mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Merge branch 'master' of https://github.com/unkn0w7n/calibre
This commit is contained in:
Kovid Goyal
commit
f43921893b
Binary file not shown.
|
Before Width: | Height: | Size: 324 B |
Binary file not shown.
|
Before Width: | Height: | Size: 142 B After Width: | Height: | Size: 170 B |
@ -1,149 +0,0 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010-2019'
|
||||
'''
|
||||
www.thetimes.co.uk/magazine/the-sunday-times-magazine/
|
||||
'''
|
||||
|
||||
from calibre import random_user_agent
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from mechanize import Request
|
||||
|
||||
|
||||
def classes(classes):
|
||||
q = frozenset(classes.split(' '))
|
||||
return dict(attrs={
|
||||
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
||||
|
||||
|
||||
class TimesOnline(BasicNewsRecipe):
|
||||
title = 'The Sunday Times Magazine UK'
|
||||
__author__ = 'Bobby Steel & Darko Miletic'
|
||||
description = 'Newsmagazine from United Kingdom and World'
|
||||
language = 'en_GB'
|
||||
publisher = 'Times Newspapers Ltd'
|
||||
category = 'news, politics, UK'
|
||||
oldest_article = 3
|
||||
max_articles_per_feed = 500
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
delay = 1
|
||||
needs_subscription = True
|
||||
publication_type = 'newspaper'
|
||||
INDEX = 'https://www.thetimes.co.uk'
|
||||
LOGIN = 'https://login.thetimes.co.uk/'
|
||||
PREFIX = u'https://www.thetimes.co.uk'
|
||||
extra_css = """
|
||||
.author-name,.authorName{font-style: italic}
|
||||
.published-date,.multi-position-photo-text{
|
||||
font-family: Arial,Helvetica,sans-serif;
|
||||
font-size: small; color: gray;
|
||||
display:block; margin-bottom: 0.5em}
|
||||
body{font-family: Georgia,"Times New Roman",Times,serif}
|
||||
"""
|
||||
|
||||
conversion_options = {
|
||||
'comment': description,
|
||||
'tags': category,
|
||||
'publisher': publisher,
|
||||
'language': language}
|
||||
|
||||
def get_browser(self, *a, **kw):
|
||||
start_url = self.INDEX
|
||||
kw['user_agent'] = random_user_agent(allow_ie=False)
|
||||
br = BasicNewsRecipe.get_browser(self, *a, **kw)
|
||||
self.log('Starting login process...')
|
||||
res = br.open(start_url)
|
||||
sso_url = res.geturl()
|
||||
self.log(sso_url)
|
||||
request_query = {
|
||||
'username': self.username,
|
||||
'password': self.password,
|
||||
's': 1,
|
||||
'gotoUrl': self.INDEX,
|
||||
}
|
||||
rq = Request(self.LOGIN, headers={
|
||||
'Accept': 'text/html',
|
||||
'Accept-Language': 'en-US,en;q=0.8',
|
||||
'X-HTTP-Method-Override': 'POST',
|
||||
'X-Requested-With': 'XMLHttpRequest',
|
||||
}, data=request_query)
|
||||
self.log('Sending login request...')
|
||||
res = br.open(rq)
|
||||
return br
|
||||
# }}}
|
||||
|
||||
def get_cover_url(self):
|
||||
from datetime import date, timedelta
|
||||
today = date.today()
|
||||
today_index = today.weekday()
|
||||
if (today_index == 5): # new edition drops on Saturday AM
|
||||
today += timedelta(1)
|
||||
elif (today_index < 5): # Mon-Thurs
|
||||
today_index = (
|
||||
today_index + 1
|
||||
) % 7 # Recalibrate to days back MON = 0, SUN = 6 -> SUN = 0 .. SAT = 6
|
||||
today = today - timedelta(today_index) # Rewind to most recent Sunday
|
||||
cover = 'https://cdn2-img.pressreader.com/pressdisplay/docserver/getimage.aspx?file=1174' + today.strftime(
|
||||
'%Y') + today.strftime('%m') + today.strftime(
|
||||
'%d') + '00000000001001&page=1&scale=100'
|
||||
self.log(cover)
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
try:
|
||||
br.open(cover)
|
||||
except:
|
||||
self.log("\nCover unavailable")
|
||||
cover = None
|
||||
return cover
|
||||
|
||||
remove_tags = [
|
||||
classes('Topics is-hidden Tooltip Toolbar Comments RelatedLinks'),
|
||||
{'name': ['object', 'link', 'iframe', 'base', 'meta', 'script']}, {
|
||||
'attrs': {
|
||||
'class': [
|
||||
'tools comments-parent', 'u-hide', 'Tooltip',
|
||||
'Toolbar Toolbar--bottom', 'Comments Article-container',
|
||||
'ArticlePager', 'Media-caption', 'RelatedLinks']}}, {
|
||||
'attrs': {
|
||||
'class': lambda x: x and 'Toolbar' in x}}]
|
||||
remove_attributes = ['lang']
|
||||
keep_only_tags = [
|
||||
dict(attrs={'id': 'article-main'}),
|
||||
dict(attrs={'class': 'f-author'}),
|
||||
dict(attrs={'id': 'bodycopy'})]
|
||||
|
||||
feeds = [(
|
||||
u'The Sunday Times Magazine',
|
||||
u'http://www.thetimes.co.uk/magazine/the-sunday-times-magazine/'),
|
||||
(u'Sunday Times Style', u'http://www.thetimes.co.uk/magazine/style/')]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return self.adeify_images(soup)
|
||||
|
||||
def parse_index(self):
|
||||
totalfeeds = []
|
||||
lfeeds = self.get_feeds()
|
||||
for feedobj in lfeeds:
|
||||
feedtitle, feedurl = feedobj
|
||||
self.report_progress(
|
||||
0,
|
||||
_('Fetching feed') + ' %s...' %
|
||||
(feedtitle if feedtitle else feedurl))
|
||||
articles = []
|
||||
soup = self.index_to_soup(feedurl)
|
||||
for atag in soup.findAll('a', href=True):
|
||||
parentName = atag.parent.name
|
||||
title = self.tag_to_string(atag).strip()
|
||||
if (
|
||||
parentName == 'h2' or
|
||||
parentName == 'h3') and title is not None and title != '':
|
||||
url = self.INDEX + atag['href']
|
||||
articles.append({
|
||||
'title': title,
|
||||
'date': '',
|
||||
'url': url,
|
||||
'description': ''})
|
||||
totalfeeds.append((feedtitle, articles))
|
||||
return totalfeeds
|
||||
@ -1,159 +1,138 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010-2019, Bobby Steel <bob at xdca.com>, Darko Miletic'
|
||||
'''
|
||||
www.thetimes.co.uk
|
||||
'''
|
||||
import html5lib
|
||||
from calibre import random_user_agent
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from lxml import html
|
||||
from mechanize import Request
|
||||
from urllib.parse import quote
|
||||
from calibre.scraper.simple import read_url
|
||||
from calibre.web.feeds.news import BasicNewsRecipe, prefixed_classes
|
||||
|
||||
def resize(x):
|
||||
if 'resize' in x:
|
||||
return x.split('&resize')[0] + '&resize=600'
|
||||
elif '?crop=' in x:
|
||||
return x + '&resize=600'
|
||||
|
||||
def classes(classes):
|
||||
q = frozenset(classes.split(' '))
|
||||
return dict(
|
||||
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
||||
|
||||
|
||||
class TimesOnline(BasicNewsRecipe):
|
||||
title = 'The Times & Sunday Times (UK)'
|
||||
__author__ = 'Bobby Steel'
|
||||
description = 'news from United Kingdom and World'
|
||||
class times(BasicNewsRecipe):
|
||||
title = 'The Times and Sunday Times'
|
||||
__author__ = 'unkn0wn'
|
||||
description = (
|
||||
'The Times, founded in 1785 as the Daily Universal Register, is the oldest national daily newspaper '
|
||||
'in the UK and holds an important place as the “paper of record” on public life, from politics and world '
|
||||
'affairs to business and sport.'
|
||||
)
|
||||
language = 'en_GB'
|
||||
publisher = 'Times Newspapers Ltd'
|
||||
category = 'news, politics, UK'
|
||||
excludeSections = ['Puzzles']
|
||||
oldest_article = 1
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
encoding = 'utf-8'
|
||||
delay = 1
|
||||
needs_subscription = True
|
||||
publication_type = 'newspaper'
|
||||
INDEX = 'http://www.thetimes.co.uk/'
|
||||
LOGIN = 'https://login.thetimes.co.uk/'
|
||||
PREFIX = u'http://www.thetimes.co.uk'
|
||||
extra_css = """
|
||||
.author-name,.authorName{font-style: italic}
|
||||
.published-date,.multi-position-photo-text{font-family: Arial,Helvetica,sans-serif;
|
||||
font-size: small; color: gray;
|
||||
display:block; margin-bottom: 0.5em}
|
||||
body{font-family: Georgia,"Times New Roman",Times,serif}
|
||||
"""
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
remove_attributes = ['width', 'height', 'style']
|
||||
masthead_url = 'https://www.thetimes.com/d/img/logos/times-black-ee1e0ce4ed.png'
|
||||
|
||||
conversion_options = {
|
||||
'comment': description,
|
||||
'tags': category,
|
||||
'publisher': publisher,
|
||||
'language': language}
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
remove_empty_feeds = True
|
||||
resolve_internal_links = True
|
||||
simultaneous_downloads = 1
|
||||
oldest_article = 1 # days
|
||||
web_url = ''
|
||||
|
||||
def get_cover_url(self):
|
||||
from datetime import date
|
||||
today = date.today()
|
||||
today_index = today.weekday()
|
||||
if (today_index == 6): # Special cover on Sundays
|
||||
cover = 'https://cdn2-img.pressreader.com/pressdisplay/docserver/getimage.aspx?file=1163' + today.strftime(
|
||||
'%Y') + today.strftime('%m') + today.strftime(
|
||||
'%d') + '00000000001001&page=1&scale=99'
|
||||
altcover = 'https://cdn2-img.pressreader.com/pressdisplay/docserver/getimage.aspx?file=1163' + today.strftime(
|
||||
'%Y') + today.strftime('%m') + today.strftime(
|
||||
'%d') + '00000051001001&page=1&scale=99'
|
||||
# on some days cover is iterated using format here for altcover
|
||||
else: # Mon-Thurs
|
||||
cover = 'https://cdn2-img.pressreader.com/pressdisplay/docserver/getimage.aspx?file=1148' + today.strftime(
|
||||
'%Y') + today.strftime('%m') + today.strftime(
|
||||
'%d') + '00000000001001&page=1&scale=99'
|
||||
altcover = 'https://cdn2-img.pressreader.com/pressdisplay/docserver/getimage.aspx?file=1148' + today.strftime(
|
||||
'%Y') + today.strftime('%m') + today.strftime(
|
||||
'%d') + '00000051001001&page=1&scale=99'
|
||||
self.log(cover)
|
||||
br = BasicNewsRecipe.get_browser(self)
|
||||
try:
|
||||
br.open(cover)
|
||||
except:
|
||||
cover = altcover
|
||||
br.open(cover)
|
||||
return cover
|
||||
soup = self.index_to_soup('https://www.frontpages.com/the-times/')
|
||||
return 'https://www.frontpages.com' + soup.find('img', attrs={'id':'giornale-img'})['src']
|
||||
|
||||
def get_browser(self, *a, **kw):
|
||||
start_url = self.INDEX
|
||||
kw['user_agent'] = random_user_agent(allow_ie=False)
|
||||
br = BasicNewsRecipe.get_browser(self, *a, **kw)
|
||||
self.log('Starting login process...')
|
||||
res = br.open(start_url)
|
||||
sso_url = res.geturl()
|
||||
self.log(sso_url)
|
||||
request_query = {
|
||||
'username': self.username,
|
||||
'password': self.password,
|
||||
's': 1,
|
||||
'gotoUrl': self.INDEX,
|
||||
}
|
||||
rq = Request(self.LOGIN, headers={
|
||||
'Accept': 'text/html',
|
||||
'Accept-Language': 'en-US,en;q=0.8',
|
||||
'X-HTTP-Method-Override': 'POST',
|
||||
'X-Requested-With': 'XMLHttpRequest',
|
||||
}, data=request_query)
|
||||
self.log('Sending login request...')
|
||||
res = br.open(rq)
|
||||
return br
|
||||
extra_css = '''
|
||||
.tc-view__TcView-nuazoi-0, [class^="keylines__KeylineItem-"], .sub { font-size:small; }
|
||||
[class^="responsive__StandfirstContainer-"] { font-style:italic; }
|
||||
'''
|
||||
|
||||
remove_tags = [
|
||||
classes('is-hidden Toolbar Tooltip Topics Comments u-hide RelatedLinks ArticlePager Media-caption'),
|
||||
{'name': ['object', 'link', 'iframe', 'base', 'meta', 'script']},
|
||||
keep_only_tags = [
|
||||
prefixed_classes(
|
||||
'responsive__HeadlineContainer- keylines__KeylineItem- responsive__StandfirstContainer- '
|
||||
'responsive__LeadAsset- responsive__ArticleContent-'
|
||||
)
|
||||
]
|
||||
|
||||
remove_attributes = ['lang']
|
||||
keep_only_tags = [{
|
||||
'attrs': {
|
||||
'id': ['article-main', 'bodycopy']}}, {
|
||||
'attrs': {
|
||||
'class': ['Article Article--default', 'f-author']}}]
|
||||
remove_tags_after = dict(attrs={'class': 'Article-content'})
|
||||
remove_tags = [
|
||||
dict(name=['svg']),
|
||||
dict(attrs={'id':'iframe-wrapper'}),
|
||||
dict(attrs={'old-position':'sticky'}),
|
||||
prefixed_classes(
|
||||
'responsive__InlineAdWrapper-'
|
||||
)
|
||||
]
|
||||
|
||||
feeds = [(u'All News', u'http://www.thetimes.co.uk/')]
|
||||
|
||||
def preprocess_raw_html(self, raw, url):
|
||||
return html.tostring(
|
||||
html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False),
|
||||
method='html',
|
||||
encoding='unicode')
|
||||
remove_tags_after = [
|
||||
dict(name = 'div', attrs={'id':'paywall-portal-article-footer'})
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
return self.adeify_images(soup)
|
||||
h2 = soup.find(**prefixed_classes('responsive__StandfirstContainer-'))
|
||||
if h2:
|
||||
h2.name = 'p'
|
||||
for h2 in soup.findAll('h2'):
|
||||
if h2.text == 'Advertisement':
|
||||
div = h2.findParent('div')
|
||||
if div:
|
||||
div.extract()
|
||||
for img in soup.findAll('img', src=True):
|
||||
img['src'] = resize(img['src'])
|
||||
for img in soup.findAll('img', attrs={'old-src':True}):
|
||||
img['src'] = resize(img['old-src'])
|
||||
for a in soup.findAll('a', href=True):
|
||||
a['href'] = 'http' + a['href'].split('http')[-1]
|
||||
div = soup.findAll(attrs={'style': lambda x: x and x.startswith(
|
||||
'color:rgb(51, 51, 51);font-family:TimesDigitalW04-Regular'
|
||||
)})
|
||||
for p in div:
|
||||
p.name = 'p'
|
||||
for d in soup.findAll(attrs={'id': lambda x: x and '.' in x}):
|
||||
d['class'] = 'sub'
|
||||
for fig in soup.findAll('figure'):
|
||||
fig['class'] = 'sub'
|
||||
return soup
|
||||
|
||||
def parse_index(self):
|
||||
soup = self.index_to_soup(self.INDEX)
|
||||
totalfeeds = []
|
||||
current_section = []
|
||||
div = []
|
||||
for div in soup.findAll('section', attrs={'data-text': True}):
|
||||
current_articles = []
|
||||
self.log('in section: ', div['data-text'])
|
||||
current_section = div['data-text']
|
||||
if current_section not in self.excludeSections:
|
||||
for article in div.findAll('div', attrs={'class': 'Item-content'}):
|
||||
h3 = article.find('h3')
|
||||
if h3 is not None:
|
||||
title = self.tag_to_string(h3)
|
||||
aurl = h3.find('a')
|
||||
if aurl is not None:
|
||||
url = aurl['href']
|
||||
if url.startswith('/'):
|
||||
url = 'http://www.thetimes.co.uk' + url
|
||||
desc = title
|
||||
self.log(
|
||||
'section: ', current_section, 'title: ', title,
|
||||
'url: ', url, 'desc: ', desc, '\n')
|
||||
current_articles.append({
|
||||
'title': title,
|
||||
'url': url,
|
||||
'description': desc})
|
||||
if current_articles:
|
||||
totalfeeds.append((current_section, current_articles))
|
||||
return totalfeeds
|
||||
articles_are_obfuscated = True
|
||||
|
||||
def get_obfuscated_article(self, url):
|
||||
soup = self.index_to_soup(url)
|
||||
link = soup.a['href']
|
||||
skip_sections =[ # add sections you want to skip
|
||||
'/video/', '/videos/', '/multimedia/',
|
||||
]
|
||||
if any(x in link for x in skip_sections):
|
||||
self.abort_article('skipping video links ', link)
|
||||
self.web_url = link
|
||||
html = self.index_to_soup(link, raw=True)
|
||||
return ({ 'data': html, 'url': link })
|
||||
|
||||
feeds = []
|
||||
when = oldest_article*24
|
||||
index = 'https://www.thetimes.com/'
|
||||
sections = [
|
||||
'politics', 'world', 'uk/politics', 'uk/scotland', 'uk', 'comment', 'business-money', 'sport',
|
||||
'life-style', 'culture', 'magazine', 'travel', 'sunday-times', 'edition', 'article'
|
||||
]
|
||||
for sec in sections:
|
||||
a = 'https://news.google.com/rss/search?q=when:{}h+allinurl:{}&hl=en-GB&gl=GB&ceid=GB:en'
|
||||
feeds.append((sec.capitalize(), a.format(when, quote(index + sec, safe=''))))
|
||||
feeds.append(('Others', a.format(when, quote(index, safe=''))))
|
||||
|
||||
def preprocess_raw_html(self, raw, url):
|
||||
access = '"userState":{"isLoggedIn":false,"isMetered":false,"hasAccess":true}'
|
||||
if access not in raw and 'comment/cartoons' not in url:
|
||||
raw_ar = read_url([], 'https://archive.is/latest/' + url)
|
||||
archive = BeautifulSoup(str(raw_ar))
|
||||
if archive.find('div', attrs={'id':'top'}):
|
||||
content = archive.find('article', attrs={'id':False})
|
||||
soup = BeautifulSoup(raw)
|
||||
article = soup.find(**prefixed_classes('responsive__ArticleContent-'))
|
||||
if article and content:
|
||||
self.log('**fetching archive content')
|
||||
article.clear()
|
||||
article.append(content)
|
||||
return str(soup)
|
||||
return raw
|
||||
return raw
|
||||
return raw
|
||||
|
||||
def populate_article_metadata(self, article, soup, first):
|
||||
article.title = article.title.replace(' - The Times', '')
|
||||
desc = soup.find(**prefixed_classes('responsive__StandfirstContainer-'))
|
||||
if desc:
|
||||
article.summary = self.tag_to_string(desc)
|
||||
article.text_summary = article.summary
|
||||
article.url = self.web_url
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user