| 1 |
#!/usr/bin/env python |
| 2 |
import json |
| 3 |
from datetime import datetime, timedelta |
| 4 |
|
| 5 |
from calibre.ebooks.BeautifulSoup import BeautifulSoup |
| 6 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 7 |
|
| 8 |
|
| 9 |
class GoComics(BasicNewsRecipe): |
| 10 |
title = 'Go Comics' |
| 11 |
__author__ = 'unkn0wn' |
| 12 |
description = 'The best and funniest cartoons you loved then and now—all in one place!' |
| 13 |
oldest_article = 2 |
| 14 |
language = 'en' |
| 15 |
remove_empty_feeds = True |
| 16 |
masthead_url = 'https://auth.amuniversal.com/development-assets/go-comics/images/logo-horizontal.svg' |
| 17 |
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/7/78/GoComics_logo.jpg/960px-GoComics_logo.jpg' |
| 18 |
simultaneous_downloads = 1 |
| 19 |
|
| 20 |
recipe_specific_options = { |
| 21 |
'coverurl': { |
| 22 |
'short': 'Cover URL', |
| 23 |
'long': 'URL of an image to be used as book cover', |
| 24 |
'default': 'https://upload.wikimedia.org/wikipedia/commons/thumb/7/78/GoComics_logo.jpg/960px-GoComics_logo.jpg', |
| 25 |
}, |
| 26 |
'mastheadurl': { |
| 27 |
'short': 'Masthead URL', |
| 28 |
'long': 'URL of an image to be used as masthead', |
| 29 |
'default': 'https://upload.wikimedia.org/wikipedia/commons/thumb/7/78/GoComics_logo.jpg/960px-GoComics_logo.jpg', |
| 30 |
}, |
| 31 |
'comics': { |
| 32 |
'short': 'enter the slugs of the url\nof the comics you want seperated by a space', |
| 33 |
'long': 'calvinandhobbes garfield animalcrackers the-born-loser ... ...', |
| 34 |
'default': 'calvinandhobbes garfield animalcrackers pearlsbeforeswine bc peanuts', |
| 35 |
}, |
| 36 |
'days': { |
| 37 |
'short': 'Oldest article to download from this news source. In days ', |
| 38 |
'long': 'For example, 3, gives you comics from past 3 days', |
| 39 |
'default': str(oldest_article), |
| 40 |
}, |
| 41 |
'res': { |
| 42 |
'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 2400', |
| 43 |
'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.', |
| 44 |
'default': '1000', |
| 45 |
}, |
| 46 |
'rev': { |
| 47 |
'short': 'Reverse the order of articles in each feed?', |
| 48 |
'long': 'enter yes', |
| 49 |
'default': 'no', |
| 50 |
}, |
| 51 |
} |
| 52 |
|
| 53 |
def __init__(self, *args, **kwargs): |
| 54 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 55 |
r = self.recipe_specific_options.get('rev') |
| 56 |
if r and isinstance(r, str): |
| 57 |
if r.lower().strip() == 'yes': |
| 58 |
self.reverse_article_order = True |
| 59 |
r = self.recipe_specific_options.get('coverurl') |
| 60 |
if r and isinstance(r, str): |
| 61 |
self.cover_url = r |
| 62 |
r = self.recipe_specific_options.get('mastheadurl') |
| 63 |
if r and isinstance(r, str): |
| 64 |
self.masthead_url = r |
| 65 |
|
| 66 |
def parse_index(self): |
| 67 |
d = self.recipe_specific_options.get('days') |
| 68 |
if d and isinstance(d, str): |
| 69 |
self.oldest_article = int(d) |
| 70 |
|
| 71 |
dates = [(datetime.now() - timedelta(days=i)).strftime('%Y/%m/%d') for i in range(self.oldest_article)] |
| 72 |
|
| 73 |
u = self.recipe_specific_options.get('comics') |
| 74 |
if u and isinstance(u, str): |
| 75 |
coms = u.split() |
| 76 |
|
| 77 |
feeds = [] |
| 78 |
|
| 79 |
for x in coms: |
| 80 |
section = x.upper() |
| 81 |
self.log(section) |
| 82 |
articles = [] |
| 83 |
for day in dates: |
| 84 |
title = section + ' | ' + day |
| 85 |
url = 'https://www.gocomics.com/' + x + '/' + day |
| 86 |
self.log('\t', title, '\n\t\t', url) |
| 87 |
articles.append({'title': title, 'url': url}) |
| 88 |
if articles: |
| 89 |
feeds.append((section, articles)) |
| 90 |
return feeds |
| 91 |
|
| 92 |
def preprocess_raw_html(self, raw, *a): |
| 93 |
width = '1000' |
| 94 |
w = self.recipe_specific_options.get('res') |
| 95 |
if w and isinstance(w, str): |
| 96 |
width = w |
| 97 |
soup = BeautifulSoup(raw) |
| 98 |
div = soup.find(attrs={'class': lambda x: x and x.startswith('ShowComicViewer_showComicViewer__comic')}) |
| 99 |
script = div.find('script', attrs={'type': 'application/ld+json'}) |
| 100 |
data = json.loads(self.tag_to_string(script)) |
| 101 |
title = '<h1>' + data['name'] + '</h1>' |
| 102 |
auth = '<p style="font-size: small;">' + data['description'] + '</p>' |
| 103 |
img = '<img src={}>'.format(data['contentUrl'] + '?optimizer=image&width=' + width + '&quality=85') |
| 104 |
return '<html><body>' + title + img + auth + '</body></html>' |
| 105 |
|
| 106 |
def populate_article_metadata(self, article, soup, first): |
| 107 |
article.title = self.tag_to_string(soup.find('h1')) |
| 108 |
article.summary = article.text_summary = self.tag_to_string(soup.find('p')) |