Convert syntax to meet py3 standards

.gitignore

@@ -48,3 +48,5 @@ recipes/*.mobi
 recipes/*.epub
 recipes/debug
 /.metadata/
+.idea
+/*env*/

manual/custom.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python2
 # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
 
+from __future__ import print_function
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 import os, re, textwrap
@@ -198,12 +199,12 @@ def update_cli_doc(name, raw, app):
     old_raw = open(path, 'rb').read() if os.path.exists(path) else ''
     if not os.path.exists(path) or old_raw != raw:
         import difflib
-        print path, 'has changed'
+        print(path, 'has changed')
         if old_raw:
             lines = difflib.unified_diff(old_raw.splitlines(), raw.splitlines(),
                     path, path)
             for line in lines:
-                print line
+                print(line)
         app.builder.info('creating '+os.path.splitext(os.path.basename(path))[0])
         p = os.path.dirname(path)
         if p and not os.path.exists(p):
@@ -236,7 +237,7 @@ def render_options(cmd, groups, options_header=True, add_program=True, header_le
 
 
 def mark_options(raw):
-    raw = re.sub(r'(\s+)--(\s+)', ur'\1``--``\2', raw)
+    raw = re.sub(r'(\s+)--(\s+)', u'\\1``--``\\2', raw)
 
     def sub(m):
         opt = m.group()

manual/latex.py

@@ -18,9 +18,9 @@ def finish(self):
         LaTeXBuilder.finish(self)
         self.info('Fixing Cyrillic characters...')
         tex = os.path.join(self.outdir, 'calibre.tex')
-        with open(tex, 'r+b') as f:
+        with open(tex, 'r+') as f:
             raw = f.read()
-            for x in (b'Михаил Горбачёв', b'Фёдор Миха́йлович Достоевский'):
-                raw = raw.replace(x, br'{\fontencoding{T2A}\selectfont %s}' % (x.replace(b'а́', b'a')))
+            for x in (u'Михаил Горбачёв', u'Фёдор Миха́йлович Достоевский'):
+                raw = raw.replace(x, u'{\\fontencoding{T2A}\\selectfont %s}' % (x.replace(u'а́', u'a')))
             f.seek(0)
             f.write(raw)

recipes/DrawAndCook.recipe

@@ -1,3 +1,4 @@
+from __future__ import print_function
 from calibre.web.feeds.news import BasicNewsRecipe
 import re
 
@@ -30,7 +31,7 @@ class DrawAndCook(BasicNewsRecipe):
             articles = self.make_links(url)
             if articles:
                 feeds.append((title, articles))
-        print 'feeds are: ', feeds
+        print('feeds are: ', feeds)
         return feeds
 
     def make_links(self, url):
@@ -45,9 +46,9 @@ class DrawAndCook(BasicNewsRecipe):
             'li', attrs={'data-id': re.compile(r'artwork_entry_\d+', re.DOTALL)})
         for recipe in recipes:
             page_url = self.INDEX + recipe.a['href']
-            print 'page_url is: ', page_url
+            print('page_url is: ', page_url)
             title = recipe.find('strong').string
-            print 'title is: ', title
+            print('title is: ', title)
             current_articles.append(
                 {'title': title, 'url': page_url, 'description': '', 'date': date})
         return current_articles

recipes/al_monitor.recipe

@@ -1,6 +1,7 @@
 #!/usr/bin/env  python2
 # -*- coding: utf-8 -*-
-__license__ = 'GPL v3'
+from __future__ import print_function
+__license__   = 'GPL v3'
 __copyright__ = '2014, spswerling'
 '''
 http://www.al-monitor.com/

recipes/am730.recipe

@@ -1,5 +1,6 @@
 # vim:fileencoding=UTF-8
 from __future__ import unicode_literals
+from __future__ import print_function
 __license__ = 'GPL v3'
 __copyright__ = '2013, Eddie Lau'
 __Date__ = ''
@@ -60,7 +61,7 @@ class AM730(BasicNewsRecipe):
             title = href.split('/')[-1].split('-')[0]
             title = urllib.unquote(title.encode('ASCII'))  # .decode('utf-8')
             if self.debug:
-                print title
+                print(title)
             try:
                 if articles.index({'title':title,'url':href})>=0:
                     # print 'already added'
@@ -73,7 +74,7 @@ class AM730(BasicNewsRecipe):
             if (len(articles) >= self.max_articles_per_feed):
                 break
         if self.debug:
-            print articles
+            print(articles)
         return (sectionName,articles)
 
     def parse_index(self):
@@ -89,8 +90,8 @@ class AM730(BasicNewsRecipe):
         SectionsArticles=[]
         for (title, url) in Sections:
             if self.debug:
-                print title
-                print url
+                print(title)
+                print(url)
             SectionsArticles.append(self.getAMSectionArticles(title,url))
 #        feeds.append(articles[0]['url'])
         return SectionsArticles

recipes/android_com_pl.recipe

@@ -15,5 +15,5 @@ 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(ur'<p>.{,1}</p>', re.DOTALL), lambda match: '')]
+        (re.compile(u'<p>.{,1}</p>', re.DOTALL), lambda match: '')]
     feeds = [(u'Android', u'http://android.com.pl/feed/')]

recipes/appledaily_tw.recipe

@@ -104,7 +104,7 @@ class AppledailyTW(BasicNewsRecipe):
     ]
 
     def preprocess_raw_html(self, raw_html, url):
-        raw_html = re.sub(ur'<a href=".*?<br><br>.*?<\/a>', '', raw_html)
+        raw_html = re.sub(unicode(r'<a href=".*?<br><br>.*?<\/a>'), '', raw_html)
         raw_html = re.sub(
-            ur'<title>(.*?)[\s]+\|.*<\/title>', '<title>\1<\/title>', raw_html)
+            unicode(r'<title>(.*?)[\s]+\|.*<\/title>', '<title>\1<\/title>'), raw_html)
         return raw_html

recipes/auto_prove.recipe

@@ -1,5 +1,6 @@
 #!/usr/bin/env  python2
-__license__ = 'GPL v3'
+from __future__ import print_function
+__license__   = 'GPL v3'
 __author__ = 'GabrieleMarini, based on Darko Miletic'
 __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini'
 __version__ = 'v1.02 Marini Gabriele '
@@ -56,7 +57,7 @@ class AutoPR(BasicNewsRecipe):
         ]:
             soup = self.index_to_soup(url)
             soup = soup.find('channel')
-            print soup
+            print(soup)
 
             for article in soup.findAllNext('item'):
                 title = self.tag_to_string(article.title)

recipes/benchmark_pl.recipe

@@ -16,8 +16,8 @@ class BenchmarkPl(BasicNewsRecipe):
     extra_css = 'ul {list-style-type: none;}'
     no_stylesheets = True
     use_embedded_content = False
-    preprocess_regexps = [(re.compile(ur'<h3><span style="font-size: small;">&nbsp;Zobacz poprzednie <a href="http://www.benchmark.pl/news/zestawienie/grupa_id/135">Opinie dnia:</a></span>.*</body>',  # noqa
-        re.DOTALL | re.IGNORECASE), lambda match: '</body>'), (re.compile(ur'Więcej o .*?</ul>', re.DOTALL | re.IGNORECASE), lambda match: '')]  # noqa
+    preprocess_regexps = [(re.compile(u'<h3><span style="font-size: small;">&nbsp;Zobacz poprzednie <a href="http://www.benchmark.pl/news/zestawienie/grupa_id/135">Opinie dnia:</a></span>.*</body>',  # noqa
+        re.DOTALL | re.IGNORECASE), lambda match: '</body>'), (re.compile(u'Więcej o .*?</ul>', re.DOTALL | re.IGNORECASE), lambda match: '')]  # noqa
 
     keep_only_tags = [dict(id=['articleHeader', 'articleGallery']), dict(
         name='div', attrs={'class': ['m_zwykly', 'gallery']}), dict(id='article')]

recipes/birmingham_post.recipe

@@ -1,3 +1,4 @@
+from __future__ import print_function
 from calibre.web.feeds.news import BasicNewsRecipe
 import re
 import mechanize
@@ -26,11 +27,11 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
         # look for the block containing the sun button and url
         cov = soup.find(attrs={'height': re.compile(
             '3'), 'alt': re.compile('Post')})
-        print
-        print '%%%%%%%%%%%%%%%', cov
-        print
+        print()
+        print('%%%%%%%%%%%%%%%', cov)
+        print()
         cov2 = str(cov['src'])
-        print '88888888 ', cov2, ' 888888888888'
+        print('88888888 ', cov2, ' 888888888888')
 
         # cover_url=cov2
         # return cover_url

recipes/brewiarz.recipe

@@ -1,6 +1,7 @@
 #!/usr/bin/env python2
 
-__license__ = 'GPL v3'
+from __future__ import print_function
+__license__   = 'GPL v3'
 
 from calibre.web.feeds.news import BasicNewsRecipe
 import datetime
@@ -142,7 +143,7 @@ class brewiarz(BasicNewsRecipe):
                     if x == tag:
                         break
                 else:
-                    print "Can't find", tag, "in", tag.parent
+                    print("Can't find", tag, "in", tag.parent)
                     continue
                 for r in reversed(tag.contents):
                     tag.parent.insert(i, r)

recipes/calgary_herald.recipe

@@ -1,5 +1,6 @@
 #!/usr/bin/env  python2
 # -*- coding: utf-8 -*-
+from __future__ import print_function
 __license__ = 'GPL v3'
 
 '''

recipes/ciekawostki_historyczne.recipe

@@ -14,8 +14,8 @@ class Ciekawostki_Historyczne(BasicNewsRecipe):
     max_articles_per_feed = 100
     extra_css = 'img.alignleft {float:left; margin-right:5px;} .alignright {float:right; margin-left:5px;}'
     oldest_article = 12
-    preprocess_regexps = [(re.compile(ur'Ten artykuł ma kilka stron.*?</fb:like>', re.DOTALL),
-                           lambda match: ''), (re.compile(ur'<h2>Zobacz też:</h2>.*?</ol>', re.DOTALL), lambda match: '')]
+    preprocess_regexps = [(re.compile(u'Ten artykuł ma kilka stron.*?</fb:like>', re.DOTALL),
+                           lambda match: ''), (re.compile(u'<h2>Zobacz też:</h2>.*?</ol>', re.DOTALL), lambda match: '')]
     no_stylesheets = True
     remove_empty_feeds = True
     keep_only_tags = [dict(name='div', attrs={'class': 'post'})]

recipes/cio_magazine.recipe

@@ -1,3 +1,4 @@
+from __future__ import print_function
 # Los primeros comentarios son las dificultades que he tenido con el Piton
 # Cuando da error UTF8 revisa los comentarios (acentos). En notepad++ Search, Goto, posicion y lo ves.
 # Editar con Notepad++ Si pone - donde no debe es que ha indentado mal... Edit - Blank operations - tab to space
@@ -87,7 +88,7 @@ class CIO_Magazine(BasicNewsRecipe):
         if INDEX.startswith('/'):  # protegiendonos de que dejen de usarlos
             INDEX = 'http://www.cio.com' + INDEX
         # Y nos aseguramos en los logs que lo estamos haciendo bien
-        print ("INDEX en parse_index: ", INDEX)
+        print("INDEX en parse_index: ", INDEX)
 
     # Ya sabemos cual es la revista... procesemosla.
         soup = self.index_to_soup(INDEX)
@@ -103,7 +104,7 @@ class CIO_Magazine(BasicNewsRecipe):
 
             if div['class'] == 'heading':
                 key = string.capwords(self.tag_to_string(div.span))
-                print ("Key: ", key)  # Esto es para depurar
+                print("Key: ", key)  # Esto es para depurar
                 articles[key] = []
                 feeds.append(key)
 
@@ -126,7 +127,7 @@ class CIO_Magazine(BasicNewsRecipe):
 
                 if summary:
                     description = self.tag_to_string(summary, use_alt=False)
-                    print ("Description = ", description)
+                    print("Description = ", description)
 
                 # Esto esta copiado del NY times
                 feed = key if key is not None else 'Uncategorized'

recipes/cnetjapan.recipe

@@ -16,11 +16,11 @@ class CNetJapan(BasicNewsRecipe):
     remove_javascript = True
 
     preprocess_regexps = [
-        (re.compile(ur'<!--\u25B2contents_left END\u25B2-->.*</body>', re.DOTALL | re.IGNORECASE | re.UNICODE),
+        (re.compile(unicode(r'<!--\u25B2contents_left END\u25B2-->.*</body>'), re.DOTALL | re.IGNORECASE | re.UNICODE),
          lambda match: '</body>'),
         (re.compile(r'<!--AD_ELU_HEADER-->.*</body>', re.DOTALL | re.IGNORECASE),
             lambda match: '</body>'),
-        (re.compile(ur'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->', re.UNICODE),
+        (re.compile(unicode(r'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->'), re.UNICODE),
             lambda match: '<!-- removed -->'),
     ]
 

recipes/cnetjapan_digital.recipe

@@ -14,11 +14,11 @@ class CNetJapanDigital(BasicNewsRecipe):
     remove_javascript = True
 
     preprocess_regexps = [
-        (re.compile(ur'<!--\u25B2contents_left END\u25B2-->.*</body>', re.DOTALL | re.IGNORECASE | re.UNICODE),
+        (re.compile(unicode(r'<!--\u25B2contents_left END\u25B2-->.*</body>'), re.DOTALL | re.IGNORECASE | re.UNICODE),
          lambda match: '</body>'),
         (re.compile(r'<!--AD_ELU_HEADER-->.*</body>', re.DOTALL | re.IGNORECASE),
             lambda match: '</body>'),
-        (re.compile(ur'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->', re.UNICODE),
+        (re.compile(unicode(r'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->'), re.UNICODE),
             lambda match: '<!-- removed -->'),
     ]
 

recipes/cnetjapan_release.recipe

@@ -14,11 +14,11 @@ class CNetJapanRelease(BasicNewsRecipe):
     remove_javascript = True
 
     preprocess_regexps = [
-        (re.compile(ur'<!--\u25B2contents_left END\u25B2-->.*</body>', re.DOTALL | re.IGNORECASE | re.UNICODE),
+        (re.compile(unicode(r'<!--\u25B2contents_left END\u25B2-->.*</body>'), re.DOTALL | re.IGNORECASE | re.UNICODE),
          lambda match: '</body>'),
         (re.compile(r'<!--AD_ELU_HEADER-->.*</body>', re.DOTALL | re.IGNORECASE),
             lambda match: '</body>'),
-        (re.compile(ur'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->', re.UNICODE),
+        (re.compile(unicode(r'<!-- \u25B2\u95A2\u9023\u30BF\u30B0\u25B2 -->.*<!-- \u25B2ZDNet\u25B2 -->'), re.UNICODE),
             lambda match: '<!-- removed -->'),
     ]
 

recipes/computerworld_pl.recipe

@@ -16,7 +16,7 @@ class Computerworld_pl(BasicNewsRecipe):
     max_articles_per_feed = 100
     use_embedded_content = False
     preprocess_regexps = [(re.compile(u'Zobacz również:', re.IGNORECASE), lambda m: ''),
-                          (re.compile(ur'[*]+reklama[*]+', re.IGNORECASE), lambda m: ''), ]
+                          (re.compile(u'[*]+reklama[*]+', re.IGNORECASE), lambda m: ''), ]
     keep_only_tags = [dict(name='article')]
     remove_tags = [dict(attrs={'class': ['share_tools nocontent', 'rec']}),
          dict(name='ul',attrs={'class':'tags'}),

recipes/daily_express.recipe

@@ -1,5 +1,6 @@
 # vim:fileencoding=UTF-8
 from __future__ import unicode_literals
+from __future__ import print_function
 
 import re
 
@@ -65,7 +66,7 @@ class AdvancedUserRecipe1390132023(BasicNewsRecipe):
         feeds = BasicNewsRecipe.parse_feeds(self)
         for feed in feeds:
             for article in feed.articles[:]:
-                print 'article.title is: ', article.title
+                print('article.title is: ', article.title)
                 if 'WATCH:' in article.title.upper():
                     feed.articles.remove(article)
 

recipes/dilemaveche.recipe

@@ -1,7 +1,8 @@
 #!/usr/bin/env  python2
 # -*- coding: utf-8 -*-
 
-__license__ = 'GPL v3'
+from __future__ import print_function
+__license__   = 'GPL v3'
 __copyright__ = u'2014-01-09, Silviu Cotoar\u0103, Marius Popescu'
 '''
 dilemaveche.ro

recipes/dnevnik_mk.recipe

@@ -1,4 +1,5 @@
 #!/usr/bin/env  python2
+from __future__ import print_function
 
 __author__ = 'Darko Spasovski'
 __license__ = 'GPL v3'
@@ -64,7 +65,7 @@ class Dnevnik(BasicNewsRecipe):
             containerTable = section.findPrevious(
                 name='table').findNextSibling(name='table')
             if containerTable is None:
-                print 'No container table found - page layout may have been changed.'
+                print('No container table found - page layout may have been changed.')
                 continue
             articles = []
             for article in containerTable.findAll('a', attrs={'class': 'WB_DNEVNIK_ArhivaFormText'}):

recipes/dobreprogamy.recipe

@@ -19,7 +19,7 @@ class Dobreprogramy_pl(BasicNewsRecipe):
     max_articles_per_feed = 100
     remove_attrs = ['style', 'width', 'height']
     preprocess_regexps = [(re.compile(
-        ur'<div id="\S+360pmp4">Twoja przeglądarka nie obsługuje Flasha i HTML5 lub wyłączono obsługę JavaScript...</div>'), lambda match: '')]
+        unicode(r'<div id="\S+360pmp4">Twoja przeglądarka nie obsługuje Flasha i HTML5 lub wyłączono obsługę JavaScript...</div>')), lambda match: '')]
     keep_only_tags = [dict(name='h1'), dict(
         attrs={'class': ['entry single']}), dict(id='phContent_divArticle')]
     remove_tags = [dict(attrs={'class': ['newsOptions', 'noPrint', 'komentarze', 'tags  font-heading-master', 'social nested-grid  grid-margin-px15-top clearfix no-mobile', 'page-info text-h4 font-heading grid-margin-px15-top color-annotation clearfix', 'series grid-margin-px30-top']}), dict(id='komentarze'), dict(id='phContent_ctl02_sBreadcrumb'), dict(name='iframe')]  # noqa

recipes/dziennik_wschodni.recipe

@@ -19,8 +19,8 @@ class DziennikWschodni(BasicNewsRecipe):
     no_stylesheets = True
     ignore_duplicate_articles = {'title', 'url'}
 
-    preprocess_regexps = [(re.compile(ur'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(ur'Przeczytaj także:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''),  # noqa
-                          (re.compile(ur'Przeczytaj również:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(ur'Zobacz też:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: '')]  # noqa
+    preprocess_regexps = [(re.compile(u'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(u'Przeczytaj także:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''),  # noqa
+                          (re.compile(u'Przeczytaj również:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(u'Zobacz też:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: '')]  # noqa
 
     keep_only_tags = [dict(id=['article', 'cover', 'photostory'])]
     remove_tags = [dict(id=['articleTags', 'articleMeta', 'boxReadIt', 'articleGalleries', 'articleConnections',

recipes/echo_dnia.recipe

@@ -20,8 +20,8 @@ class EchoDnia(BasicNewsRecipe):
     use_embedded_content = False
     ignore_duplicate_articles = {'title', 'url'}
 
-    preprocess_regexps = [(re.compile(ur'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(ur'Przeczytaj także:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''),  # noqa
-                          (re.compile(ur'Przeczytaj również:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(ur'Zobacz też:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: '')]  # noqa
+    preprocess_regexps = [(re.compile(u'Czytaj:.*?</a>', re.DOTALL), lambda match: ''), (re.compile(u'Przeczytaj także:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''),  # noqa
+                          (re.compile(u'Przeczytaj również:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: ''), (re.compile(u'Zobacz też:.*?</a>', re.DOTALL | re.IGNORECASE), lambda match: '')]  # noqa
 
     keep_only_tags = [dict(id=['article', 'cover', 'photostory'])]
     remove_tags = [dict(id=['articleTags', 'articleMeta', 'boxReadIt', 'articleGalleries', 'articleConnections',

recipes/edmonton_journal.recipe

@@ -1,5 +1,6 @@
 #!/usr/bin/env  python2
 # -*- coding: utf-8 -*-
+from __future__ import print_function
 __license__ = 'GPL v3'
 
 '''

recipes/el_cultural.recipe

@@ -1,3 +1,4 @@
+from __future__ import print_function
 from calibre.web.feeds.recipes import BasicNewsRecipe
 
 
@@ -31,7 +32,7 @@ class RevistaElCultural(BasicNewsRecipe):
 
     # TO GET ARTICLES IN SECTION
     def ec_parse_section(self, url, titleSection):
-        print 'Section: ' + titleSection
+        print('Section: ' + titleSection)
         soup = self.index_to_soup(url)
         div = soup.find(attrs={'id': 'gallery'})
         current_articles = []