diff --git a/recipes/calgary_herald.recipe b/recipes/calgary_herald.recipe index f7b1ee71d5..8c98aad4ae 100644 --- a/recipes/calgary_herald.recipe +++ b/recipes/calgary_herald.recipe @@ -7,7 +7,7 @@ www.canada.com ''' import re from calibre.web.feeds.recipes import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import Tag, BeautifulStoneSoup +from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup, Tag class CanWestPaper(BasicNewsRecipe): @@ -51,20 +51,20 @@ class CanWestPaper(BasicNewsRecipe): # un-comment the following six lines for the Vancouver Province -## title = u'Vancouver Province' -## url_prefix = 'http://www.theprovince.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' -## logo_url = 'vplogo.jpg' -## fp_tag = 'CAN_TP' + # title = u'Vancouver Province' + # url_prefix = 'http://www.theprovince.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' + # logo_url = 'vplogo.jpg' + # fp_tag = 'CAN_TP' # un-comment the following six lines for the Vancouver Sun -## title = u'Vancouver Sun' -## url_prefix = 'http://www.vancouversun.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' -## logo_url = 'vslogo.jpg' -## fp_tag = 'CAN_VS' + # title = u'Vancouver Sun' + # url_prefix = 'http://www.vancouversun.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' + # logo_url = 'vslogo.jpg' + # fp_tag = 'CAN_VS' # un-comment the following six lines for the Calgary Herald title = u'Calgary Herald' @@ -117,15 +117,17 @@ class CanWestPaper(BasicNewsRecipe): .photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } #photocredit { font-size: xx-small; font-weight: normal; }''' - keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'}),dict(name='div', attrs={'id':'storyphoto'})] + keep_only_tags = [dict(name='div', attrs={'id':re.compile('story')})] - remove_tags = [{'class':'comments'}, - dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), + remove_tags = [{'class':'comments'},{'class':'comment-intro'},{'class':'storytab'}, + dict(name='div', attrs={'class':'section_title'}),dict(name='div', attrs={'class':'sharebar'}),dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), dict(name='h2', attrs={'id':'photocredit'}), 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='div', attrs={'id':'soundoff'}), + dict(name='div', attrs={'id':re.compile('flyer')}), dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})] @@ -252,18 +254,23 @@ class CanWestPaper(BasicNewsRecipe): def handle_article(adiv,key): - h1tag = adiv.h1 + if adiv.name=='h1' or adiv.name=='h3': + h1tag = adiv + else: + h1tag = adiv.h1 + if h1tag is None: + h1tag = adiv.h3 if h1tag is not None: atag = h1tag.a if atag is not None: url = atag['href'] - if atag['href'].startswith('http'): + if url.startswith('/'): + url = self.url_prefix+url + if not url.startswith(self.url_prefix): + print("Rejected "+url) return - elif atag['href'].startswith('/'): - url = self.url_prefix+atag['href'] - else: - url = self.url_prefix+'/'+atag['href'] if url in self.url_list: + print("Rejected dup "+url) return self.url_list.append(url) title = self.tag_to_string(atag,False) @@ -290,22 +297,21 @@ class CanWestPaper(BasicNewsRecipe): articles[key].append(dict(title=title,url=url,date='',description=description,author='',content='')) def parse_web_index(key, keyurl): + print("Section: "+key+': '+self.url_prefix+keyurl) try: soup = self.index_to_soup(self.url_prefix+keyurl) except: + print("Section: "+key+' NOT FOUND'); return ans.append(key) mainsoup = soup.find('div','bodywrapper') footer = mainsoup.find(attrs={'id':'footerfeature'}) if footer is not None: footer.extract() - print("Section: "+key) - for wdiv in mainsoup.findAll('div',attrs={'id':re.compile('^HorizontalFeatureSlider_1_Story')}): - handle_article(wdiv,key) - wdiv.extract() - for wdiv in mainsoup.findAll(attrs={'id':['featurewidget','textfeature','textlinks_timestamp']}): - for adiv in wdiv.findAll('div','featurecontent'): - handle_article(adiv,key) + for wdiv in mainsoup.findAll(attrs={'class':['genericfeature']}): + wdiv.extract() + for wdiv in mainsoup.findAll(attrs={'class':['headline','featurecontent']}): + handle_article(wdiv,key) for (k,url) in self.postmedia_index_pages: parse_web_index(k,url) diff --git a/recipes/edmonton_journal.recipe b/recipes/edmonton_journal.recipe index 33d42d198e..e54159d7d7 100644 --- a/recipes/edmonton_journal.recipe +++ b/recipes/edmonton_journal.recipe @@ -51,28 +51,28 @@ class CanWestPaper(BasicNewsRecipe): # un-comment the following six lines for the Vancouver Province -## title = u'Vancouver Province' -## url_prefix = 'http://www.theprovince.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' -## logo_url = 'vplogo.jpg' -## fp_tag = 'CAN_TP' + # title = u'Vancouver Province' + # url_prefix = 'http://www.theprovince.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' + # logo_url = 'vplogo.jpg' + # fp_tag = 'CAN_TP' # un-comment the following six lines for the Vancouver Sun -## title = u'Vancouver Sun' -## url_prefix = 'http://www.vancouversun.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' -## logo_url = 'vslogo.jpg' -## fp_tag = 'CAN_VS' + # title = u'Vancouver Sun' + # url_prefix = 'http://www.vancouversun.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' + # logo_url = 'vslogo.jpg' + # fp_tag = 'CAN_VS' # un-comment the following six lines for the Calgary Herald -## title = u'Calgary Herald' -## url_prefix = 'http://www.calgaryherald.com' -## description = u'News from Calgary, AB' -## std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' -## logo_url = 'chlogo.jpg' -## fp_tag = 'CAN_CH' + # title = u'Calgary Herald' + # url_prefix = 'http://www.calgaryherald.com' + # description = u'News from Calgary, AB' + # std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' + # logo_url = 'chlogo.jpg' + # fp_tag = 'CAN_CH' # un-comment the following six lines for the Edmonton Journal title = u'Edmonton Journal' @@ -117,15 +117,17 @@ class CanWestPaper(BasicNewsRecipe): .photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } #photocredit { font-size: xx-small; font-weight: normal; }''' - keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'}),dict(name='div', attrs={'id':'storyphoto'})] + keep_only_tags = [dict(name='div', attrs={'id':re.compile('story')})] - remove_tags = [{'class':'comments'}, - dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), + remove_tags = [{'class':'comments'},{'class':'comment-intro'},{'class':'storytab'}, + dict(name='div', attrs={'class':'section_title'}),dict(name='div', attrs={'class':'sharebar'}),dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), dict(name='h2', attrs={'id':'photocredit'}), 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='div', attrs={'id':'soundoff'}), + dict(name='div', attrs={'id':re.compile('flyer')}), dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})] @@ -252,18 +254,23 @@ class CanWestPaper(BasicNewsRecipe): def handle_article(adiv,key): - h1tag = adiv.h1 + if adiv.name=='h1' or adiv.name=='h3': + h1tag = adiv + else: + h1tag = adiv.h1 + if h1tag is None: + h1tag = adiv.h3 if h1tag is not None: atag = h1tag.a if atag is not None: url = atag['href'] - if atag['href'].startswith('http'): + if url.startswith('/'): + url = self.url_prefix+url + if not url.startswith(self.url_prefix): + print("Rejected "+url) return - elif atag['href'].startswith('/'): - url = self.url_prefix+atag['href'] - else: - url = self.url_prefix+'/'+atag['href'] if url in self.url_list: + print("Rejected dup "+url) return self.url_list.append(url) title = self.tag_to_string(atag,False) @@ -290,22 +297,21 @@ class CanWestPaper(BasicNewsRecipe): articles[key].append(dict(title=title,url=url,date='',description=description,author='',content='')) def parse_web_index(key, keyurl): + print("Section: "+key+': '+self.url_prefix+keyurl) try: soup = self.index_to_soup(self.url_prefix+keyurl) except: + print("Section: "+key+' NOT FOUND'); return ans.append(key) mainsoup = soup.find('div','bodywrapper') footer = mainsoup.find(attrs={'id':'footerfeature'}) if footer is not None: footer.extract() - print("Section: "+key) - for wdiv in mainsoup.findAll('div',attrs={'id':re.compile('^HorizontalFeatureSlider_1_Story')}): - handle_article(wdiv,key) - wdiv.extract() - for wdiv in mainsoup.findAll(attrs={'id':['featurewidget','textfeature','textlinks_timestamp']}): - for adiv in wdiv.findAll('div','featurecontent'): - handle_article(adiv,key) + for wdiv in mainsoup.findAll(attrs={'class':['genericfeature']}): + wdiv.extract() + for wdiv in mainsoup.findAll(attrs={'class':['headline','featurecontent']}): + handle_article(wdiv,key) for (k,url) in self.postmedia_index_pages: parse_web_index(k,url) diff --git a/recipes/montreal_gazette.recipe b/recipes/montreal_gazette.recipe index 66f951f62f..497ad337ce 100644 --- a/recipes/montreal_gazette.recipe +++ b/recipes/montreal_gazette.recipe @@ -51,44 +51,44 @@ class CanWestPaper(BasicNewsRecipe): # un-comment the following six lines for the Vancouver Province -## title = u'Vancouver Province' -## url_prefix = 'http://www.theprovince.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' -## logo_url = 'vplogo.jpg' -## fp_tag = 'CAN_TP' + # title = u'Vancouver Province' + # url_prefix = 'http://www.theprovince.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' + # logo_url = 'vplogo.jpg' + # fp_tag = 'CAN_TP' # un-comment the following six lines for the Vancouver Sun -## title = u'Vancouver Sun' -## url_prefix = 'http://www.vancouversun.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' -## logo_url = 'vslogo.jpg' -## fp_tag = 'CAN_VS' + # title = u'Vancouver Sun' + # url_prefix = 'http://www.vancouversun.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' + # logo_url = 'vslogo.jpg' + # fp_tag = 'CAN_VS' # un-comment the following six lines for the Calgary Herald -## title = u'Calgary Herald' -## url_prefix = 'http://www.calgaryherald.com' -## description = u'News from Calgary, AB' -## std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' -## logo_url = 'chlogo.jpg' -## fp_tag = 'CAN_CH' + # title = u'Calgary Herald' + # url_prefix = 'http://www.calgaryherald.com' + # description = u'News from Calgary, AB' + # std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' + # logo_url = 'chlogo.jpg' + # fp_tag = 'CAN_CH' # un-comment the following six lines for the Edmonton Journal -## title = u'Edmonton Journal' -## url_prefix = 'http://www.edmontonjournal.com' -## description = u'News from Edmonton, AB' -## std_logo_url = 'http://www.edmontonjournal.com/images/logo_edmontonjournal.jpg' -## logo_url = 'ejlogo.jpg' -## fp_tag = 'CAN_EJ' + # title = u'Edmonton Journal' + # url_prefix = 'http://www.edmontonjournal.com' + # description = u'News from Edmonton, AB' + # std_logo_url = 'http://www.edmontonjournal.com/images/logo_edmontonjournal.jpg' + # logo_url = 'ejlogo.jpg' + # fp_tag = 'CAN_EJ' # un-comment the following six lines for the Ottawa Citizen -## title = u'Ottawa Citizen' -## url_prefix = 'http://www.ottawacitizen.com' -## description = u'News from Ottawa, ON' -## std_logo_url = 'http://www.ottawacitizen.com/images/logo_ottawacitizen.jpg' -## logo_url = 'oclogo.jpg' -## fp_tag = 'CAN_OC' + # title = u'Ottawa Citizen' + # url_prefix = 'http://www.ottawacitizen.com' + # description = u'News from Ottawa, ON' + # std_logo_url = 'http://www.ottawacitizen.com/images/logo_ottawacitizen.jpg' + # logo_url = 'oclogo.jpg' + # fp_tag = 'CAN_OC' # un-comment the following six lines for the Montreal Gazette title = u'Montreal Gazette' @@ -117,15 +117,17 @@ class CanWestPaper(BasicNewsRecipe): .photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } #photocredit { font-size: xx-small; font-weight: normal; }''' - keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'}),dict(name='div', attrs={'id':'storyphoto'})] + keep_only_tags = [dict(name='div', attrs={'id':re.compile('story')})] - remove_tags = [{'class':'comments'}, - dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), + remove_tags = [{'class':'comments'},{'class':'comment-intro'},{'class':'storytab'}, + dict(name='div', attrs={'class':'section_title'}),dict(name='div', attrs={'class':'sharebar'}),dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), dict(name='h2', attrs={'id':'photocredit'}), 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='div', attrs={'id':'soundoff'}), + dict(name='div', attrs={'id':re.compile('flyer')}), dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})] @@ -252,18 +254,23 @@ class CanWestPaper(BasicNewsRecipe): def handle_article(adiv,key): - h1tag = adiv.h1 + if adiv.name=='h1' or adiv.name=='h3': + h1tag = adiv + else: + h1tag = adiv.h1 + if h1tag is None: + h1tag = adiv.h3 if h1tag is not None: atag = h1tag.a if atag is not None: url = atag['href'] - if atag['href'].startswith('http'): + if url.startswith('/'): + url = self.url_prefix+url + if not url.startswith(self.url_prefix): + print("Rejected "+url) return - elif atag['href'].startswith('/'): - url = self.url_prefix+atag['href'] - else: - url = self.url_prefix+'/'+atag['href'] if url in self.url_list: + print("Rejected dup "+url) return self.url_list.append(url) title = self.tag_to_string(atag,False) @@ -290,22 +297,21 @@ class CanWestPaper(BasicNewsRecipe): articles[key].append(dict(title=title,url=url,date='',description=description,author='',content='')) def parse_web_index(key, keyurl): + print("Section: "+key+': '+self.url_prefix+keyurl) try: soup = self.index_to_soup(self.url_prefix+keyurl) except: + print("Section: "+key+' NOT FOUND'); return ans.append(key) mainsoup = soup.find('div','bodywrapper') footer = mainsoup.find(attrs={'id':'footerfeature'}) if footer is not None: footer.extract() - print("Section: "+key) - for wdiv in mainsoup.findAll('div',attrs={'id':re.compile('^HorizontalFeatureSlider_1_Story')}): - handle_article(wdiv,key) - wdiv.extract() - for wdiv in mainsoup.findAll(attrs={'id':['featurewidget','textfeature','textlinks_timestamp']}): - for adiv in wdiv.findAll('div','featurecontent'): - handle_article(adiv,key) + for wdiv in mainsoup.findAll(attrs={'class':['genericfeature']}): + wdiv.extract() + for wdiv in mainsoup.findAll(attrs={'class':['headline','featurecontent']}): + handle_article(wdiv,key) for (k,url) in self.postmedia_index_pages: parse_web_index(k,url) diff --git a/recipes/ottawa_citizen.recipe b/recipes/ottawa_citizen.recipe index 99052343ca..de93477e04 100644 --- a/recipes/ottawa_citizen.recipe +++ b/recipes/ottawa_citizen.recipe @@ -51,36 +51,36 @@ class CanWestPaper(BasicNewsRecipe): # un-comment the following six lines for the Vancouver Province -## title = u'Vancouver Province' -## url_prefix = 'http://www.theprovince.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' -## logo_url = 'vplogo.jpg' -## fp_tag = 'CAN_TP' + # title = u'Vancouver Province' + # url_prefix = 'http://www.theprovince.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' + # logo_url = 'vplogo.jpg' + # fp_tag = 'CAN_TP' # un-comment the following six lines for the Vancouver Sun -## title = u'Vancouver Sun' -## url_prefix = 'http://www.vancouversun.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' -## logo_url = 'vslogo.jpg' -## fp_tag = 'CAN_VS' + # title = u'Vancouver Sun' + # url_prefix = 'http://www.vancouversun.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' + # logo_url = 'vslogo.jpg' + # fp_tag = 'CAN_VS' # un-comment the following six lines for the Calgary Herald -## title = u'Calgary Herald' -## url_prefix = 'http://www.calgaryherald.com' -## description = u'News from Calgary, AB' -## std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' -## logo_url = 'chlogo.jpg' -## fp_tag = 'CAN_CH' + # title = u'Calgary Herald' + # url_prefix = 'http://www.calgaryherald.com' + # description = u'News from Calgary, AB' + # std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' + # logo_url = 'chlogo.jpg' + # fp_tag = 'CAN_CH' # un-comment the following six lines for the Edmonton Journal -## title = u'Edmonton Journal' -## url_prefix = 'http://www.edmontonjournal.com' -## description = u'News from Edmonton, AB' -## std_logo_url = 'http://www.edmontonjournal.com/images/logo_edmontonjournal.jpg' -## logo_url = 'ejlogo.jpg' -## fp_tag = 'CAN_EJ' + # title = u'Edmonton Journal' + # url_prefix = 'http://www.edmontonjournal.com' + # description = u'News from Edmonton, AB' + # std_logo_url = 'http://www.edmontonjournal.com/images/logo_edmontonjournal.jpg' + # logo_url = 'ejlogo.jpg' + # fp_tag = 'CAN_EJ' # un-comment the following six lines for the Ottawa Citizen title = u'Ottawa Citizen' @@ -117,15 +117,17 @@ class CanWestPaper(BasicNewsRecipe): .photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } #photocredit { font-size: xx-small; font-weight: normal; }''' - keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'}),dict(name='div', attrs={'id':'storyphoto'})] + keep_only_tags = [dict(name='div', attrs={'id':re.compile('story')})] - remove_tags = [{'class':'comments'}, - dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), + remove_tags = [{'class':'comments'},{'class':'comment-intro'},{'class':'storytab'}, + dict(name='div', attrs={'class':'section_title'}),dict(name='div', attrs={'class':'sharebar'}),dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), dict(name='h2', attrs={'id':'photocredit'}), 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='div', attrs={'id':'soundoff'}), + dict(name='div', attrs={'id':re.compile('flyer')}), dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})] @@ -252,18 +254,23 @@ class CanWestPaper(BasicNewsRecipe): def handle_article(adiv,key): - h1tag = adiv.h1 + if adiv.name=='h1' or adiv.name=='h3': + h1tag = adiv + else: + h1tag = adiv.h1 + if h1tag is None: + h1tag = adiv.h3 if h1tag is not None: atag = h1tag.a if atag is not None: url = atag['href'] - if atag['href'].startswith('http'): + if url.startswith('/'): + url = self.url_prefix+url + if not url.startswith(self.url_prefix): + print("Rejected "+url) return - elif atag['href'].startswith('/'): - url = self.url_prefix+atag['href'] - else: - url = self.url_prefix+'/'+atag['href'] if url in self.url_list: + print("Rejected dup "+url) return self.url_list.append(url) title = self.tag_to_string(atag,False) @@ -290,22 +297,21 @@ class CanWestPaper(BasicNewsRecipe): articles[key].append(dict(title=title,url=url,date='',description=description,author='',content='')) def parse_web_index(key, keyurl): + print("Section: "+key+': '+self.url_prefix+keyurl) try: soup = self.index_to_soup(self.url_prefix+keyurl) except: + print("Section: "+key+' NOT FOUND'); return ans.append(key) mainsoup = soup.find('div','bodywrapper') footer = mainsoup.find(attrs={'id':'footerfeature'}) if footer is not None: footer.extract() - print("Section: "+key) - for wdiv in mainsoup.findAll('div',attrs={'id':re.compile('^HorizontalFeatureSlider_1_Story')}): - handle_article(wdiv,key) - wdiv.extract() - for wdiv in mainsoup.findAll(attrs={'id':['featurewidget','textfeature','textlinks_timestamp']}): - for adiv in wdiv.findAll('div','featurecontent'): - handle_article(adiv,key) + for wdiv in mainsoup.findAll(attrs={'class':['genericfeature']}): + wdiv.extract() + for wdiv in mainsoup.findAll(attrs={'class':['headline','featurecontent']}): + handle_article(wdiv,key) for (k,url) in self.postmedia_index_pages: parse_web_index(k,url) diff --git a/recipes/vancouver_provice.recipe b/recipes/vancouver_provice.recipe deleted file mode 100644 index 9bb8085fdc..0000000000 --- a/recipes/vancouver_provice.recipe +++ /dev/null @@ -1,314 +0,0 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- -__license__ = 'GPL v3' - -''' -www.canada.com -''' -import re -from calibre.web.feeds.recipes import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup, Tag - - -class CanWestPaper(BasicNewsRecipe): - - postmedia_index_pages = [ - (u'Headlines',u'/index.html'), - (u'Ottawa & Area',u'/news/ottawa/index.html'), - (u'Vancouver',u'/news/vancouver/index.html'), - (u'Calgary',u'/news/calgary/index.html'), - (u'Edmonton',u'/news/edmonton/index.html'), - (u'Montreal',u'/news/montreal/index.html'), - (u'Fraser Valley',u'/news/fraser-valley/index.html'), - (u'British Columbia',u'/news/bc/index.html'), - (u'Alberta',u'/news/alberta/index.html'), - (u'Canada',u'/news/canada/index.html'), - (u'National',u'/news/national/index.html'), - (u'Politics',u'/news/politics/index.html'), - (u'Insight',u'/news/insight/index.html'), - (u'Special Reports',u'/news/specialreports/index.html'), - (u'Gangs',u'/news/gangs/index.html'), - (u'Education',u'/news/education/index.html'), - (u'Health',u'/news/health/index.html'), - (u'Environment',u'/news/environment/index.html'), - (u'World',u'/news/world/index.html'), - (u'Police Blotter',u'/news/crime-and-justice/index.html'), - (u'Crime',u'/news/blotter/index.html'), - (u'Around Town',u'/news/topic.html?t=keyword&q=Around+Town'), - (u'Diplomatica',u'/news/diplomatica/index.html'), - (u'Opinion',u'/opinion/index.html'), - (u'Columnists',u'/columnists/index.html'), - (u'Editorials',u'/opinion/editorials/index.html'), - (u'Letters',u'/opinion/letters/index.html'), - (u'Business',u'/business/index.html'), - (u'Sports',u'/sports/index.html'), - (u'Arts',u'/entertainment/index.html'), - (u'Life',u'/life/index.html'), - (u'Technology',u'/technology/index.html'), - (u'Travel',u'/travel/index.html'), - (u'Health',u'/health/index.html') - ] - - - # un-comment the following six lines for the Vancouver Province - title = u'Vancouver Province' - url_prefix = 'http://www.theprovince.com' - description = u'News from Vancouver, BC' - std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' - logo_url = 'vplogo.jpg' - fp_tag = 'CAN_TP' - - # un-comment the following six lines for the Vancouver Sun -## title = u'Vancouver Sun' -## url_prefix = 'http://www.vancouversun.com' -## description = u'News from Vancouver, BC' -## std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' -## logo_url = 'vslogo.jpg' -## fp_tag = 'CAN_VS' - - # un-comment the following six lines for the Calgary Herald -## title = u'Calgary Herald' -## url_prefix = 'http://www.calgaryherald.com' -## description = u'News from Calgary, AB' -## std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' -## logo_url = 'chlogo.jpg' -## fp_tag = 'CAN_CH' - - # un-comment the following six lines for the Edmonton Journal -## title = u'Edmonton Journal' -## url_prefix = 'http://www.edmontonjournal.com' -## description = u'News from Edmonton, AB' -## std_logo_url = 'http://www.edmontonjournal.com/images/logo_edmontonjournal.jpg' -## logo_url = 'ejlogo.jpg' -## fp_tag = 'CAN_EJ' - - # un-comment the following six lines for the Ottawa Citizen -## title = u'Ottawa Citizen' -## url_prefix = 'http://www.ottawacitizen.com' -## description = u'News from Ottawa, ON' -## std_logo_url = 'http://www.ottawacitizen.com/images/logo_ottawacitizen.jpg' -## logo_url = 'oclogo.jpg' -## fp_tag = 'CAN_OC' - - # un-comment the following six lines for the Montreal Gazette -## title = u'Montreal Gazette' -## url_prefix = 'http://www.montrealgazette.com' -## description = u'News from Montreal, QC' -## std_logo_url = 'http://www.montrealgazette.com/images/logo_montrealgazette.jpg' -## logo_url = 'mglogo.jpg' -## fp_tag = 'CAN_MG' - - Kindle_Fire=False - masthead_url = std_logo_url - - url_list = [] - language = 'en_CA' - __author__ = 'Nick Redding' - no_stylesheets = True - timefmt = ' [%b %d]' - encoding = 'utf-8' - extra_css = ''' - .timestamp { font-size:xx-small; display: block; } - #storyheader { font-size: medium; } - #storyheader h1 { font-size: x-large; } - #storyheader h2 { font-size: small; font-style: italic; } - .byline { font-size:xx-small; } - #photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } - .photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } - #photocredit { font-size: xx-small; font-weight: normal; }''' - - keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'}),dict(name='div', attrs={'id':'storyphoto'})] - - remove_tags = [{'class':'comments'}, - dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), - dict(name='h2', attrs={'id':'photocredit'}), - 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 get_cover_url(self): - from datetime import timedelta, date - cover = 'http://webmedia.newseum.org/newseum-multimedia/dfp/jpg'+str(date.today().day)+'/lg/'+self.fp_tag+'.jpg' - br = BasicNewsRecipe.get_browser(self) - daysback=1 - try: - br.open(cover) - except: - while daysback<7: - cover = 'http://webmedia.newseum.org/newseum-multimedia/dfp/jpg'+str((date.today() - timedelta(days=daysback)).day)+'/lg/'+self.fp_tag+'.jpg' - br = BasicNewsRecipe.get_browser(self) - try: - br.open(cover) - except: - daysback = daysback+1 - continue - break - if daysback==7: - self.log("\nCover unavailable") - cover = None - return cover - - def prepare_masthead_image(self, path_to_image, out_path): - if self.Kindle_Fire: - from calibre.utils.magick import Image, create_canvas - img = Image() - img.open(path_to_image) - width, height = img.size - img2 = create_canvas(width, height) - img2.compose(img) - img2.save(out_path) - else: - BasicNewsRecipe.prepare_masthead_image(self, path_to_image, out_path) - - def fixChars(self,string): - # Replace lsquo (\x91) - fixed = re.sub("\x91","‘",string) - # Replace rsquo (\x92) - fixed = re.sub("\x92","’",fixed) - # Replace ldquo (\x93) - fixed = re.sub("\x93","“",fixed) - # Replace rdquo (\x94) - fixed = re.sub("\x94","”",fixed) - # Replace ndash (\x96) - fixed = re.sub("\x96","–",fixed) - # Replace mdash (\x97) - fixed = re.sub("\x97","—",fixed) - fixed = re.sub("’","’",fixed) - return fixed - - def massageNCXText(self, description): - # Kindle TOC descriptions won't render certain characters - if description: - massaged = unicode(BeautifulStoneSoup(description, convertEntities=BeautifulStoneSoup.HTML_ENTITIES)) - # Replace '&' with '&' - massaged = re.sub("&","&", massaged) - return self.fixChars(massaged) - else: - return description - - def populate_article_metadata(self, article, soup, first): - if first: - picdiv = soup.find('body').find('img') - if picdiv is not None: - self.add_toc_thumbnail(article,re.sub(r'links\\link\d+\\','',picdiv['src'])) - xtitle = article.text_summary.strip() - if len(xtitle) == 0: - desc = soup.find('meta',attrs={'property':'og:description'}) - if desc is not None: - article.summary = article.text_summary = desc['content'] - - def strip_anchors(self,soup): - paras = soup.findAll(True) - for para in paras: - aTags = para.findAll('a') - for a in aTags: - if a.img is None: - a.replaceWith(a.renderContents().decode('cp1252','replace')) - return soup - - - def preprocess_html(self,soup): - #delete empty id attributes--they screw up the TOC for unknown reasons - divtags = soup.findAll('div',attrs={'id':''}) - if divtags: - for div in divtags: - del(div['id']) - - pgall = soup.find('div',attrs={'id':'storyphoto'}) - if pgall is not None: # photo gallery perhaps - if (soup.find('div',attrs={'id':'storycontent'}) is None): - allpics = Tag(soup,'div') - first_img = pgall.find('div','storyimage') - if first_img is not None: - first_img.extract() - tlist = pgall.find('div',attrs={'id':'relatedthumbs'}) - if tlist is not None: - for atag in tlist.findAll('a'): - img = Tag(soup,'img') - srcpre, sep, srcpost = atag.img['src'].partition('?') - img['src'] = srcpre - pdesc = Tag(soup,'p') - pdesc.insert(0,atag.img['alt']) - pdesc['class']='photocaption' - div = Tag(soup,'div') - div.insert(0,pdesc) - div.insert(0,img) - allpics.append(div) - pgall.replaceWith(allpics) - - for pg in soup.findAll('div',attrs={'id':'storyphoto'}): - pg.extract() - return self.strip_anchors(soup) - - - - def parse_index(self): - - articles = {} - ans = [] - - - def handle_article(adiv,key): - h1tag = adiv.h1 - if h1tag is not None: - atag = h1tag.a - if atag is not None: - url = atag['href'] - if atag['href'].startswith('http'): - return - elif atag['href'].startswith('/'): - url = self.url_prefix+atag['href'] - else: - url = self.url_prefix+'/'+atag['href'] - if url in self.url_list: - return - self.url_list.append(url) - title = self.tag_to_string(atag,False) - if 'VIDEO' in title.upper(): - return - if 'GALLERY' in title.upper(): - return - if 'PHOTOS' in title.upper(): - return - dtag = adiv.find('div','content') - description='' - print("URL "+url) - print("TITLE "+title) - if dtag is not None: - stag = dtag.span - if stag is not None: - if stag['class'] != 'timestamp': - description = self.tag_to_string(stag,False) - else: - description = self.tag_to_string(dtag,False) - print("DESCRIPTION: "+description) - if not articles.has_key(key): - articles[key] = [] - articles[key].append(dict(title=title,url=url,date='',description=description,author='',content='')) - - def parse_web_index(key, keyurl): - try: - soup = self.index_to_soup(self.url_prefix+keyurl) - except: - return - ans.append(key) - mainsoup = soup.find('div','bodywrapper') - footer = mainsoup.find(attrs={'id':'footerfeature'}) - if footer is not None: - footer.extract() - print("Section: "+key) - for wdiv in mainsoup.findAll('div',attrs={'id':re.compile('^HorizontalFeatureSlider_1_Story')}): - handle_article(wdiv,key) - wdiv.extract() - for wdiv in mainsoup.findAll(attrs={'id':['featurewidget','textfeature','textlinks_timestamp']}): - for adiv in wdiv.findAll('div','featurecontent'): - handle_article(adiv,key) - - for (k,url) in self.postmedia_index_pages: - parse_web_index(k,url) - ans = [(key, articles[key]) for key in ans if articles.has_key(key)] - return ans - diff --git a/recipes/vancouver_province.recipe b/recipes/vancouver_province.recipe index 0648f29f41..9050c65673 100644 --- a/recipes/vancouver_province.recipe +++ b/recipes/vancouver_province.recipe @@ -1,105 +1,138 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- - __license__ = 'GPL v3' ''' www.canada.com ''' - import re -from calibre.web.feeds.news import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup +from calibre.web.feeds.recipes import BasicNewsRecipe +from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup, Tag class CanWestPaper(BasicNewsRecipe): - # un-comment the following four lines for the Victoria Times Colonist -## title = u'Victoria Times Colonist' -## url_prefix = 'http://www.timescolonist.com' -## description = u'News from Victoria, BC' -## fp_tag = 'CAN_TC' + postmedia_index_pages = [ + (u'Headlines',u'/index.html'), + (u'Ottawa & Area',u'/news/ottawa/index.html'), + (u'Vancouver',u'/news/vancouver/index.html'), + (u'Calgary',u'/news/calgary/index.html'), + (u'Edmonton',u'/news/edmonton/index.html'), + (u'Montreal',u'/news/montreal/index.html'), + (u'Fraser Valley',u'/news/fraser-valley/index.html'), + (u'British Columbia',u'/news/bc/index.html'), + (u'Alberta',u'/news/alberta/index.html'), + (u'Canada',u'/news/canada/index.html'), + (u'National',u'/news/national/index.html'), + (u'Politics',u'/news/politics/index.html'), + (u'Insight',u'/news/insight/index.html'), + (u'Special Reports',u'/news/specialreports/index.html'), + (u'Gangs',u'/news/gangs/index.html'), + (u'Education',u'/news/education/index.html'), + (u'Health',u'/news/health/index.html'), + (u'Environment',u'/news/environment/index.html'), + (u'World',u'/news/world/index.html'), + (u'Police Blotter',u'/news/crime-and-justice/index.html'), + (u'Crime',u'/news/blotter/index.html'), + (u'Around Town',u'/news/topic.html?t=keyword&q=Around+Town'), + (u'Diplomatica',u'/news/diplomatica/index.html'), + (u'Opinion',u'/opinion/index.html'), + (u'Columnists',u'/columnists/index.html'), + (u'Editorials',u'/opinion/editorials/index.html'), + (u'Letters',u'/opinion/letters/index.html'), + (u'Business',u'/business/index.html'), + (u'Sports',u'/sports/index.html'), + (u'Arts',u'/entertainment/index.html'), + (u'Life',u'/life/index.html'), + (u'Technology',u'/technology/index.html'), + (u'Travel',u'/travel/index.html'), + (u'Health',u'/health/index.html') + ] - # un-comment the following four lines for the Vancouver Province + + # un-comment the following six lines for the Vancouver Province title = u'Vancouver Province' url_prefix = 'http://www.theprovince.com' description = u'News from Vancouver, BC' - fp_tag = 'CAN_VP' + std_logo_url = 'http://www.theprovince.com/images/logo_theprovince.jpg' + logo_url = 'vplogo.jpg' + fp_tag = 'CAN_TP' - # un-comment the following four lines for the Vancouver Sun -## title = u'Vancouver Sun' -## url_prefix = 'http://www.vancouversun.com' -## description = u'News from Vancouver, BC' -## fp_tag = 'CAN_VS' + # un-comment the following six lines for the Vancouver Sun + # title = u'Vancouver Sun' + # url_prefix = 'http://www.vancouversun.com' + # description = u'News from Vancouver, BC' + # std_logo_url = 'http://www.vancouversun.com/images/logo_vancouversun.jpg' + # logo_url = 'vslogo.jpg' + # fp_tag = 'CAN_VS' - # un-comment the following four lines for the Edmonton Journal -## title = u'Edmonton Journal' -## url_prefix = 'http://www.edmontonjournal.com' -## description = u'News from Edmonton, AB' -## fp_tag = 'CAN_EJ' - - # un-comment the following four lines for the Calgary Herald + # un-comment the following six lines for the Calgary Herald ## title = u'Calgary Herald' ## url_prefix = 'http://www.calgaryherald.com' ## description = u'News from Calgary, AB' +## std_logo_url = 'http://www.calgaryherald.com/images/logo_calgaryherald.jpg' +## logo_url = 'chlogo.jpg' ## fp_tag = 'CAN_CH' - # un-comment the following four lines for the Regina Leader-Post -## title = u'Regina Leader-Post' -## url_prefix = 'http://www.leaderpost.com' -## description = u'News from Regina, SK' -## fp_tag = '' + # un-comment the following six lines for the Edmonton Journal +## title = u'Edmonton Journal' +## url_prefix = 'http://www.edmontonjournal.com' +## description = u'News from Edmonton, AB' +## std_logo_url = 'http://www.edmontonjournal.com/images/logo_edmontonjournal.jpg' +## logo_url = 'ejlogo.jpg' +## fp_tag = 'CAN_EJ' - # un-comment the following four lines for the Saskatoon Star-Phoenix -## title = u'Saskatoon Star-Phoenix' -## url_prefix = 'http://www.thestarphoenix.com' -## description = u'News from Saskatoon, SK' -## fp_tag = '' - - # un-comment the following four lines for the Windsor Star -## title = u'Windsor Star' -## url_prefix = 'http://www.windsorstar.com' -## description = u'News from Windsor, ON' -## fp_tag = 'CAN_' - - # un-comment the following four lines for the Ottawa Citizen + # un-comment the following six lines for the Ottawa Citizen ## title = u'Ottawa Citizen' ## url_prefix = 'http://www.ottawacitizen.com' ## description = u'News from Ottawa, ON' +## std_logo_url = 'http://www.ottawacitizen.com/images/logo_ottawacitizen.jpg' +## logo_url = 'oclogo.jpg' ## fp_tag = 'CAN_OC' - # un-comment the following four lines for the Montreal Gazette + # un-comment the following six lines for the Montreal Gazette ## title = u'Montreal Gazette' ## url_prefix = 'http://www.montrealgazette.com' ## description = u'News from Montreal, QC' +## std_logo_url = 'http://www.montrealgazette.com/images/logo_montrealgazette.jpg' +## logo_url = 'mglogo.jpg' ## fp_tag = 'CAN_MG' + Kindle_Fire=False + masthead_url = std_logo_url + url_list = [] language = 'en_CA' __author__ = 'Nick Redding' no_stylesheets = True - timefmt = ' [%b %d]' + timefmt = ' [%b %d]' + encoding = 'utf-8' 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; } + #storyheader h2 { font-size: small; 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'}), + #photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } + .photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } + #photocredit { font-size: xx-small; font-weight: normal; }''' + + keep_only_tags = [dict(name='div', attrs={'id':re.compile('story')})] + + remove_tags = [{'class':'comments'},{'class':'comment-intro'},{'class':'storytab'}, + dict(name='div', attrs={'class':'section_title'}),dict(name='div', attrs={'class':'sharebar'}),dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), + dict(name='h2', attrs={'id':'photocredit'}), 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='div', attrs={'id':'soundoff'}), + dict(name='div', attrs={'id':re.compile('flyer')}), dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})] + def get_cover_url(self): from datetime import timedelta, date - if self.fp_tag=='': - return None cover = 'http://webmedia.newseum.org/newseum-multimedia/dfp/jpg'+str(date.today().day)+'/lg/'+self.fp_tag+'.jpg' br = BasicNewsRecipe.get_browser(self) daysback=1 @@ -120,6 +153,18 @@ class CanWestPaper(BasicNewsRecipe): cover = None return cover + def prepare_masthead_image(self, path_to_image, out_path): + if self.Kindle_Fire: + from calibre.utils.magick import Image, create_canvas + img = Image() + img.open(path_to_image) + width, height = img.size + img2 = create_canvas(width, height) + img2.compose(img) + img2.save(out_path) + else: + BasicNewsRecipe.prepare_masthead_image(self, path_to_image, out_path) + def fixChars(self,string): # Replace lsquo (\x91) fixed = re.sub("\x91","‘",string) @@ -166,55 +211,110 @@ class CanWestPaper(BasicNewsRecipe): a.replaceWith(a.renderContents().decode('cp1252','replace')) return soup - def preprocess_html(self, soup): + + def preprocess_html(self,soup): + #delete empty id attributes--they screw up the TOC for unknown reasons + divtags = soup.findAll('div',attrs={'id':''}) + if divtags: + for div in divtags: + del(div['id']) + + pgall = soup.find('div',attrs={'id':'storyphoto'}) + if pgall is not None: # photo gallery perhaps + if (soup.find('div',attrs={'id':'storycontent'}) is None): + allpics = Tag(soup,'div') + first_img = pgall.find('div','storyimage') + if first_img is not None: + first_img.extract() + tlist = pgall.find('div',attrs={'id':'relatedthumbs'}) + if tlist is not None: + for atag in tlist.findAll('a'): + img = Tag(soup,'img') + srcpre, sep, srcpost = atag.img['src'].partition('?') + img['src'] = srcpre + pdesc = Tag(soup,'p') + pdesc.insert(0,atag.img['alt']) + pdesc['class']='photocaption' + div = Tag(soup,'div') + div.insert(0,pdesc) + div.insert(0,img) + allpics.append(div) + pgall.replaceWith(allpics) + + for pg in soup.findAll('div',attrs={'id':'storyphoto'}): + pg.extract() return self.strip_anchors(soup) def parse_index(self): - soup = self.index_to_soup(self.url_prefix+'/news/todays-paper/index.html') articles = {} - key = 'News' - ans = ['News'] + ans = [] - # 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='')) + def handle_article(adiv,key): + if adiv.name=='h1' or adiv.name=='h3': + h1tag = adiv + else: + h1tag = adiv.h1 + if h1tag is None: + h1tag = adiv.h3 + if h1tag is not None: + atag = h1tag.a + if atag is not None: + url = atag['href'] + if url.startswith('/'): + url = self.url_prefix+url + if not url.startswith(self.url_prefix): + print("Rejected "+url) + return + if url in self.url_list: + print("Rejected dup "+url) + return + self.url_list.append(url) + title = self.tag_to_string(atag,False) + if 'VIDEO' in title.upper(): + return + if 'GALLERY' in title.upper(): + return + if 'PHOTOS' in title.upper(): + return + dtag = adiv.find('div','content') + description='' + print("URL "+url) + print("TITLE "+title) + if dtag is not None: + stag = dtag.span + if stag is not None: + if stag['class'] != 'timestamp': + description = self.tag_to_string(stag,False) + else: + description = self.tag_to_string(dtag,False) + print("DESCRIPTION: "+description) + if not articles.has_key(key): + articles[key] = [] + articles[key].append(dict(title=title,url=url,date='',description=description,author='',content='')) + + def parse_web_index(key, keyurl): + print("Section: "+key+': '+self.url_prefix+keyurl) + try: + soup = self.index_to_soup(self.url_prefix+keyurl) + except: + print("Section: "+key+' NOT FOUND'); + return + ans.append(key) + mainsoup = soup.find('div','bodywrapper') + footer = mainsoup.find(attrs={'id':'footerfeature'}) + if footer is not None: + footer.extract() + for wdiv in mainsoup.findAll(attrs={'class':['genericfeature']}): + wdiv.extract() + for wdiv in mainsoup.findAll(attrs={'class':['headline','featurecontent']}): + handle_article(wdiv,key) + + for (k,url) in self.postmedia_index_pages: + parse_web_index(k,url) ans = [(key, articles[key]) for key in ans if articles.has_key(key)] return ans + diff --git a/recipes/vancouver_sun.recipe b/recipes/vancouver_sun.recipe index faea272558..025217c03c 100644 --- a/recipes/vancouver_sun.recipe +++ b/recipes/vancouver_sun.recipe @@ -117,15 +117,17 @@ class CanWestPaper(BasicNewsRecipe): .photocaption { font-size: xx-small; font-style: italic; font-weight: normal; } #photocredit { font-size: xx-small; font-weight: normal; }''' - keep_only_tags = [dict(name='div', attrs={'id':'storyheader'}),dict(name='div', attrs={'id':'storycontent'}),dict(name='div', attrs={'id':'storyphoto'})] + keep_only_tags = [dict(name='div', attrs={'id':re.compile('story')})] - remove_tags = [{'class':'comments'}, - dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), + remove_tags = [{'class':'comments'},{'class':'comment-intro'},{'class':'storytab'}, + dict(name='div', attrs={'class':'section_title'}),dict(name='div', attrs={'class':'sharebar'}),dict(name='div', attrs={'class':'navbar'}),dict(name='div', attrs={'class':'morelinks'}), dict(name='h2', attrs={'id':'photocredit'}), 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='div', attrs={'id':'soundoff'}), + dict(name='div', attrs={'id':re.compile('flyer')}), dict(name='li', attrs={'class':'print'}),dict(name='li', attrs={'class':'share'}),dict(name='ul', attrs={'class':'bullet'})] @@ -252,18 +254,23 @@ class CanWestPaper(BasicNewsRecipe): def handle_article(adiv,key): - h1tag = adiv.h1 + if adiv.name=='h1' or adiv.name=='h3': + h1tag = adiv + else: + h1tag = adiv.h1 + if h1tag is None: + h1tag = adiv.h3 if h1tag is not None: atag = h1tag.a if atag is not None: url = atag['href'] - if atag['href'].startswith('http'): + if url.startswith('/'): + url = self.url_prefix+url + if not url.startswith(self.url_prefix): + print("Rejected "+url) return - elif atag['href'].startswith('/'): - url = self.url_prefix+atag['href'] - else: - url = self.url_prefix+'/'+atag['href'] if url in self.url_list: + print("Rejected dup "+url) return self.url_list.append(url) title = self.tag_to_string(atag,False) @@ -290,22 +297,21 @@ class CanWestPaper(BasicNewsRecipe): articles[key].append(dict(title=title,url=url,date='',description=description,author='',content='')) def parse_web_index(key, keyurl): + print("Section: "+key+': '+self.url_prefix+keyurl) try: soup = self.index_to_soup(self.url_prefix+keyurl) except: + print("Section: "+key+' NOT FOUND'); return ans.append(key) mainsoup = soup.find('div','bodywrapper') footer = mainsoup.find(attrs={'id':'footerfeature'}) if footer is not None: footer.extract() - print("Section: "+key) - for wdiv in mainsoup.findAll('div',attrs={'id':re.compile('^HorizontalFeatureSlider_1_Story')}): - handle_article(wdiv,key) - wdiv.extract() - for wdiv in mainsoup.findAll(attrs={'id':['featurewidget','textfeature','textlinks_timestamp']}): - for adiv in wdiv.findAll('div','featurecontent'): - handle_article(adiv,key) + for wdiv in mainsoup.findAll(attrs={'class':['genericfeature']}): + wdiv.extract() + for wdiv in mainsoup.findAll(attrs={'class':['headline','featurecontent']}): + handle_article(wdiv,key) for (k,url) in self.postmedia_index_pages: parse_web_index(k,url)