageAttribution','postDate','utilities','cartoonInfo','left','middle','col300','articleSubscribe4free',' articleFlyout','articleFlyout floatRight','fourFreeBar']})
+ ,dict(name='div', attrs={'id':['cartoonThumbs','rightColumn','header','partners']})
+ ,dict(name='ul', attrs={'class':['slideshowNav','hotTopicsList topicList']})
+ ]
+ remove_attributes = ['width','height', 'style', 'font', 'color']
+ extra_css = '''
+ h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
+ h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
+ h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
+ p {font-family:Arial,Helvetica,sans-serif;}
+ '''
+ filter_regexps = [r'www\.palmcoastdata\.com']
- conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
- }
-
- keep_only_tags = [
- dict(name=['h1','h2'])
- , dict(name='div', attrs={'class':'basefont'})
- , dict(name='div', attrs={'id':'slideshowLoader'})
- ]
-
- remove_tags = [
- dict(name='div', attrs={'id':['digg_dugg','articleRight','dateHeader']})
- ,dict(name=['object','embed','iframe'])
- ]
-
-
- feeds = [
- (u'News & Opinions' , u'http://www.theweek.com/section/index/news_opinion.rss')
- ,(u'Arts & Leisure' , u'http://www.theweek.com/section/index/arts_leisure.rss')
- ,(u'Business' , u'http://www.theweek.com/section/index/business.rss' )
- ,(u'Cartoon & Short takes' , u'http://www.theweek.com/section/index/cartoons_wit.rss')
- ]
-
+ feeds = [
+ (u'News-Opinion', u'http://theweek.com/section/index/news_opinion.rss'),
+ (u'Business', u'http://theweek.com/section/index/business.rss'),
+ (u'Arts-Life', u'http://theweek.com/section/index/arts_life.rss'),
+ (u'Cartoons', u'http://theweek.com/section/index/cartoon_wit/0/all-cartoons.rss')
+ ]
diff --git a/resources/recipes/volksrant.recipe b/resources/recipes/volksrant.recipe
index 6f3ec4ce0d..386cb1e729 100644
--- a/resources/recipes/volksrant.recipe
+++ b/resources/recipes/volksrant.recipe
@@ -1,4 +1,3 @@
-#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import with_statement
@@ -29,13 +28,16 @@ class AdvancedUserRecipe1249039563(BasicNewsRecipe):
language = 'nl'
extra_css = '''
- body{font-family:Arial,Helvetica,sans-serif; font-size:small;}
+ body{font-family:Arial,Helvetica,sans-serif;font-size:small;}
h1{font-size:large;}
'''
'''
Change Log:
Date: 10/10/10 - Modified code to include obfuscated to get the print version
Author: Tony Stegall
+
+ Date: 01/01/11 - Modified for better results around December/January.
+ Author: Martin Tarenskeen
'''
#######################################################################################################
temp_files = []
@@ -48,11 +50,17 @@ class AdvancedUserRecipe1249039563(BasicNewsRecipe):
year = date.today().year
try:
- response = br.follow_link(url_regex='.*?(%d)(\\/)(article)(\\/)(print)(\\/)'%year, nr = 0)
- html = response.read()
+ response = br.follow_link(url_regex='.*?(%d)(\\/)(article)(\\/)(print)(\\/)'%year, nr = 0)
+ html = response.read()
except:
- response = br.open(url)
- html = response.read()
+ year = year-1
+ try:
+ response = br.follow_link(url_regex='.*?(%d)(\\/)(article)(\\/)(print)(\\/)'%year, nr = 0)
+ html = response.read()
+ except:
+ response = br.open(url)
+ html = response.read()
+
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html)
@@ -76,10 +84,3 @@ class AdvancedUserRecipe1249039563(BasicNewsRecipe):
(u'Cultuur', u'http://www.volkskrant.nl/rss/kunst.rss'),
(u'Gezondheid & Wetenschap', u'http://www.volkskrant.nl/rss/wetenschap.rss'),
(u'Internet & Media', u'http://www.volkskrant.nl/rss/media.rss') ]
-
-
-'''
-example for formating
-'''
-# original url: http://www.volkskrant.nl/vk/nl/2668/Buitenland/article/detail/1031493/2010/10/10/Noord-Korea-ziet-nieuwe-leider.dhtml
-# print url : http://www.volkskrant.nl/vk/nl/2668/2010/article/print/detail/1031493/Noord-Korea-ziet-nieuwe-leider.dhtml
diff --git a/resources/recipes/wired.recipe b/resources/recipes/wired.recipe
index 9599d54de9..bb9a97f5c4 100644
--- a/resources/recipes/wired.recipe
+++ b/resources/recipes/wired.recipe
@@ -38,12 +38,12 @@ class Wired(BasicNewsRecipe):
keep_only_tags = [dict(name='div', attrs={'class':'post'})]
remove_tags_after = dict(name='div', attrs={'class':'tweetmeme_button'})
remove_tags = [
- dict(name=['object','embed','iframe','link'])
+ dict(name=['object','embed','iframe','link','meta','base'])
,dict(name='div', attrs={'class':['podcast_storyboard','tweetmeme_button']})
,dict(attrs={'id':'ff_bottom_nav'})
,dict(name='a',attrs={'href':'http://www.wired.com/app'})
]
- remove_attributes = ['height','width']
+ remove_attributes = ['height','width','lang','border','clear']
def parse_index(self):
@@ -78,7 +78,9 @@ class Wired(BasicNewsRecipe):
divurl = item.find('div',attrs={'class':'feature-header'})
if divurl:
divdesc = item.find('div',attrs={'class':'feature-text'})
- url = 'http://www.wired.com' + divurl.a['href']
+ url = divurl.a['href']
+ if not divurl.a['href'].startswith('http://www.wired.com'):
+ url = 'http://www.wired.com' + divurl.a['href']
title = self.tag_to_string(divurl.a)
description = self.tag_to_string(divdesc)
date = strftime(self.timefmt)
@@ -127,5 +129,17 @@ class Wired(BasicNewsRecipe):
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
+ for item in soup.findAll('a'):
+ if item.string is not None:
+ tstr = item.string
+ item.replaceWith(tstr)
+ else:
+ item.name='span'
+ for atrs in ['href','target','alt','title','name','id']:
+ if item.has_key(atrs):
+ del item[atrs]
+ for item in soup.findAll('img'):
+ if not item.has_key('alt'):
+ item['alt'] = 'image'
return soup
diff --git a/setup/installer/osx/app/main.py b/setup/installer/osx/app/main.py
index 140f58a6b7..209ea14955 100644
--- a/setup/installer/osx/app/main.py
+++ b/setup/installer/osx/app/main.py
@@ -612,8 +612,13 @@ class Py2App(object):
dmg = os.path.join(destdir, volname+'.dmg')
if os.path.exists(dmg):
os.unlink(dmg)
- subprocess.check_call(['/usr/bin/hdiutil', 'create', '-srcfolder', os.path.abspath(d),
+ tdir = tempfile.mkdtemp()
+ shutil.copytree(d, os.path.join(tdir, os.path.basename(d)),
+ symlinks=True)
+ os.symlink('/Applications', os.path.join(tdir, 'Applications'))
+ subprocess.check_call(['/usr/bin/hdiutil', 'create', '-srcfolder', tdir,
'-volname', volname, '-format', format, dmg])
+ shutil.rmtree(tdir)
if internet_enable:
subprocess.check_call(['/usr/bin/hdiutil', 'internet-enable', '-yes', dmg])
size = os.stat(dmg).st_size/(1024*1024.)
diff --git a/setup/publish.py b/setup/publish.py
index ba8a4992a7..fb873a90d9 100644
--- a/setup/publish.py
+++ b/setup/publish.py
@@ -43,8 +43,8 @@ class Stage3(Command):
description = 'Stage 3 of the publish process'
sub_commands = ['upload_user_manual', 'upload_demo', 'sdist',
- 'upload_to_google_code', 'tag_release', 'upload_to_server',
- 'upload_to_sourceforge', 'upload_to_mobileread',
+ 'upload_to_mobileread', 'upload_to_google_code',
+ 'tag_release', 'upload_to_server', 'upload_to_sourceforge',
]
class Stage4(Command):
diff --git a/src/calibre/__init__.py b/src/calibre/__init__.py
index a8cbe87e3e..2585b5d081 100644
--- a/src/calibre/__init__.py
+++ b/src/calibre/__init__.py
@@ -254,7 +254,7 @@ def browser(honor_time=True, max_time=2, mobile_browser=False):
opener.set_handle_refresh(True, max_time=max_time, honor_time=honor_time)
opener.set_handle_robots(False)
opener.addheaders = [('User-agent', ' Mozilla/5.0 (Windows; U; Windows CE 5.1; rv:1.8.1a3) Gecko/20060610 Minimo/0.016' if mobile_browser else \
- 'Mozilla/5.0 (X11; U; i686 Linux; en_US; rv:1.8.0.4) Gecko/20060508 Firefox/1.5.0.4')]
+ 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.13) Gecko/20101210 Gentoo Firefox/3.6.13')]
http_proxy = get_proxies().get('http', None)
if http_proxy:
opener.set_proxies({'http':http_proxy})
diff --git a/src/calibre/constants.py b/src/calibre/constants.py
index 731b56ad18..bc359a2b79 100644
--- a/src/calibre/constants.py
+++ b/src/calibre/constants.py
@@ -2,7 +2,7 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
__appname__ = 'calibre'
-__version__ = '0.7.35'
+__version__ = '0.7.37'
__author__ = "Kovid Goyal