Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update tvxs

Browse Source
This commit is contained in:
Kovid Goyal 2013-04-12 09:10:36 +05:30
parent c439cc94f1
commit 07c0cb85ce
1 changed files with 21 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
recipes/tvxs.recipe
View File

@ -1,5 +1,6 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai # vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
import re
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class TVXS(BasicNewsRecipe): class TVXS(BasicNewsRecipe):
@ -8,19 +9,30 @@ class TVXS(BasicNewsRecipe):
description = 'News from Greece' description = 'News from Greece'
max_articles_per_feed = 100 max_articles_per_feed = 100
oldest_article = 3 oldest_article = 3
simultaneous_downloads = 1
publisher = 'TVXS' publisher = 'TVXS'
category = 'news, GR' category = 'news, sport, greece'
language = 'el' language = 'el'
encoding = None encoding = None
use_embedded_content = False use_embedded_content = False
remove_empty_feeds = True remove_empty_feeds = True
#conversion_options = { 'linearize_tables': True} conversion_options = {'smarten_punctuation': True}
no_stylesheets = True no_stylesheets = True
publication_type = 'newspaper'
remove_tags_before = dict(name='h1',attrs={'class':'print-title'}) remove_tags_before = dict(name='h1',attrs={'class':'print-title'})
remove_tags_after = dict(name='div',attrs={'class':'field field-type-relevant-content field-field-relevant-articles'}) remove_tags_after = dict(name='div',attrs={'class':'field field-type-relevant-content field-field-relevant-articles'})
remove_attributes = ['width', 'src', 'header', 'footer'] remove_tags = [dict(name='div',attrs={'class':'field field-type-relevant-content field-field-relevant-articles'}),
dict(name='div',attrs={'class':'field field-type-filefield field-field-image-gallery'}),
dict(name='div',attrs={'class':'filefield-file'})]
remove_attributes = ['border', 'cellspacing', 'align', 'cellpadding', 'colspan', 'valign', 'vspace', 'hspace', 'alt', 'width', 'height']
extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
table { width: 100%; } \
td img { display: block; margin: 5px auto; } \
ul { padding-top: 10px; } \
ol { padding-top: 10px; } \
li { padding-top: 5px; padding-bottom: 5px; } \
h1 { text-align: center; font-size: 125%; font-weight: bold; } \
h2, h3, h4, h5, h6 { text-align: center; font-size: 100%; font-weight: bold; }'
preprocess_regexps = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''), (re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: '')]
feeds = [(u'Ελλάδα', 'http://tvxs.gr/feeds/2/feed.xml'), feeds = [(u'Ελλάδα', 'http://tvxs.gr/feeds/2/feed.xml'),
(u'Κόσμος', 'http://tvxs.gr/feeds/5/feed.xml'), (u'Κόσμος', 'http://tvxs.gr/feeds/5/feed.xml'),
@ -35,17 +47,10 @@ class TVXS(BasicNewsRecipe):
(u'Ιστορία', 'http://tvxs.gr/feeds/1573/feed.xml'), (u'Ιστορία', 'http://tvxs.gr/feeds/1573/feed.xml'),
(u'Χιούμορ', 'http://tvxs.gr/feeds/692/feed.xml')] (u'Χιούμορ', 'http://tvxs.gr/feeds/692/feed.xml')]
def print_version(self, url): def print_version(self, url):
import urllib2, urlparse, StringIO, gzip br = self.get_browser()
response = br.open(url)
fp = urllib2.urlopen(url) data = response.read()
data = fp.read()
if fp.info()['content-encoding'] == 'gzip':
gzip_data = StringIO.StringIO(data)
gzipper = gzip.GzipFile(fileobj=gzip_data)
data = gzipper.read()
fp.close()
pos_1 = data.find('<a href="/print/') pos_1 = data.find('<a href="/print/')
if pos_1 == -1: if pos_1 == -1:
@ -57,5 +62,5 @@ class TVXS(BasicNewsRecipe):
pos_1 += len('<a href="') pos_1 += len('<a href="')
new_url = data[pos_1:pos_2] new_url = data[pos_1:pos_2]
print_url = urlparse.urljoin(url, new_url) print_url = "http://tvxs.gr" + new_url
return print_url return print_url