Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-07 09:01:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

Updated Arcamax

Browse Source
This commit is contained in:
Kovid Goyal 2011-04-18 08:43:55 -06:00
parent 89d2b56ce8
commit 27cd0b6873
1 changed files with 36 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
recipes/arcamax.recipe
View File

@ -6,12 +6,13 @@ __copyright__ = 'Copyright 2010 Starson17'
www.arcamax.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Arcamax(BasicNewsRecipe):
title = 'Arcamax'
__author__ = 'Starson17'
__version__ = '1.03'
__date__ = '25 November 2010'
__version__ = '1.04'
__date__ = '18 April 2011'
description = u'Family Friendly Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.'
category = 'news, comics'
language = 'en'
@ -30,8 +31,15 @@ class Arcamax(BasicNewsRecipe):
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':['toon']}),
]
keep_only_tags = [dict(name='div', attrs={'class':['comics-header']}),
dict(name='b', attrs={'class':['current']}),
dict(name='article', attrs={'class':['comic']}),
]
remove_tags = [dict(name='div', attrs={'id':['comicfull' ]}),
dict(name='div', attrs={'class':['calendar' ]}),
dict(name='nav', attrs={'class':['calendar-nav' ]}),
]
def parse_index(self):
feeds = []
@ -71,7 +79,6 @@ class Arcamax(BasicNewsRecipe):
#(u"Rugrats", u"http://www.arcamax.com/rugrats"),
(u"Speed Bump", u"http://www.arcamax.com/speedbump"),
(u"Wizard of Id", u"http://www.arcamax.com/wizardofid"),
(u"Dilbert", u"http://www.arcamax.com/dilbert"),
(u"Zits", u"http://www.arcamax.com/zits"),
]:
articles = self.make_links(url)
@ -86,24 +93,41 @@ class Arcamax(BasicNewsRecipe):
for page in pages:
page_soup = self.index_to_soup(url)
if page_soup:
title = page_soup.find(name='div', attrs={'class':'toon'}).p.img['alt']
title = page_soup.find(name='div', attrs={'class':'comics-header'}).h1.contents[0]
print 'title is: ', title
page_url = url
prev_page_url = 'http://www.arcamax.com' + page_soup.find('a', attrs={'class':'next'}, text='Previous').parent['href']
current_articles.append({'title': title, 'url': page_url, 'description':'', 'date':''})
print 'url is: ', url
# orig prev_page_url = 'http://www.arcamax.com' + page_soup.find('a', attrs={'class':'prev'}, text='Previous').parent['href']
prev_page_url = 'http://www.arcamax.com' + page_soup.find('span', text='Previous').parent.parent['href']
print 'prev_page_url is: ', prev_page_url
date = self.tag_to_string(page_soup.find(name='b', attrs={'class':['current']}))
print 'date is: ', date
current_articles.append({'title': title, 'url': page_url, 'description':'', 'date': date})
url = prev_page_url
current_articles.reverse()
return current_articles
def preprocess_html(self, soup):
main_comic = soup.find('p',attrs={'class':'m0'})
if main_comic.a['target'] == '_blank':
main_comic.a.img['id'] = 'main_comic'
for img_tag in soup.findAll('img'):
parent_tag = img_tag.parent
if parent_tag.name == 'a':
new_tag = Tag(soup,'p')
new_tag.insert(0,img_tag)
parent_tag.replaceWith(new_tag)
elif parent_tag.name == 'p':
if not self.tag_to_string(parent_tag) == '':
new_div = Tag(soup,'div')
new_tag = Tag(soup,'p')
new_tag.insert(0,img_tag)
parent_tag.replaceWith(new_div)
new_div.insert(0,new_tag)
new_div.insert(1,parent_tag)
return soup
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
img#main_comic {max-width:100%; min-width:100%;}
img {max-width:100%; min-width:100%;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''