mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-23 06:53:02 -05:00
486 lines
20 KiB
Python
486 lines
20 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
nytimes.com
|
|
V5 - One picture per article, moved to top:
|
|
Headline
|
|
Image
|
|
Byline
|
|
Story
|
|
'''
|
|
import re, string, time
|
|
from calibre import strftime
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup, NavigableString, Tag
|
|
|
|
class NYTimes(BasicNewsRecipe):
|
|
|
|
title = 'The New York Times'
|
|
__author__ = 'GRiker'
|
|
language = 'en'
|
|
|
|
description = 'Daily news from the New York Times (subscription version)'
|
|
allSectionKeywords = ['The Front Page', 'International','National','Obituaries','Editorials',
|
|
'New York','Business Day','Science Times','Sports','Dining','Arts',
|
|
'Home','Styles','Sunday Business','Week In Review','Travel','Magazine',
|
|
'Book Review','Weddings','Real Estate','Automobiles',"T Men's Fashion",
|
|
"T Women's Fashion"]
|
|
|
|
# List of sections to exclude
|
|
# To add a section, copy the section name from the allSectionKeywords list above
|
|
# For example, to exclude 'Dining' and 'Weddings':
|
|
#excludeSectionKeywords = ['Dining','Weddings']
|
|
excludeSectionKeywords = []
|
|
|
|
# List of sections to include (test and debug only)
|
|
# By default, any sections in today's paper that are not listed in excludeSectionKeywords
|
|
# are downloaded. fetch_only specifies that only certain sections are to be downloaded.
|
|
# This should only be used for testing and debugging.
|
|
# For example, to download only 'The Front Page' section:
|
|
# fetch_only = set(['The Front Page'])
|
|
fetch_only = set([])
|
|
if fetch_only:
|
|
excludeSectionKeywords = list(set(allSectionKeywords) ^ fetch_only)
|
|
|
|
# one_picture_per_article specifies that calibre should only use the first image
|
|
# from an article (if one exists). If one_picture_per_article = True, the image
|
|
# will be moved to a location between the headline and the byline.
|
|
# If one_picture_per_article = False, all images from the article will be included
|
|
# and shown in their original location.
|
|
one_picture_per_article = True
|
|
|
|
timefmt = ''
|
|
needs_subscription = True
|
|
remove_tags_before = dict(id='article')
|
|
remove_tags_after = dict(id='article')
|
|
remove_tags = [dict(attrs={'class':[
|
|
'articleFooter',
|
|
'articleTools',
|
|
'columnGroup doubleRule',
|
|
'columnGroup singleRule',
|
|
'columnGroup last',
|
|
'columnGroup last',
|
|
'doubleRule',
|
|
'dottedLine',
|
|
'entry-meta',
|
|
'icon enlargeThis',
|
|
'leftNavTabs',
|
|
'module box nav',
|
|
'nextArticleLink',
|
|
'nextArticleLink clearfix',
|
|
'post-tools',
|
|
'relatedSearchesModule',
|
|
'side_tool',
|
|
'singleAd',
|
|
'subNavigation tabContent active',
|
|
'subNavigation tabContent active clearfix',
|
|
]}),
|
|
dict(id=[
|
|
'adxLeaderboard',
|
|
'archive',
|
|
'articleExtras',
|
|
'articleInline',
|
|
'blog_sidebar',
|
|
'businessSearchBar',
|
|
'cCol',
|
|
'entertainmentSearchBar',
|
|
'footer',
|
|
'header',
|
|
'header_search',
|
|
'login',
|
|
'masthead',
|
|
'masthead-nav',
|
|
'memberTools',
|
|
'navigation',
|
|
'portfolioInline',
|
|
'relatedArticles',
|
|
'side_search',
|
|
'side_index',
|
|
'side_tool',
|
|
'toolsRight',
|
|
]),
|
|
dict(name=['script', 'noscript', 'style'])]
|
|
masthead_url = 'http://graphics8.nytimes.com/images/misc/nytlogo379x64.gif'
|
|
no_stylesheets = True
|
|
extra_css = '.headline {text-align: left;}\n \
|
|
.byline {font-family: monospace; \
|
|
text-align: left; \
|
|
margin-top: 0px; \
|
|
margin-bottom: 0px;}\n \
|
|
.dateline {font-size: small; \
|
|
margin-top: 0px; \
|
|
margin-bottom: 0px;}\n \
|
|
.timestamp {font-size: small; \
|
|
margin-top: 0px; \
|
|
margin-bottom: 0px;}\n \
|
|
.source {text-align: left;}\n \
|
|
.image {text-align: center;}\n \
|
|
.credit {text-align: right; \
|
|
font-size: small; \
|
|
margin-top: 0px; \
|
|
margin-bottom: 0px;}\n \
|
|
.articleBody {text-align: left;}\n \
|
|
.authorId {text-align: left; \
|
|
font-style: italic;}\n '
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
if self.username is not None and self.password is not None:
|
|
try:
|
|
br.open('http://www.nytimes.com/auth/login')
|
|
br.select_form(name='login')
|
|
br['USERID'] = self.username
|
|
br['PASSWORD'] = self.password
|
|
raw = br.submit().read()
|
|
if 'Sorry, we could not find the combination you entered. Please try again.' in raw:
|
|
raise Exception('Your username and password are incorrect')
|
|
#open('/t/log.html', 'wb').write(raw)
|
|
except:
|
|
self.log("\nFailed to login")
|
|
|
|
return br
|
|
|
|
def get_cover_url(self):
|
|
cover = None
|
|
st = time.localtime()
|
|
year = str(st.tm_year)
|
|
month = "%.2d" % st.tm_mon
|
|
day = "%.2d" % st.tm_mday
|
|
cover = 'http://graphics8.nytimes.com/images/' + year + '/' + month +'/' + day +'/nytfrontpage/scan.jpg'
|
|
br = BasicNewsRecipe.get_browser()
|
|
try:
|
|
br.open(cover)
|
|
except:
|
|
self.log("\nCover unavailable")
|
|
cover = None
|
|
return cover
|
|
|
|
def get_masthead_title(self):
|
|
return 'NYTimes GR Version'
|
|
|
|
def dump_ans(self, ans):
|
|
total_article_count = 0
|
|
for section in ans :
|
|
if self.verbose:
|
|
self.log("section %s: %d articles" % (section[0], len(section[1])) )
|
|
for article in section[1]:
|
|
total_article_count += 1
|
|
if self.verbose:
|
|
self.log("\t%-40.40s... \t%-60.60s..." % (article['title'].encode('mac-roman','replace'),
|
|
article['url'].encode('mac-roman','replace')))
|
|
self.log( "Queued %d articles" % total_article_count )
|
|
|
|
def dump_hex(self, src, length=16):
|
|
''' Diagnostic '''
|
|
FILTER=''.join([(len(repr(chr(x)))==3) and chr(x) or '.' for x in range(256)])
|
|
N=0; result=''
|
|
while src:
|
|
s,src = src[:length],src[length:]
|
|
hexa = ' '.join(["%02X"%ord(x) for x in s])
|
|
s = s.translate(FILTER)
|
|
result += "%04X %-*s %s\n" % (N, length*3, hexa, s)
|
|
N+=length
|
|
print result
|
|
|
|
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)
|
|
|
|
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 parse_index(self):
|
|
soup = self.index_to_soup('http://www.nytimes.com/pages/todayspaper/index.html')
|
|
|
|
def feed_title(div):
|
|
return ''.join(div.findAll(text=True, recursive=False)).strip()
|
|
|
|
articles = {}
|
|
key = None
|
|
ans = []
|
|
# Find each instance of class="section-headline", class="story", class="story headline"
|
|
for div in soup.findAll(True,
|
|
attrs={'class':['section-headline', 'story', 'story headline']}):
|
|
|
|
if div['class'] == 'section-headline':
|
|
key = string.capwords(feed_title(div))
|
|
if self.excludeSectionKeywords:
|
|
excluded = re.compile('|'.join(self.excludeSectionKeywords))
|
|
if excluded.search(key):
|
|
self.log("Skipping section %s" % key)
|
|
continue
|
|
articles[key] = []
|
|
ans.append(key)
|
|
|
|
elif div['class'] in ['story', 'story headline'] :
|
|
a = div.find('a', href=True)
|
|
if not a:
|
|
continue
|
|
url = re.sub(r'\?.*', '', a['href'])
|
|
url += '?pagewanted=all'
|
|
|
|
title = self.massageNCXText(self.tag_to_string(a, use_alt=True).strip())
|
|
|
|
description = ''
|
|
pubdate = strftime('%a, %d %b')
|
|
summary = div.find(True, attrs={'class':'summary'})
|
|
if summary:
|
|
description = self.massageNCXText(self.tag_to_string(summary, use_alt=False))
|
|
|
|
author = ''
|
|
authorAttribution = div.find(True, attrs={'class':'storyheadline-author'})
|
|
if authorAttribution:
|
|
author = self.tag_to_string(authorAttribution, use_alt=False)
|
|
else:
|
|
authorAttribution = div.find(True, attrs={'class':'byline'})
|
|
if authorAttribution:
|
|
author = self.tag_to_string(authorAttribution, use_alt=False)
|
|
# Kill commas - Kindle switches to '&'
|
|
author = re.sub(',','',author)
|
|
|
|
feed = key if key is not None else 'Uncategorized'
|
|
if not articles.has_key(feed):
|
|
articles[feed] = []
|
|
if not 'podcasts' in url:
|
|
articles[feed].append(
|
|
dict(title=title, url=url, date=pubdate,
|
|
description=description, author=author,
|
|
content=''))
|
|
ans = self.sort_index_by(ans, {'The Front Page':-1,
|
|
'Dining In, Dining Out':1,
|
|
'Obituaries':2})
|
|
ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
|
|
self.dump_ans(ans)
|
|
return ans
|
|
|
|
def preprocess_html(self, soup):
|
|
# Skip ad pages served before actual article
|
|
skip_tag = soup.find(True, {'name':'skip'})
|
|
if skip_tag is not None:
|
|
self.log.error("Found forwarding link: %s" % skip_tag.parent['href'])
|
|
url = 'http://www.nytimes.com' + re.sub(r'\?.*', '', skip_tag.parent['href'])
|
|
url += '?pagewanted=all'
|
|
self.log.error("Skipping ad to article at '%s'" % url)
|
|
soup = self.index_to_soup(url)
|
|
return self.strip_anchors(soup)
|
|
|
|
def postprocess_html(self,soup, True):
|
|
print "\npostprocess_html()\n"
|
|
|
|
if self.one_picture_per_article:
|
|
# Remove all images after first
|
|
largeImg = soup.find(True, {'class':'articleSpanImage'})
|
|
inlineImgs = soup.findAll(True, {'class':'inlineImage module'})
|
|
if largeImg:
|
|
for inlineImg in inlineImgs:
|
|
inlineImg.extract()
|
|
else:
|
|
if inlineImgs:
|
|
firstImg = inlineImgs[0]
|
|
for inlineImg in inlineImgs[1:]:
|
|
inlineImg.extract()
|
|
# Move firstImg after headline
|
|
cgFirst = soup.find(True, {'class':'columnGroup first'})
|
|
if cgFirst:
|
|
# Strip all sibling NavigableStrings: noise
|
|
navstrings = cgFirst.findAll(text=True, recursive=False)
|
|
[ns.extract() for ns in navstrings]
|
|
headline_found = False
|
|
tag = cgFirst.find(True)
|
|
insertLoc = 0
|
|
while True:
|
|
insertLoc += 1
|
|
if hasattr(tag,'class') and tag['class'] == 'articleHeadline':
|
|
headline_found = True
|
|
break
|
|
tag = tag.nextSibling
|
|
if not tag:
|
|
headline_found = False
|
|
break
|
|
if headline_found:
|
|
cgFirst.insert(insertLoc,firstImg)
|
|
else:
|
|
self.log(">>> No class:'columnGroup first' found <<<")
|
|
# Change class="kicker" to <h3>
|
|
kicker = soup.find(True, {'class':'kicker'})
|
|
if kicker and kicker.contents[0]:
|
|
h3Tag = Tag(soup, "h3")
|
|
h3Tag.insert(0, self.fixChars(self.tag_to_string(kicker,
|
|
use_alt=False)))
|
|
kicker.replaceWith(h3Tag)
|
|
|
|
# Change captions to italic -1
|
|
for caption in soup.findAll(True, {'class':'caption'}) :
|
|
if caption and caption.contents[0]:
|
|
emTag = Tag(soup, "em")
|
|
c = self.fixChars(self.tag_to_string(caption,use_alt=False)).strip()
|
|
mp_off = c.find("More Photos")
|
|
if mp_off >= 0:
|
|
c = c[:mp_off]
|
|
emTag.insert(0, c)
|
|
hrTag = Tag(soup, 'hr')
|
|
#hrTag['style'] = "margin-top:0em;margin-bottom:0em"
|
|
emTag.insert(1, hrTag)
|
|
caption.replaceWith(emTag)
|
|
|
|
# Change <nyt_headline> to <h2>
|
|
h1 = soup.find('h1')
|
|
if h1:
|
|
headline = h1.find("nyt_headline")
|
|
if headline:
|
|
tag = Tag(soup, "h2")
|
|
tag['class'] = "headline"
|
|
tag.insert(0, self.fixChars(headline.contents[0]))
|
|
h1.replaceWith(tag)
|
|
else:
|
|
# Blog entry - replace headline, remove <hr> tags
|
|
headline = soup.find('title')
|
|
if headline:
|
|
tag = Tag(soup, "h2")
|
|
tag['class'] = "headline"
|
|
tag.insert(0, self.fixChars(headline.contents[0]))
|
|
soup.insert(0, tag)
|
|
hrs = soup.findAll('hr')
|
|
for hr in hrs:
|
|
hr.extract()
|
|
|
|
# Change <h1> to <h3> - used in editorial blogs
|
|
masthead = soup.find("h1")
|
|
if masthead:
|
|
# Nuke the href
|
|
if masthead.a:
|
|
del(masthead.a['href'])
|
|
tag = Tag(soup, "h3")
|
|
tag.insert(0, self.fixChars(masthead.contents[0]))
|
|
masthead.replaceWith(tag)
|
|
|
|
# Change <span class="bold"> to <b>
|
|
for subhead in soup.findAll(True, {'class':'bold'}) :
|
|
if subhead.contents:
|
|
bTag = Tag(soup, "b")
|
|
bTag.insert(0, subhead.contents[0])
|
|
subhead.replaceWith(bTag)
|
|
|
|
# Synthesize a section header
|
|
dsk = soup.find('meta', attrs={'name':'dsk'})
|
|
if dsk and dsk.has_key('content'):
|
|
hTag = Tag(soup,'h3')
|
|
hTag['class'] = 'section'
|
|
hTag.insert(0,NavigableString(dsk['content']))
|
|
articleTag = soup.find(True, attrs={'id':'article'})
|
|
if articleTag:
|
|
articleTag.insert(0,hTag)
|
|
|
|
# Add class="articleBody" to <div> so we can format with CSS
|
|
divTag = soup.find('div',attrs={'id':'articleBody'})
|
|
if divTag:
|
|
divTag['class'] = divTag['id']
|
|
|
|
# Add class="authorId" to <div> so we can format with CSS
|
|
divTag = soup.find('div',attrs={'id':'authorId'})
|
|
if divTag and divTag.contents[0]:
|
|
tag = Tag(soup, "p")
|
|
tag['class'] = "authorId"
|
|
tag.insert(0, self.fixChars(self.tag_to_string(divTag.contents[0],
|
|
use_alt=False)))
|
|
divTag.replaceWith(tag)
|
|
|
|
return soup
|
|
|
|
def postprocess_book(self, oeb, opts, log) :
|
|
print "\npostprocess_book()\n"
|
|
|
|
def extract_byline(href) :
|
|
# <meta name="byline" content=
|
|
soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
|
|
byline = soup.find('meta',attrs={'name':['byl','CLMST']})
|
|
if byline :
|
|
author = byline['content']
|
|
else :
|
|
# Try for <div class="byline">
|
|
byline = soup.find('div', attrs={'class':'byline'})
|
|
if byline:
|
|
author = byline.renderContents()
|
|
else:
|
|
print "couldn't find byline in %s" % href
|
|
print soup.prettify()
|
|
return None
|
|
# Kill commas - Kindle switches to '&'
|
|
return re.sub(',','',author)
|
|
|
|
def extract_description(href) :
|
|
soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
|
|
description = soup.find('meta',attrs={'name':['description','description ']})
|
|
if description :
|
|
# print repr(description['content'])
|
|
# print self.massageNCXText(description['content'])
|
|
return self.massageNCXText(description['content'])
|
|
else:
|
|
# Take first paragraph of article
|
|
articleBody = soup.find('div',attrs={'id':'articleBody'})
|
|
if not articleBody:
|
|
# Try again with class instead of id
|
|
articleBody = soup.find('div',attrs={'class':'articleBody'})
|
|
if not articleBody:
|
|
print 'postprocess_book.extract_description(): Did not find <div id="articleBody">:'
|
|
print soup.prettify()
|
|
return None
|
|
paras = articleBody.findAll('p')
|
|
for p in paras:
|
|
if p.renderContents() > '' :
|
|
return self.massageNCXText(self.tag_to_string(p,use_alt=False))
|
|
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).decode('utf-8')
|
|
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)
|
|
|
|
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('utf-8','replace'))
|
|
#a.replaceWith(a.renderContents().decode('cp1252','replace'))
|
|
return soup
|
|
|