mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
80 lines
3.4 KiB
Plaintext
80 lines
3.4 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import re
|
|
from calibre.utils.magick import Image, create_canvas
|
|
|
|
|
|
class AdvancedUserRecipe1307556816(BasicNewsRecipe):
|
|
title = u'Geek and Poke'
|
|
__author__ = u'DrMerry'
|
|
description = u'Geek and Poke Cartoons'
|
|
publisher = u'Oliver Widder'
|
|
author = u'Oliver Widder, DrMerry (calibre-code), calibre'
|
|
oldest_article = 31
|
|
max_articles_per_feed = 100
|
|
language = u'en'
|
|
simultaneous_downloads = 1
|
|
timefmt = ' [%a, %d %B, %Y]'
|
|
summary_length = -1
|
|
no_stylesheets = True
|
|
category = 'News.IT, Cartoon, Humor, Geek'
|
|
use_embedded_content = False
|
|
cover_url = 'http://geekandpoke.typepad.com/aboutcoders.jpeg'
|
|
remove_javascript = True
|
|
remove_empty_feeds = True
|
|
publication_type = 'blog'
|
|
masthead_url = None
|
|
conversion_options = {
|
|
'comments': '', 'tags': category, 'language': language, 'publisher': publisher, 'author': author
|
|
}
|
|
|
|
remove_tags_before = dict(name='p', attrs={'class': 'content-nav'})
|
|
remove_tags_after = dict(name='div', attrs={'class': 'entry-content'})
|
|
remove_tags = [dict(name='div', attrs={'class': 'entry-footer'}),
|
|
dict(name='div', attrs={'id': 'alpha'}),
|
|
dict(name='div', attrs={'id': 'gamma'}),
|
|
dict(name='iframe'),
|
|
dict(name='p', attrs={'class': 'content-nav'})]
|
|
|
|
filter_regexps = [(r'feedburner\.com'),
|
|
(r'pixel.quantserve\.com'),
|
|
(r'googlesyndication\.com'),
|
|
(r'yimg\.com'),
|
|
(r'scorecardresearch\.com')]
|
|
|
|
preprocess_regexps = [
|
|
(re.compile(r'(<p>( |\s)*</p>|<a[^>]*>Tweet</a>|<a[^>]*>|</a>|<!--.*?-->|<h2[^>]*>[^<]*</h2>[^<]*)', re.DOTALL | re.IGNORECASE), lambda match: ''),
|
|
(re.compile(r'( |\s\s)+\s*', re.DOTALL |
|
|
re.IGNORECASE), lambda match: ' '),
|
|
(re.compile(r'(<h3[^>]*>)<a[^>]>((?!</a)*)</a></h3>', re.DOTALL |
|
|
re.IGNORECASE), lambda match: match.group(1) + match.group(2) + '</h3>'),
|
|
(re.compile(r'(<img[^>]*alt="([^"]*)"[^>]*>)', re.DOTALL | re.IGNORECASE),
|
|
lambda match: '<div id="merryImage"><cite>' + match.group(2) + '</cite><br>' + match.group(1) + '</div>'),
|
|
(re.compile(r'<br( /)?>(<br( /)?>)+', re.DOTALL |
|
|
re.IGNORECASE), lambda match: '<br>'),
|
|
]
|
|
|
|
extra_css = 'body, h3, p, div, span{margin:0px; padding:0px} h3.entry-header{font-size: 0.8em} div.entry-body{font-size: 0.7em}'
|
|
|
|
def postprocess_html(self, soup, first):
|
|
for tag in soup.findAll('img', src=True):
|
|
iurl = tag['src']
|
|
img = Image()
|
|
img.open(iurl)
|
|
# print '***img is: ', iurl, '\n****width is: ', width, 'height is:
|
|
# ', height
|
|
img.trim(0)
|
|
# print '***TRIMMED img width is: ', width, 'height is: ', height
|
|
left = 0
|
|
top = 0
|
|
border_color = '#ffffff'
|
|
width, height = img.size
|
|
# print '***retrieved img width is: ', width, 'height is: ', height
|
|
height_correction = 1.17
|
|
canvas = create_canvas(
|
|
width, height * height_correction, border_color)
|
|
canvas.compose(img, left, top)
|
|
canvas.save(iurl)
|
|
return soup
|
|
|
|
feeds = ['http://feeds.feedburner.com/GeekAndPoke?format=xml']
|