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 Arcamax

Browse Source
This commit is contained in:
Kovid Goyal 2012-09-07 08:32:34 +05:30
parent dd5fe809cc
commit cc13e025d7
1 changed files with 21 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
recipes/arcamax.recipe
View File

@ -31,15 +31,13 @@ class Arcamax(BasicNewsRecipe):
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':['comics-header']}),
dict(name='b', attrs={'class':['current']}),
dict(name='article', attrs={'class':['comic']}),
keep_only_tags = [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' ]}),
]
#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 = []
@ -48,20 +46,20 @@ class Arcamax(BasicNewsRecipe):
#(u"9 Chickweed Lane", u"http://www.arcamax.com/ninechickweedlane"),
#(u"Agnes", u"http://www.arcamax.com/agnes"),
#(u"Andy Capp", u"http://www.arcamax.com/andycapp"),
(u"BC", u"http://www.arcamax.com/bc"),
(u"BC", u"http://www.arcamax.com/thefunnies/bc"),
#(u"Baby Blues", u"http://www.arcamax.com/babyblues"),
#(u"Beetle Bailey", u"http://www.arcamax.com/beetlebailey"),
(u"Blondie", u"http://www.arcamax.com/blondie"),
(u"Blondie", u"http://www.arcamax.com/thefunnies/blondie"),
#u"Boondocks", u"http://www.arcamax.com/boondocks"),
#(u"Cathy", u"http://www.arcamax.com/cathy"),
#(u"Daddys Home", u"http://www.arcamax.com/daddyshome"),
(u"Dilbert", u"http://www.arcamax.com/dilbert"),
(u"Dilbert", u"http://www.arcamax.com/thefunnies/dilbert"),
#(u"Dinette Set", u"http://www.arcamax.com/thedinetteset"),
(u"Dog Eat Doug", u"http://www.arcamax.com/dogeatdoug"),
(u"Doonesbury", u"http://www.arcamax.com/doonesbury"),
(u"Dog Eat Doug", u"http://www.arcamax.com/thefunnies/dogeatdoug"),
(u"Doonesbury", u"http://www.arcamax.com/thefunnies/doonesbury"),
#(u"Dustin", u"http://www.arcamax.com/dustin"),
(u"Family Circus", u"http://www.arcamax.com/familycircus"),
(u"Garfield", u"http://www.arcamax.com/garfield"),
(u"Family Circus", u"http://www.arcamax.com/thefunnies/familycircus"),
(u"Garfield", u"http://www.arcamax.com/thefunnies/garfield"),
#(u"Get Fuzzy", u"http://www.arcamax.com/getfuzzy"),
#(u"Girls and Sports", u"http://www.arcamax.com/girlsandsports"),
#(u"Hagar the Horrible", u"http://www.arcamax.com/hagarthehorrible"),
@ -70,16 +68,16 @@ class Arcamax(BasicNewsRecipe):
#(u"Luann", u"http://www.arcamax.com/luann"),
#(u"Momma", u"http://www.arcamax.com/momma"),
#(u"Mother Goose and Grimm", u"http://www.arcamax.com/mothergooseandgrimm"),
(u"Mutts", u"http://www.arcamax.com/mutts"),
(u"Mutts", u"http://www.arcamax.com/thefunnies/mutts"),
#(u"Non Sequitur", u"http://www.arcamax.com/nonsequitur"),
#(u"Pearls Before Swine", u"http://www.arcamax.com/pearlsbeforeswine"),
#(u"Pickles", u"http://www.arcamax.com/pickles"),
#(u"Red and Rover", u"http://www.arcamax.com/redandrover"),
#(u"Rubes", u"http://www.arcamax.com/rubes"),
#(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"Zits", u"http://www.arcamax.com/zits"),
(u"Speed Bump", u"http://www.arcamax.com/thefunnies/speedbump"),
(u"Wizard of Id", u"http://www.arcamax.com/thefunnies/wizardofid"),
(u"Zits", u"http://www.arcamax.com/thefunnies/zits"),
]:
articles = self.make_links(url)
if articles:
@ -93,11 +91,11 @@ class Arcamax(BasicNewsRecipe):
for page in pages:
page_soup = self.index_to_soup(url)
if page_soup:
title = self.tag_to_string(page_soup.find(name='div', attrs={'class':'comics-header'}).h1.contents[0])
title = self.tag_to_string(page_soup.find(name='div', attrs={'class':'columnheader'}).h1.contents[0])
page_url = 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']
date = self.tag_to_string(page_soup.find(name='b', attrs={'class':['current']}))
prev_page_url = 'http://www.arcamax.com' + page_soup.find(name='a', attrs={'class':['prev']})['href']
date = self.tag_to_string(page_soup.find(name='span', attrs={'class':['cur']}))
current_articles.append({'title': title, 'url': page_url, 'description':'', 'date': date})
url = prev_page_url
current_articles.reverse()
@ -127,3 +125,4 @@ class Arcamax(BasicNewsRecipe):
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''