#!/usr/bin/env python import json from datetime import datetime, timedelta from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.web.feeds.news import BasicNewsRecipe class GoComics(BasicNewsRecipe): title = 'Go Comics' __author__ = 'unkn0wn' description = ( 'The best and funniest cartoons you loved then and now—all in one place!' ) oldest_article = 2 language = 'en' remove_empty_feeds = True masthead_url = 'https://auth.amuniversal.com/development-assets/go-comics/images/logo-horizontal.svg' cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/7/78/GoComics_logo.jpg/960px-GoComics_logo.jpg' simultaneous_downloads = 1 recipe_specific_options = { 'coverurl': { 'short': 'Cover URL', 'long': 'URL of an image to be used as book cover', 'default': 'https://upload.wikimedia.org/wikipedia/commons/thumb/7/78/GoComics_logo.jpg/960px-GoComics_logo.jpg' }, 'mastheadurl': { 'short': 'Masthead URL', 'long': 'URL of an image to be used as masthead', 'default': 'https://upload.wikimedia.org/wikipedia/commons/thumb/7/78/GoComics_logo.jpg/960px-GoComics_logo.jpg' }, 'comics': { 'short': 'enter the slugs of the url\nof the comics you want seperated by a space', 'long': 'calvinandhobbes garfield animalcrackers the-born-loser ... ...', 'default': 'calvinandhobbes garfield animalcrackers pearlsbeforeswine bc peanuts', }, 'days': { 'short': 'Oldest article to download from this news source. In days ', 'long': 'For example, 3, gives you comics from past 3 days', 'default': str(oldest_article), }, 'res': { 'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 2400', 'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.', 'default': '1000', }, 'rev': { 'short': 'Reverse the order of articles in each feed?', 'long': 'enter yes', 'default': 'no', }, } def __init__(self, *args, **kwargs): BasicNewsRecipe.__init__(self, *args, **kwargs) r = self.recipe_specific_options.get('rev') if r and isinstance(r, str): if r.lower().strip() == 'yes': self.reverse_article_order = True r = self.recipe_specific_options.get('coverurl') if r and isinstance(r, str): self.cover_url=r r = self.recipe_specific_options.get('mastheadurl') if r and isinstance(r, str): self.masthead_url=r def parse_index(self): d = self.recipe_specific_options.get('days') if d and isinstance(d, str): self.oldest_article = int(d) dates = [ (datetime.now() - timedelta(days=i)).strftime('%Y/%m/%d') for i in range(self.oldest_article) ] u = self.recipe_specific_options.get('comics') if u and isinstance(u, str): coms = u.split() feeds = [] for x in coms: section = x.upper() self.log(section) articles = [] for day in dates: title = section + ' | ' + day url = 'https://www.gocomics.com/' + x + '/' + day self.log('\t', title, '\n\t\t', url) articles.append({'title': title, 'url': url}) if articles: feeds.append((section, articles)) return feeds def preprocess_raw_html(self, raw, *a): width = '1000' w = self.recipe_specific_options.get('res') if w and isinstance(w, str): width = w soup = BeautifulSoup(raw) div = soup.find( attrs={ 'class': lambda x: x and x.startswith('ShowComicViewer_showComicViewer__comic') } ) script = div.find('script', attrs={'type': 'application/ld+json'}) data = json.loads(self.tag_to_string(script)) title = '

' + data['name'] + '

' auth = '

' + data['description'] + '

' img = ''.format( data['contentUrl'] + '?optimizer=image&width=' + width + '&quality=85' ) return '' + title + img + auth + '' def populate_article_metadata(self, article, soup, first): article.title = self.tag_to_string(soup.find('h1')) article.summary = article.text_summary = self.tag_to_string(soup.find('p'))