Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

New recipes for various CanWest Canadian news sources by Nick Redding

Browse Source
This commit is contained in:
Kovid Goyal 2010-01-20 21:01:43 -07:00
parent df019215ca
commit 5132aba5f0
10 changed files with 1185 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

121
resources/recipes/calgary_herald.recipe Normal file
View File

@ -0,0 +1,121 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Calgary Herald
title = u'Calgary Herald'
url_prefix = 'http://www.calgaryherald.com'
description = u'News from Calgary, AB'
# un-comment the following three lines for the Regina Leader-Post
#title = u'Regina Leader-Post'
#url_prefix = 'http://www.leaderpost.com'
#description = u'News from Regina, SK'
# un-comment the following three lines for the Saskatoon Star-Phoenix
#title = u'Saskatoon Star-Phoenix'
#url_prefix = 'http://www.thestarphoenix.com'
#description = u'News from Saskatoon, SK'
# un-comment the following three lines for the Windsor Star
#title = u'Windsor Star'
#url_prefix = 'http://www.windsorstar.com'
#description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

126
resources/recipes/edmonton_journal.recipe Normal file
View File

@ -0,0 +1,126 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Edmonton Journal
title = u'Edmonton Journal'
url_prefix = 'http://www.edmontonjournal.com'
description = u'News from Edmonton, AB'
# un-comment the following three lines for the Calgary Herald
#title = u'Calgary Herald'
#url_prefix = 'http://www.calgaryherald.com'
#description = u'News from Calgary, AB'
# un-comment the following three lines for the Regina Leader-Post
#title = u'Regina Leader-Post'
#url_prefix = 'http://www.leaderpost.com'
#description = u'News from Regina, SK'
# un-comment the following three lines for the Saskatoon Star-Phoenix
#title = u'Saskatoon Star-Phoenix'
#url_prefix = 'http://www.thestarphoenix.com'
#description = u'News from Saskatoon, SK'
# un-comment the following three lines for the Windsor Star
#title = u'Windsor Star'
#url_prefix = 'http://www.windsorstar.com'
#description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

96
resources/recipes/montreal_gazette.recipe Normal file
View File

@ -0,0 +1,96 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Montreal Gazette
title = u'Montreal Gazette'
url_prefix = 'http://www.montrealgazette.com'
description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

101
resources/recipes/ottawa_citizen.recipe Normal file
View File

@ -0,0 +1,101 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Ottawa Citizen
title = u'Ottawa Citizen'
url_prefix = 'http://www.ottawacitizen.com'
description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

116
resources/recipes/regina_leader_post.recipe Normal file
View File

@ -0,0 +1,116 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Regina Leader-Post
title = u'Regina Leader-Post'
url_prefix = 'http://www.leaderpost.com'
description = u'News from Regina, SK'
# un-comment the following three lines for the Saskatoon Star-Phoenix
#title = u'Saskatoon Star-Phoenix'
#url_prefix = 'http://www.thestarphoenix.com'
#description = u'News from Saskatoon, SK'
# un-comment the following three lines for the Windsor Star
#title = u'Windsor Star'
#url_prefix = 'http://www.windsorstar.com'
#description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

111
resources/recipes/saskatoon_star_phoenix.recipe Normal file
View File

@ -0,0 +1,111 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Saskatoon Star-Phoenix
title = u'Saskatoon Star-Phoenix'
url_prefix = 'http://www.thestarphoenix.com'
description = u'News from Saskatoon, SK'
# un-comment the following three lines for the Windsor Star
#title = u'Windsor Star'
#url_prefix = 'http://www.windsorstar.com'
#description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

136
resources/recipes/vancouver_provice.recipe Normal file
View File

@ -0,0 +1,136 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Vancouver Province
title = u'Vancouver Province'
url_prefix = 'http://www.theprovince.com'
description = u'News from Vancouver, BC'
# un-comment the following three lines for the Vancouver Sun
#title = u'Vancouver Sun'
#url_prefix = 'http://www.vancouversun.com'
#description = u'News from Vancouver, BC'
# un-comment the following three lines for the Edmonton Journal
#title = u'Edmonton Journal'
#url_prefix = 'http://www.edmontonjournal.com'
#description = u'News from Edmonton, AB'
# un-comment the following three lines for the Calgary Herald
#title = u'Calgary Herald'
#url_prefix = 'http://www.calgaryherald.com'
#description = u'News from Calgary, AB'
# un-comment the following three lines for the Regina Leader-Post
#title = u'Regina Leader-Post'
#url_prefix = 'http://www.leaderpost.com'
#description = u'News from Regina, SK'
# un-comment the following three lines for the Saskatoon Star-Phoenix
#title = u'Saskatoon Star-Phoenix'
#url_prefix = 'http://www.thestarphoenix.com'
#description = u'News from Saskatoon, SK'
# un-comment the following three lines for the Windsor Star
#title = u'Windsor Star'
#url_prefix = 'http://www.windsorstar.com'
#description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

131
resources/recipes/vancouver_sun.recipe Normal file
View File

@ -0,0 +1,131 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Vancouver Sun
title = u'Vancouver Sun'
url_prefix = 'http://www.vancouversun.com'
description = u'News from Vancouver, BC'
# un-comment the following three lines for the Edmonton Journal
#title = u'Edmonton Journal'
#url_prefix = 'http://www.edmontonjournal.com'
#description = u'News from Edmonton, AB'
# un-comment the following three lines for the Calgary Herald
#title = u'Calgary Herald'
#url_prefix = 'http://www.calgaryherald.com'
#description = u'News from Calgary, AB'
# un-comment the following three lines for the Regina Leader-Post
#title = u'Regina Leader-Post'
#url_prefix = 'http://www.leaderpost.com'
#description = u'News from Regina, SK'
# un-comment the following three lines for the Saskatoon Star-Phoenix
#title = u'Saskatoon Star-Phoenix'
#url_prefix = 'http://www.thestarphoenix.com'
#description = u'News from Saskatoon, SK'
# un-comment the following three lines for the Windsor Star
#title = u'Windsor Star'
#url_prefix = 'http://www.windsorstar.com'
#description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

141
resources/recipes/vic_times.recipe Normal file
View File

@ -0,0 +1,141 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Victoria Times Colonist
title = u'Victoria Times Colonist'
url_prefix = 'http://www.timescolonist.com'
description = u'News from Victoria, BC'
# un-comment the following three lines for the Vancouver Province
#title = u'Vancouver Province'
#url_prefix = 'http://www.theprovince.com'
#description = u'News from Vancouver, BC'
# un-comment the following three lines for the Vancouver Sun
#title = u'Vancouver Sun'
#url_prefix = 'http://www.vancouversun.com'
#description = u'News from Vancouver, BC'
# un-comment the following three lines for the Edmonton Journal
#title = u'Edmonton Journal'
#url_prefix = 'http://www.edmontonjournal.com'
#description = u'News from Edmonton, AB'
# un-comment the following three lines for the Calgary Herald
#title = u'Calgary Herald'
#url_prefix = 'http://www.calgaryherald.com'
#description = u'News from Calgary, AB'
# un-comment the following three lines for the Regina Leader-Post
#title = u'Regina Leader-Post'
#url_prefix = 'http://www.leaderpost.com'
#description = u'News from Regina, SK'
# un-comment the following three lines for the Saskatoon Star-Phoenix
#title = u'Saskatoon Star-Phoenix'
#url_prefix = 'http://www.thestarphoenix.com'
#description = u'News from Saskatoon, SK'
# un-comment the following three lines for the Windsor Star
#title = u'Windsor Star'
#url_prefix = 'http://www.windsorstar.com'
#description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans

106
resources/recipes/windows_star.recipe Normal file
View File

@ -0,0 +1,106 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
'''
www.canada.com
'''
from calibre.web.feeds.recipes import BasicNewsRecipe
class CanWestPaper(BasicNewsRecipe):
# un-comment the following three lines for the Windsor Star
title = u'Windsor Star'
url_prefix = 'http://www.windsorstar.com'
description = u'News from Windsor, ON'
# un-comment the following three lines for the Ottawa Citizen
#title = u'Ottawa Citizen'
#url_prefix = 'http://www.ottawacitizen.com'
#description = u'News from Ottawa, ON'
# un-comment the following three lines for the Montreal Gazette
#title = u'Montreal Gazette'
#url_prefix = 'http://www.montrealgazette.com'
#description = u'News from Montreal, QC'
language = 'en_CA'
__author__ = 'Nick Redding'
no_stylesheets = True
timefmt = ' [%b %d]'
extra_css = '''
.timestamp { font-size:xx-small; display: block; }
#storyheader { font-size: medium; }
#storyheader h1 { font-size: x-large; }
#storyheader h2 { font-size: large; font-style: italic; }
.byline { font-size:xx-small; }
#photocaption { font-size: small; font-style: italic }
#photocredit { font-size: xx-small; }'''
keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'})]
remove_tags = [{'class':'comments'},
dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}),
dict(name='div', attrs={'class':'viewmore'}),dict(name='li', attrs={'class':'email'}),
dict(name='div', attrs={'class':'story_tool_hr'}),dict(name='div', attrs={'class':'clear'}),
dict(name='div', attrs={'class':'story_tool'}),dict(name='div', attrs={'class':'copyright'}),
dict(name='div', attrs={'class':'rule_grey_solid'}),
dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})]
def preprocess_html(self,soup):
#delete iempty id attributes--they screw up the TOC for unknow reasons
divtags = soup.findAll('div',attrs={'id':''})
if divtags:
for div in divtags:
del(div['id'])
return soup
def parse_index(self):
soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html')
articles = {}
key = 'News'
ans = ['News']
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div',attrs={'class' : ["section_title02","featurecontent"]}):
#self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
# div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3,False)
ans.append(key)
self.log("Section name %s" % key)
continue
# div contains article data
h1tag = divtag.find('h1')
if not h1tag:
continue
atag = h1tag.find('a',href=True)
if not atag:
continue
url = self.url_prefix+'/news/todays-paper/'+atag['href']
#self.log("Section %s" % key)
#self.log("url %s" % url)
title = self.tag_to_string(atag,False)
#self.log("title %s" % title)
pubdate = ''
description = ''
ptag = divtag.find('p');
if ptag:
description = self.tag_to_string(ptag,False)
#self.log("description %s" % description)
author = ''
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag,False)
#self.log("author %s" % author)
if not articles.has_key(key):
articles[key] = []
articles[key].append(dict(title=title,url=url,date=pubdate,description=description,author=author,content=''))
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
return ans