mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Fix Slate
This commit is contained in:
Kovid Goyal
parent
5c14e6ea3b
commit
a7beccd294
@ -9,285 +9,79 @@ calibre recipe for slate.com
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.recipes import BasicNewsRecipe
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup, NavigableString, CData, Comment, Tag
|
||||
|
||||
class Slate(BasicNewsRecipe):
|
||||
# Method variables for customizing downloads
|
||||
description = 'A general-interest publication offering analysis and commentary about politics, news and culture.'
|
||||
__author__ = 'GRiker, Sujata Raman and Nick Redding'
|
||||
max_articles_per_feed = 100
|
||||
oldest_article = 14
|
||||
recursions = 0
|
||||
delay = 0
|
||||
simultaneous_downloads = 5
|
||||
timeout = 120.0
|
||||
__author__ = 'Kovid Goyal'
|
||||
timefmt = ''
|
||||
feeds = None
|
||||
no_stylesheets = True
|
||||
encoding = None
|
||||
language = 'en'
|
||||
title = 'Slate'
|
||||
INDEX = 'http://slate.com'
|
||||
encoding = 'utf-8'
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'<!--.*?-->', re.DOTALL), lambda x: ''),
|
||||
(re.compile(r'^.*?<html', re.DOTALL), lambda x:'<html'),
|
||||
(re.compile(r'<meta[^>]+?/>', re.DOTALL), lambda x:''),
|
||||
]
|
||||
remove_tags = [
|
||||
{'name':['link', 'script']},
|
||||
{'class':['share-box-flank', 'sl-crumbs', 'sl-tbar',
|
||||
'sl-chunky-tbar']},
|
||||
]
|
||||
remove_tags_after = [{'class':'sl-art-creds-cntr'}]
|
||||
keep_only_tags = {'class':'sl-body-wrapper'}
|
||||
remove_attributes = ['style']
|
||||
|
||||
slate_complete = True
|
||||
if slate_complete:
|
||||
title = 'Slate (complete)'
|
||||
else:
|
||||
title = 'Slate (weekly)'
|
||||
def print_version(self, url):
|
||||
return url.replace('.html', '.single.html')
|
||||
|
||||
# Method variables for customizing feed parsing
|
||||
summary_length = 250
|
||||
use_embedded_content = None
|
||||
|
||||
# Method variables for pre/post processing of HTML
|
||||
preprocess_regexps = [ (re.compile(r'<p><em>Disclosure: <strong>Slate</strong> is owned by the Washington Post.*</p>',
|
||||
re.DOTALL|re.IGNORECASE),
|
||||
lambda match: ''),
|
||||
(re.compile(r'<p><strong><em>Join the discussion about this story on.*</p>',
|
||||
re.DOTALL|re.IGNORECASE),
|
||||
lambda match: '') ]
|
||||
|
||||
match_regexps = []
|
||||
|
||||
# The second entry is for 'Big Money', which comes from a different site, uses different markup
|
||||
keep_only_tags = [dict(attrs={ 'id':['article_top', 'article_body']}),
|
||||
dict(attrs={ 'id':['content']}) ]
|
||||
|
||||
# The second entry is for 'Big Money', which comes from a different site, uses different markup
|
||||
remove_tags = [dict(attrs={ 'id':['toolbox','recommend_tab','insider_ad_wrapper',
|
||||
'article_bottom_tools_cntr','fray_article_discussion','fray_article_links','bottom_sponsored_links','author_bio',
|
||||
'bizbox_links_bottom','ris_links_wrapper','BOXXLE',
|
||||
'comments_button','add_comments_button','comments-to-fray','marriott_ad',
|
||||
'article_bottom_tools','recommend_tab2','fbog_article_bottom_cntr']}),
|
||||
dict(attrs={ 'id':['content-top','service-links-bottom','hed']}) ]
|
||||
|
||||
excludedDescriptionKeywords = ['Slate V','Twitter feed','podcast']
|
||||
excludedTitleKeywords = ['Gabfest','Slate V','on Twitter']
|
||||
excludedAuthorKeywords = []
|
||||
excludedContentKeywords = ['http://twitter.com/Slate']
|
||||
|
||||
extra_css = '''
|
||||
.h1_subhead{font-family:Arial; font-size:small; }
|
||||
h1{font-family:Verdana; font-size:large; }
|
||||
.byline {font-family:Georgia; margin-bottom: 0px; }
|
||||
.dateline {font-family:Arial; font-size: smaller; height: 0pt;}
|
||||
.imagewrapper {font-family:Verdana;font-size:x-small; }
|
||||
.source {font-family:Verdana; font-size:x-small;}
|
||||
.credit {font-family:Verdana; font-size: smaller;}
|
||||
#article_body {font-family:Verdana; }
|
||||
#content {font-family:Arial; }
|
||||
.caption{font-family:Verdana;font-style:italic; font-size:x-small;}
|
||||
h3{font-family:Arial; font-size:small}
|
||||
'''
|
||||
|
||||
# Local variables to extend class
|
||||
baseURL = 'http://slate.com'
|
||||
section_dates = []
|
||||
|
||||
# class extension methods
|
||||
def tag_to_strings(self, tag):
|
||||
if not tag:
|
||||
return ''
|
||||
if isinstance(tag, basestring):
|
||||
return tag
|
||||
strings = []
|
||||
for item in tag.contents:
|
||||
if isinstance(item, (NavigableString, CData)):
|
||||
strings.append(item.string)
|
||||
elif isinstance(item, Tag):
|
||||
res = self.tag_to_string(item,use_alt=False)
|
||||
if res:
|
||||
strings.append(res)
|
||||
return strings
|
||||
|
||||
def extract_named_sections(self):
|
||||
soup = self.index_to_soup( self.baseURL )
|
||||
soup_nav_bar = soup.find(True, attrs={'id':'nav'})
|
||||
briefing_nav = soup.find('li')
|
||||
briefing_url = briefing_nav.a['href']
|
||||
for section_nav in soup_nav_bar.findAll('li'):
|
||||
section_name = self.tag_to_string(section_nav,use_alt=False)
|
||||
self.section_dates.append(section_name)
|
||||
|
||||
soup = self.index_to_soup(briefing_url)
|
||||
|
||||
self.log("Briefing url = %s " % briefing_url)
|
||||
section_lists = soup.findAll('ul','view_links_list')
|
||||
|
||||
sections = []
|
||||
for section in section_lists :
|
||||
sections.append(section)
|
||||
return sections
|
||||
|
||||
|
||||
def extract_dated_sections(self):
|
||||
soup = self.index_to_soup( self.baseURL )
|
||||
soup_top_stories = soup.find(True, attrs={'id':'tap3_cntr'})
|
||||
if soup_top_stories:
|
||||
self.section_dates.append("Top Stories")
|
||||
self.log("SELECTION TOP STORIES %s" % "Top Stories")
|
||||
|
||||
soup = soup.find(True, attrs={'id':'toc_links_container'})
|
||||
|
||||
todays_section = soup.find(True, attrs={'class':'todaydateline'})
|
||||
self.section_dates.append(self.tag_to_string(todays_section,use_alt=False))
|
||||
self.log("SELECTION DATE %s" % self.tag_to_string(todays_section,use_alt=False))
|
||||
|
||||
older_section_dates = soup.findAll(True, attrs={'class':'maindateline'})
|
||||
for older_section in older_section_dates :
|
||||
self.section_dates.append(self.tag_to_string(older_section,use_alt=False))
|
||||
self.log("SELECTION DATE %s" % self.tag_to_string(older_section,use_alt=False))
|
||||
|
||||
if soup_top_stories:
|
||||
headline_stories = soup_top_stories
|
||||
self.log("HAVE top_stories")
|
||||
else:
|
||||
headline_stories = None
|
||||
self.log("NO top_stories")
|
||||
section_lists = soup.findAll('ul')
|
||||
# Prepend the headlines to the first section
|
||||
if headline_stories:
|
||||
section_lists.insert(0,headline_stories)
|
||||
|
||||
sections = []
|
||||
for section in section_lists :
|
||||
sections.append(section)
|
||||
return sections
|
||||
|
||||
|
||||
def extract_section_articles(self, sections_html) :
|
||||
# Find the containers with section content
|
||||
sections = sections_html
|
||||
|
||||
articles = {}
|
||||
key = None
|
||||
def parse_index(self) :
|
||||
ans = []
|
||||
|
||||
for (i,section) in enumerate(sections) :
|
||||
|
||||
# Get the section name
|
||||
if section.has_key('id') :
|
||||
self.log("PROCESSING SECTION id = %s" % section['id'])
|
||||
key = self.section_dates[i]
|
||||
if key.startswith("Pod"):
|
||||
continue
|
||||
if key.startswith("Blog"):
|
||||
continue
|
||||
articles[key] = []
|
||||
ans.append(key)
|
||||
elif self.slate_complete:
|
||||
key = self.section_dates[i]
|
||||
if key.startswith("Pod"):
|
||||
continue
|
||||
if key.startswith("Blog"):
|
||||
continue
|
||||
self.log("PROCESSING SECTION name = %s" % key)
|
||||
articles[key] = []
|
||||
ans.append(key)
|
||||
else :
|
||||
self.log("SECTION %d HAS NO id" % i);
|
||||
continue
|
||||
|
||||
# Get the section article_list
|
||||
article_list = section.findAll('li')
|
||||
|
||||
# Extract the article attributes
|
||||
for article in article_list :
|
||||
bylines = self.tag_to_strings(article)
|
||||
url = article.a['href']
|
||||
title = bylines[0]
|
||||
full_title = self.tag_to_string(article,use_alt=False)
|
||||
#self.log("ARTICLE TITLE%s" % title)
|
||||
#self.log("ARTICLE FULL_TITLE%s" % full_title)
|
||||
#self.log("URL %s" % url)
|
||||
author = None
|
||||
description = None
|
||||
pubdate = None
|
||||
|
||||
if len(bylines) == 2 and self.tag_to_string(article).find("Today's Papers") > 0 :
|
||||
description = "A summary of what's in the major U.S. newspapers."
|
||||
|
||||
if len(bylines) == 3 :
|
||||
author = bylines[2].strip()
|
||||
author = re.sub('[\r][\n][\t][\t\t]','', author)
|
||||
author = re.sub(',','', author)
|
||||
if bylines[1] is not None :
|
||||
description = bylines[1]
|
||||
full_byline = self.tag_to_string(article)
|
||||
if full_byline.find('major U.S. newspapers') > 0 :
|
||||
description = "A summary of what's in the major U.S. newspapers."
|
||||
|
||||
if len(bylines) > 3 and author is not None:
|
||||
author += " | "
|
||||
for (i,substring) in enumerate(bylines[3:]) :
|
||||
#print "substring: %s" % substring.encode('cp1252')
|
||||
author += substring.strip()
|
||||
if i < len(bylines[3:]) :
|
||||
author += " | "
|
||||
|
||||
# Skip articles whose descriptions contain excluded keywords
|
||||
if description is not None and len(self.excludedDescriptionKeywords):
|
||||
excluded = re.compile('|'.join(self.excludedDescriptionKeywords))
|
||||
found_excluded = excluded.search(description)
|
||||
if found_excluded :
|
||||
self.log(" >>> skipping %s (description keyword exclusion: %s) <<<\n" % (title, found_excluded.group(0)))
|
||||
continue
|
||||
|
||||
# Skip articles whose title contain excluded keywords
|
||||
if full_title is not None and len(self.excludedTitleKeywords):
|
||||
excluded = re.compile('|'.join(self.excludedTitleKeywords))
|
||||
#self.log("evaluating full_title: %s" % full_title)
|
||||
found_excluded = excluded.search(full_title)
|
||||
if found_excluded :
|
||||
self.log(" >>> skipping %s (title keyword exclusion: %s) <<<\n" % (title, found_excluded.group(0)))
|
||||
continue
|
||||
|
||||
# Skip articles whose author contain excluded keywords
|
||||
if author is not None and len(self.excludedAuthorKeywords):
|
||||
excluded = re.compile('|'.join(self.excludedAuthorKeywords))
|
||||
found_excluded = excluded.search(author)
|
||||
if found_excluded :
|
||||
self.log(" >>> skipping %s (author keyword exclusion: %s) <<<\n" % (title, found_excluded.group(0)))
|
||||
continue
|
||||
|
||||
skip_this_article = False
|
||||
# Check to make sure we're not adding a duplicate
|
||||
for article in articles[key] :
|
||||
if article['url'] == url :
|
||||
skip_this_article = True
|
||||
self.log("SKIPPING DUP %s" % url)
|
||||
break
|
||||
|
||||
if skip_this_article :
|
||||
continue
|
||||
|
||||
# Build the dictionary entry for this article
|
||||
feed = key
|
||||
if not articles.has_key(feed) :
|
||||
articles[feed] = []
|
||||
articles[feed].append(dict(title=title, url=url, date=pubdate, description=description,
|
||||
author=author, content=''))
|
||||
#self.log("KEY %s" % feed)
|
||||
#self.log("APPENDED %s" % url)
|
||||
# Promote 'newspapers' to top
|
||||
for (i,article) in enumerate(articles[feed]) :
|
||||
if article['description'] is not None :
|
||||
if article['description'].find('newspapers') > 0 :
|
||||
articles[feed].insert(0,articles[feed].pop(i))
|
||||
|
||||
|
||||
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
|
||||
for sectitle, url in (
|
||||
('News & Politics', '/articles/news_and_politics.html'),
|
||||
('Technology', '/articles/technology.html'),
|
||||
('Business', '/articles/business.html'),
|
||||
('Arts', '/articles/arts.html'),
|
||||
('Life', '/articles/life.html'),
|
||||
('Health & Science', '/articles/health_and_science.html'),
|
||||
('Sports', '/articles/sports.html'),
|
||||
('Double X', '/articles/double_x.html'),
|
||||
):
|
||||
url = self.INDEX + url
|
||||
self.log('Found section:', sectitle)
|
||||
articles = self.slate_section_articles(self.index_to_soup(url))
|
||||
if articles:
|
||||
ans.append((sectitle, articles))
|
||||
return ans
|
||||
|
||||
def print_version(self, url) :
|
||||
return url + 'pagenum/all/'
|
||||
|
||||
# Class methods
|
||||
def parse_index(self) :
|
||||
if self.slate_complete:
|
||||
sections = self.extract_named_sections()
|
||||
else:
|
||||
sections = self.extract_dated_sections()
|
||||
section_list = self.extract_section_articles(sections)
|
||||
return section_list
|
||||
def slate_section_articles(self, soup):
|
||||
cont = soup.find('div', id='most_read')
|
||||
seen = set()
|
||||
ans = []
|
||||
for h4 in cont.findAll('h4'):
|
||||
a = h4.find('a', href=True)
|
||||
if a is None: continue
|
||||
url = a['href']
|
||||
if url.startswith('/'):
|
||||
url = self.INDEX + url
|
||||
if url in seen: continue
|
||||
seen.add(url)
|
||||
title = self.tag_to_string(a)
|
||||
parent = h4.parent
|
||||
h3 = parent.find('h3')
|
||||
desc = ''
|
||||
if h3 is not None:
|
||||
desc = self.tag_to_string(h3)
|
||||
a = parent.find('a', rel='author')
|
||||
if a is not None:
|
||||
a = self.tag_to_string(a)
|
||||
art = {'title':title, 'description':desc, 'date':'', 'url':url}
|
||||
if a:
|
||||
art['author'] = a
|
||||
self.log('\tFound article:', title, ' by ', a)
|
||||
ans.append(art)
|
||||
return ans
|
||||
|
||||
def get_masthead_url(self):
|
||||
masthead = 'http://img.slate.com/images/redesign2008/slate_logo.gif'
|
||||
@ -299,153 +93,4 @@ class Slate(BasicNewsRecipe):
|
||||
masthead = None
|
||||
return masthead
|
||||
|
||||
def stripAnchors(self,soup):
|
||||
body = soup.find('div',attrs={'id':['article_body','content']})
|
||||
if body is not None:
|
||||
paras = body.findAll('p')
|
||||
if paras is not None:
|
||||
for para in paras:
|
||||
aTags = para.findAll('a')
|
||||
if aTags is not None:
|
||||
for a in aTags:
|
||||
if a.img is None:
|
||||
#print repr(a.renderContents())
|
||||
a.replaceWith(a.renderContents().decode('utf-8','replace'))
|
||||
return soup
|
||||
|
||||
def preprocess_html(self, soup) :
|
||||
|
||||
# Remove 'grayPlus4.png' images
|
||||
imgs = soup.findAll('img')
|
||||
if imgs is not None:
|
||||
for img in imgs:
|
||||
if re.search("grayPlus4.png",str(img)):
|
||||
img.extract()
|
||||
|
||||
# Delete article based upon content keywords
|
||||
if len(self.excludedDescriptionKeywords):
|
||||
excluded = re.compile('|'.join(self.excludedContentKeywords))
|
||||
found_excluded = excluded.search(str(soup))
|
||||
if found_excluded :
|
||||
print "No allowed content found, removing article"
|
||||
raise Exception('Rejected article')
|
||||
|
||||
# Articles from www.thebigmoney.com use different tagging for byline, dateline and body
|
||||
head = soup.find('head')
|
||||
if head.link is not None and re.search('www\.thebigmoney\.com', str(head)):
|
||||
byline = soup.find('div',attrs={'id':'byline'})
|
||||
if byline is not None:
|
||||
byline['class'] = byline['id']
|
||||
|
||||
dateline = soup.find('div',attrs={'id':'dateline'})
|
||||
if dateline is not None:
|
||||
dateline['class'] = dateline['id']
|
||||
|
||||
body = soup.find('div',attrs={'id':'content'})
|
||||
if body is not None:
|
||||
body['class'] = 'article_body'
|
||||
|
||||
# Synthesize a department kicker
|
||||
h3Tag = Tag(soup,'h3')
|
||||
emTag = Tag(soup,'em')
|
||||
emTag.insert(0,NavigableString("the big money: Today's business press"))
|
||||
h3Tag.insert(0,emTag)
|
||||
soup.body.insert(0,h3Tag)
|
||||
|
||||
# Strip anchors from HTML
|
||||
return self.stripAnchors(soup)
|
||||
|
||||
def postprocess_html(self, soup, first_fetch) :
|
||||
|
||||
# Fix up dept_kicker as <h3><em>
|
||||
dept_kicker = soup.find('div', attrs={'class':'department_kicker'})
|
||||
if dept_kicker is not None :
|
||||
kicker_strings = self.tag_to_strings(dept_kicker)
|
||||
kicker = ''.join(kicker_strings[2:])
|
||||
kicker = re.sub('\.','',kicker)
|
||||
h3Tag = Tag(soup, "h3")
|
||||
emTag = Tag(soup, "em")
|
||||
emTag.insert(0,NavigableString(kicker))
|
||||
h3Tag.insert(0, emTag)
|
||||
dept_kicker.replaceWith(h3Tag)
|
||||
else:
|
||||
self.log("No kicker--return null")
|
||||
return None
|
||||
|
||||
# Fix up the concatenated byline and dateline
|
||||
byline = soup.find(True,attrs={'class':'byline'})
|
||||
if byline is not None :
|
||||
bylineTag = Tag(soup,'div')
|
||||
bylineTag['class'] = 'byline'
|
||||
#bylineTag['height'] = '0em'
|
||||
bylineTag.insert(0,self.tag_to_string(byline))
|
||||
byline.replaceWith(bylineTag)
|
||||
|
||||
dateline = soup.find(True, attrs={'class':'dateline'})
|
||||
if dateline is not None :
|
||||
datelineTag = Tag(soup, 'div')
|
||||
datelineTag['class'] = 'dateline'
|
||||
#datelineTag['margin-top'] = '0em'
|
||||
datelineTag.insert(0,self.tag_to_string(dateline))
|
||||
dateline.replaceWith(datelineTag)
|
||||
|
||||
# Change captions to italic, add <hr>
|
||||
for caption in soup.findAll(True, {'class':'caption'}) :
|
||||
if caption is not None:
|
||||
emTag = Tag(soup, "em")
|
||||
emTag.insert(0, '<br />' + self.tag_to_string(caption))
|
||||
hrTag = Tag(soup, 'hr')
|
||||
emTag.insert(1, hrTag)
|
||||
caption.replaceWith(emTag)
|
||||
|
||||
# Fix photos
|
||||
for photo in soup.findAll('span',attrs={'class':'imagewrapper'}):
|
||||
if photo.a is not None and photo.a.img is not None:
|
||||
divTag = Tag(soup,'div')
|
||||
divTag['class'] ='imagewrapper'
|
||||
divTag.insert(0,photo.a.img)
|
||||
photo.replaceWith(divTag)
|
||||
|
||||
return soup
|
||||
|
||||
def postprocess_book(self, oeb, opts, log) :
|
||||
|
||||
def extract_byline(href) :
|
||||
soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
|
||||
byline = soup.find(True,attrs={'class':'byline'})
|
||||
if byline is not None:
|
||||
return self.tag_to_string(byline,use_alt=False)
|
||||
else :
|
||||
return None
|
||||
|
||||
def extract_description(href) :
|
||||
soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
|
||||
paragraphs = soup.findAll('p')
|
||||
for p in paragraphs :
|
||||
if self.tag_to_string(p,use_alt=False).startswith('By ') or \
|
||||
self.tag_to_string(p,use_alt=False).startswith('Posted '):
|
||||
continue
|
||||
comment = p.find(text=lambda text:isinstance(text, Comment))
|
||||
if comment is not None:
|
||||
continue
|
||||
else:
|
||||
return self.tag_to_string(p,use_alt=False)[:self.summary_length] + '...'
|
||||
|
||||
return None
|
||||
|
||||
# Method entry point here
|
||||
# Single section toc looks different than multi-section tocs
|
||||
if oeb.toc.depth() == 2 :
|
||||
for article in oeb.toc :
|
||||
if article.author is None :
|
||||
article.author = extract_byline(article.href)
|
||||
if article.description is None :
|
||||
article.description = extract_description(article.href)
|
||||
elif oeb.toc.depth() == 3 :
|
||||
for section in oeb.toc :
|
||||
for article in section :
|
||||
if article.author is None :
|
||||
article.author = extract_byline(article.href)
|
||||
if article.description is None :
|
||||
article.description = extract_description(article.href)
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user