calibre/recipes/galaxys_edge.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

66 lines
2.5 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import absolute_import, division, print_function, unicode_literals
import re
import shutil
try:
from urllib.parse import urlencode
except ImportError:
from urllib import urlencode
from calibre.ptempfile import PersistentTemporaryDirectory, PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1515196393(BasicNewsRecipe):
title = "The Galaxy's Edge"
__author__ = 'andyh2000'
delay = 2
oldest_article = 7
max_articles_per_feed = 100
auto_cleanup = True
language = 'en'
encoding = 'utf8'
no_stylesheets = True
extra_css = '.photo-caption { font-size: smaller }'
def parse_index(self):
soup = self.index_to_soup('http://www.galaxysedge.com/')
cover_image = soup.find('div', attrs={'class':'ci-img'})
cover_image = cover_image.find('img')
self.cover_url = cover_image['src']
issue_title = soup.find('h1')
self.title = "Galaxy's Edge: " + self.tag_to_string(issue_title).lower().title()
toc = soup.find('div', attrs={'class':'nav-tabs'})
current_section = "Articles"
current_articles = []
feeds = []
br = self.get_browser()
self.ctdir = PersistentTemporaryDirectory()
for x in toc.findAll(['li'], attrs={"class": re.compile(".*get_content.*")}):
edwo = x.find('a')
title = self.tag_to_string(edwo)
self.log('\t\tFound article:', title)
post_id = x["data-post-id"]
cat_id = x["data-cat-id"]
parent_id = x["data-parent-id"]
self.log('\t\tdata-parent-id', parent_id)
self.log('\t\tdata-cat-id', cat_id)
self.log('\t\tdata-post-id', post_id)
data = urlencode({'action':'get_content', 'cat_id':cat_id, 'parent_id':parent_id, 'post_id':post_id})
r=br.open('http://www.galaxysedge.com/wp-content/themes/galaxyedge/get_content.php', data)
content_file = PersistentTemporaryFile(suffix='.html', dir=self.ctdir)
content_file.write(r.read())
content_file.close()
current_articles.append({'title': title, 'url':'file://' + content_file.name, 'description':'', 'date':''})
if current_articles and current_section:
feeds.append((current_section, current_articles))
return feeds
def cleanup(self):
self.log("Deleting temp files...")
shutil.rmtree(self.ctdir)