mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
147 lines
6.5 KiB
Python
147 lines
6.5 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = 'Copyright 2010 Starson17'
|
|
'''
|
|
www.arcamax.com
|
|
'''
|
|
|
|
import os
|
|
|
|
from calibre.ptempfile import PersistentTemporaryDirectory
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Arcamax(BasicNewsRecipe):
|
|
title = 'Arcamax'
|
|
__author__ = 'Kovid Goyal'
|
|
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'
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
simultaneous_downloads = 1
|
|
cover_url = 'https://www.arcamax.com/images/pub/amuse/leftcol/zits.jpg'
|
|
|
|
# ###### USER PREFERENCES - SET COMICS AND NUMBER OF COMICS TO RETRIEVE ##
|
|
num_comics_to_get = 7
|
|
# CHOOSE COMIC STRIPS BELOW - REMOVE COMMENT '# ' FROM IN FRONT OF DESIRED
|
|
# STRIPS
|
|
|
|
recipe_specific_options = {
|
|
'days': {
|
|
'short': 'NUMBER OF COMICS TO RETRIEVE',
|
|
'default': str(num_comics_to_get)
|
|
}
|
|
}
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
|
d = self.recipe_specific_options.get('days')
|
|
if d and isinstance(d, str):
|
|
self.num_comics_to_get = float(d)
|
|
|
|
conversion_options = {'linearize_tables': True, 'comment': description, 'tags': category, 'language': language
|
|
}
|
|
|
|
keep_only_tags = [
|
|
dict(name='header', attrs={'class': 'fn-content-header bluelabel', 'style': False}),
|
|
dict(name='figure', attrs={'class': ['comic']}),
|
|
]
|
|
|
|
remove_tags_after = [
|
|
dict(name='figure', attrs={'class': ['comic']}),
|
|
]
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
self.panel_tdir = PersistentTemporaryDirectory('arcamax')
|
|
self.panel_counter = 0
|
|
|
|
# https://www.arcamax.com/comics
|
|
|
|
for title, url in [
|
|
# ####### COMICS - GENERAL ########
|
|
# (u"9 Chickweed Lane", u"https://www.arcamax.com/thefunnies/ninechickweedlane"),
|
|
# (u"Agnes", u"https://www.arcamax.com/thefunnies/agnes"),
|
|
# (u"Andy Capp", u"https://www.arcamax.com/thefunnies/andycapp"),
|
|
(u'BC', u'https://www.arcamax.com/thefunnies/bc'),
|
|
# (u"Baby Blues", u"https://www.arcamax.com/thefunnies/babyblues"),
|
|
# (u"Beetle Bailey", u"https://www.arcamax.com/thefunnies/beetlebailey"),
|
|
(u'Blondie', u'https://www.arcamax.com/thefunnies/blondie'),
|
|
# u"Boondocks", u"https://www.arcamax.com/thefunnies/boondocks"),
|
|
# (u"Cathy", u"https://www.arcamax.com/thefunnies/cathy"),
|
|
# (u"Daddys Home", u"https://www.arcamax.com/thefunnies/daddyshome"),
|
|
# (u"Dinette Set", u"https://www.arcamax.com/thefunnies/thedinetteset"),
|
|
(u'Dog Eat Doug', u'https://www.arcamax.com/thefunnies/dogeatdoug'),
|
|
# (u"Doonesbury", u"https://www.arcamax.com/thefunnies/doonesbury"),
|
|
# (u"Dustin", u"https://www.arcamax.com/thefunnies/dustin"),
|
|
(u'Family Circus', u'https://www.arcamax.com/thefunnies/familycircus'),
|
|
(u'Garfield', u'https://www.arcamax.com/thefunnies/garfield'),
|
|
# (u"Get Fuzzy", u"https://www.arcamax.com/thefunnies/getfuzzy"),
|
|
# (u"Girls and Sports", u"https://www.arcamax.com/thefunnies/girlsandsports"),
|
|
# (u"Hagar the Horrible", u"https://www.arcamax.com/thefunnies/hagarthehorrible"),
|
|
# (u"Heathcliff", u"https://www.arcamax.com/thefunnies/heathcliff"),
|
|
# (u"Jerry King Cartoons", u"https://www.arcamax.com/thefunnies/humorcartoon"),
|
|
# (u"Luann", u"https://www.arcamax.com/thefunnies/luann"),
|
|
# (u"Momma", u"https://www.arcamax.com/thefunnies/momma"),
|
|
# (u"Mother Goose and Grimm", u"https://www.arcamax.com/thefunnies/mothergooseandgrimm"),
|
|
(u'Mutts', u'https://www.arcamax.com/thefunnies/mutts'),
|
|
# (u"Non Sequitur", u"https://www.arcamax.com/thefunnies/nonsequitur"),
|
|
# (u"Pearls Before Swine", u"https://www.arcamax.com/thefunnies/pearlsbeforeswine"),
|
|
# (u"Pickles", u"https://www.arcamax.com/thefunnies/pickles"),
|
|
# (u"Red and Rover", u"https://www.arcamax.com/thefunnies/redandrover"),
|
|
# (u"Rubes", u"https://www.arcamax.com/thefunnies/rubes"),
|
|
# (u"Rugrats", u"https://www.arcamax.com/thefunnies/rugrats"),
|
|
(u'Speed Bump', u'https://www.arcamax.com/thefunnies/speedbump'),
|
|
(u'Wizard of Id', u'https://www.arcamax.com/thefunnies/wizardofid'),
|
|
(u'Zits', u'https://www.arcamax.com/thefunnies/zits'),
|
|
]:
|
|
self.log('Finding strips for:', title)
|
|
articles = self.make_links(url, title)
|
|
if articles:
|
|
feeds.append((title, articles))
|
|
if self.test and len(feeds) >= self.test[0]:
|
|
break
|
|
return feeds
|
|
|
|
def make_links(self, url, title):
|
|
current_articles = []
|
|
num = self.num_comics_to_get
|
|
while num > 0:
|
|
num -= 1
|
|
raw = self.index_to_soup(url, raw=True)
|
|
self.panel_counter += 1
|
|
path = os.path.join(self.panel_tdir, '%d.html' %
|
|
self.panel_counter)
|
|
with open(path, 'wb') as f:
|
|
f.write(raw)
|
|
soup = self.index_to_soup(raw)
|
|
a = soup.find(name='a', attrs={'class': ['prev']})
|
|
prev_page_url = 'https://www.arcamax.com' + a['href']
|
|
title = self.tag_to_string(
|
|
soup.find('title')).partition('|')[0].strip()
|
|
if 'for' not in title.split():
|
|
title = title + ' for today'
|
|
date = self.tag_to_string(
|
|
soup.find(name='span', attrs={'class': ['cur']}))
|
|
self.log('\tFound:', title, 'at:', url)
|
|
current_articles.append(
|
|
{'title': title, 'url': 'file://' + path, 'description': '', 'date': date})
|
|
if self.test and len(current_articles) >= self.test[1]:
|
|
break
|
|
url = prev_page_url
|
|
current_articles.reverse()
|
|
return current_articles
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', src=True):
|
|
if img['src'].startswith('/'):
|
|
img['src'] = 'https://arcamax.com' + img['src']
|
|
return soup
|
|
|
|
extra_css = '''
|
|
img { display:block; margin:0 auto; }
|
|
'''
|