def handle_latest_episode_intent(self, message):
utter = message.data['utterance']
podcast_names = [
self.settings["nameone"], self.settings["nametwo"],
self.settings["namethree"]
]
podcast_urls = [
self.settings["feedone"], self.settings["feedtwo"],
self.settings["feedthree"]
]
#check if the user specified a podcast to check for a new podcast
for i in range(0, len(podcast_names)):
#skip if podcast slot left empty
if podcast_names[i] == "":
continue
elif podcast_names[i].lower() in utter.lower():
parsed_feed = pp.parse(podcast_urls[i],
urllib.urlopen(podcast_urls[i]))
last_episode = (parsed_feed['episodes'][0]['title'])
speech_string = "The latest episode of " + podcast_names[
i] + " is " + last_episode
self.speak(speech_string)
return True
#if no podcast names are provided, list all new episodes
new_episodes = []
for i in range(0, len(podcast_urls)):
if not podcast_urls[i]:
continue
parsed_feed = pp.parse(podcast_urls[i],
urllib.urlopen(podcast_urls[i]))
last_episode = (parsed_feed['episodes'][0]['title'])
new_episodes.append(last_episode)
speech_string = "The latest episodes are the following: "
for i in range(0, len(new_episodes)):
#if the podcast is the last in a list add "and" before the podcast name
if i == (len(new_episodes) - 1) and i > 0:
speech_string = speech_string + "and " + podcast_names[
i] + ": " + new_episodes[i]
else:
speech_string = speech_string + podcast_names[
i] + ": " + new_episodes[i] + ", "
self.speak(speech_string)
def CPS_start(self, phrase, data):
self.log.info("CPS_start phrase: {} data: {}".format(phrase, data))
tracklist = []
parsed_feed = pp.parse(data, urllib.request.urlopen(Request(data,
data=None, headers={'User-Agent': self.user_agent}))
)
episode_title = (parsed_feed['episodes'][0]['title'])
# try and parse the rss feed, some are incompatible
try:
episode = (parsed_feed["episodes"][0]["enclosures"][0]["url"])
except:
self.speak_dialog('badrss')
# check for any redirects
episode = urllib.request.urlopen(Request(episode, data=None, headers={'User-Agent': self.user_agent}))
redirected_episode = episode.geturl()
http_episode = re.sub('https', 'http', redirected_episode)
self.log.info("http_episode: {}".format(http_episode))
tracklist.append(http_episode)
if self.state in ['playing', 'paused']:
self.mediaplayer.stop()
self.mediaplayer.clear_list()
self.mediaplayer.add_list(tracklist)
# self.speak(self._get_play_message(data))
self.mediaplayer.play()
self.state = 'playing'
def main():
"""Playing media."""
parser = argparse.ArgumentParser(
description="This script play a given media on the mpd (local) server")
parser.add_argument(
"-c",
choices=['play', 'stop', 'status', 'volup', 'voldown', 'pod'],
required=True)
parser.add_argument("-u", help="url to play")
args = parser.parse_args()
media = args.u
command = args.c
myplayer = player()
if command == 'play':
if media is not None:
myplayer.play(media)
else:
print "You must enter a media url/path to play"
elif command == 'stop':
myplayer.stop()
elif command == 'volup':
myplayer.volup()
elif command == 'voldown':
myplayer.voldown()
elif command == 'status':
state = myplayer.status()
for cle, val in state.items():
print cle + " : " + val
elif command == 'podlist':
parsed = podcastparser.parse(media, urllib.urlopen(media))
pprint.pprint(parsed)
def run():
try:
for podcast in self.data["podcasts"]:
raw = urlopen(
podcast["feed_url"],
timeout=self._podcast_timeout,
context=ssl.create_default_context(
cafile=certifi.where()),
)
parsed = podcastparser.parse(podcast["feed_url"], raw)
episodes = parsed["episodes"]
podcast["episodes"] = []
for episode in episodes:
title = episode["title"]
media_url = episode["enclosures"][0]["url"]
# podcast['episodes'].append({"title":unicodedata.normalize('NFKD', title).encode('ascii','ignore'), "url":media_url})
podcast["episodes"].append({
"title": title,
"url": media_url
})
self.save()
logger.info(
"Transistor Library: done downloading podcasts infos")
except Exception as e:
logger.error(
"Transistor: Can't retrieve podcast data: {}".format(
str(e)))
def _handle_paged_feed(self, max_episodes):
page = 2
remaining_episodes = max_episodes - len(self.parsed['episodes'])
while ('paged_feed_next' in self.parsed and
page < self.PAGED_FEED_MAX_PAGES and
remaining_episodes > 0):
# Take the next page from the paged feed
url = self.parsed['paged_feed_next']
del self.parsed['paged_feed_next']
if not url:
break
try:
logger.debug('Downloading page %d from %s', page, url)
stream = util.urlopen(url)
parsed = podcastparser.parse(url, stream, remaining_episodes)
added_episodes = len(parsed['episodes'])
remaining_episodes -= added_episodes
logger.debug('Page %d contains %d additional episodes', page,
added_episodes)
self.parsed['episodes'].extend(parsed['episodes'])
# Next iteration if we still have a next page
if 'paged_feed_next' in parsed:
self.parsed['paged_feed_next'] = parsed['paged_feed_next']
except Exception as e:
logger.warn('Error while fetching feed page %d from %s: %s', page, url, e)
# Give up, don't try to download additional pages here
break
page += 1
def refresh():
for rss in rss_links:
parsed = podcastparser.parse(rss, urllib.request.urlopen(rss), 20)
title = parsed.get('title')
description = remove_html(parsed.get('description'))
image = parsed.get('cover_url')
link = parsed.get('link')
podcast = Podcast.query.filter_by(link=parsed.get('link')).first()
if(podcast is None):
podcast = Podcast(title=title, description=description, image=image, link=link)
db.session.add(podcast)
db.session.commit()
for episode in parsed.get('episodes'):
episode_title = episode.get('title')
episode_link = episode.get('link')
episode_audio_url = episode.get('enclosures')[0]['url']
episode_time_published = episode.get('published')
episode_length = episode.get('total_time')
episode_podcast = podcast
episode = Episode.query.filter_by(audio_url=episode_audio_url).first()
if(episode is None):
episode = Episode(title=episode_title,
link=episode_link,
audio_url=episode_audio_url,
time_published=episode_time_published,
length=episode_length,
podcast=episode_podcast)
db.session.add(episode)
db.session.commit()
def __init__(self, channel, max_episodes):
url = channel.authenticate_url(channel.url)
logger.info('Parsing via podcastparser: %s', url)
headers = {}
if channel.http_etag:
headers['If-None-Match'] = channel.http_etag
if channel.http_last_modified:
headers['If-Modified-Since'] = channel.http_last_modified
try:
stream = util.urlopen(url, headers)
self.status = 200
info = stream.info()
self.etag = info.get('etag')
self.modified = info.get('last-modified')
self.parsed = podcastparser.parse(url, stream, max_episodes)
self._handle_paged_feed(max_episodes)
except urllib.error.HTTPError as error:
self.status = error.code
if error.code == 304:
logger.info('Not modified')
else:
logger.warn('Feed update failed: %s', error)
raise error
self.etag = None
self.modified = None
self.parsed = None
def _handle_paged_feed(self, max_episodes):
page = 2
remaining_episodes = max_episodes - len(self.parsed['episodes'])
while ('paged_feed_next' in self.parsed
and page < self.PAGED_FEED_MAX_PAGES
and remaining_episodes > 0):
# Take the next page from the paged feed
url = self.parsed['paged_feed_next']
del self.parsed['paged_feed_next']
if not url:
break
try:
logger.debug('Downloading page %d from %s', page, url)
stream = util.urlopen(url)
parsed = podcastparser.parse(url, stream, remaining_episodes)
added_episodes = len(parsed['episodes'])
remaining_episodes -= added_episodes
logger.debug('Page %d contains %d additional episodes', page,
added_episodes)
self.parsed['episodes'].extend(parsed['episodes'])
# Next iteration if we still have a next page
if 'paged_feed_next' in parsed:
self.parsed['paged_feed_next'] = parsed['paged_feed_next']
except Exception as e:
logger.warn('Error while fetching feed page %d from %s: %s',
page, url, e)
# Give up, don't try to download additional pages here
break
page += 1
def main():
"""Playing media."""
parser = argparse.ArgumentParser(
description="This script play a given media on the mpd (local) server")
parser.add_argument("-c",
choices=['play', 'stop', 'status', 'volup', 'voldown', 'pod'],
required=True)
parser.add_argument("-u", help="url to play")
args = parser.parse_args()
media = args.u
command = args.c
myplayer = player()
if command == 'play':
if media is not None:
myplayer.play(media)
else:
print "You must enter a media url/path to play"
elif command == 'stop':
myplayer.stop()
elif command == 'volup':
myplayer.volup()
elif command == 'voldown':
myplayer.voldown()
elif command == 'status':
state = myplayer.status()
for cle, val in state.items():
print cle + " : " + val
elif command == 'podlist':
parsed = podcastparser.parse(media, urllib.urlopen(media))
pprint.pprint(parsed)
def update_using_feedservice(urls):
import podcastparser
from urllib.request import urlopen
podcasts = []
for url in urls:
feed = podcastparser.parse(url, urlopen(url), 5)
if feed is None:
_LOGGER.info("Feed not updated: %s", url)
continue
# Handle permanent redirects
if feed.get("new_location", False):
new_url = feed["new_location"]
_LOGGER.info("Redirect %s => %s", url, new_url)
url = new_url
# Error handling
if feed.get("errors", False):
_LOGGER.error("Error parsing feed: %s", repr(feed["errors"]))
continue
# Update per-podcast metadata
podcast = {
"title": feed.get("title", ""),
"link": feed.get("link", url),
"description": feed.get("description", ""),
"cover_url": feed.get("logo", ""),
"episodes": [parse_entry(entry) for entry in feed["episodes"]],
}
podcasts.append(podcast)
return podcasts
def parse_feed(event, context):
feedurl = event['queryStringParameters']['feedUrl']
parsed = podcastparser.parse(feedurl, urllib.request.urlopen(feedurl))
body = {
'title': parsed['title'],
'link': parsed['link'],
'description': parsed['description'],
'episodes': [ {
'title': e['title'],
'description': e['description'],
'published': e['published'],
'mediaUrl': e['enclosures'][0]['url']
} for e in parsed['episodes'] ]
}
response = {
'statusCode': 200,
'headers': {
'Access-Control-Allow-Origin': '*',
'Content-Type': 'application/json'
},
'body': json.dumps(body),
'isBase64Encoded': False
}
return response
def __init__(self, channel, max_episodes):
url = channel.authenticate_url(channel.url)
logger.info('Parsing via podcastparser: %s', url)
headers = {}
if channel.http_etag:
headers['If-None-Match'] = channel.http_etag
if channel.http_last_modified:
headers['If-Modified-Since'] = channel.http_last_modified
try:
stream = util.urlopen(url, headers)
self.status = 200
info = stream.info()
self.etag = info.get('etag')
self.modified = info.get('last-modified')
self.parsed = podcastparser.parse(url, stream, max_episodes)
except urllib.error.HTTPError as error:
self.status = error.code
if error.code == 304:
logger.info('Not modified')
else:
logger.warn('Feed update failed: %s', error)
raise error
self.etag = None
self.modified = None
self.parsed = None
def __init__(self, link):
super().__init__()
feed = podcastparser.parse(link, urlopen(link))
self.title = feed['title']
for item in feed['episodes']:
self.items.append(PodcastArticle(item['title'], item['description'], item['link'], date.fromtimestamp(item['published'])))
self.items.reverse()
def fetch_episodes(url):
parsed = podcastparser.parse(url, urlopen(url))
#print(parsed)
new = [dict(title=episode['title'], pub=episode['published'], \
duration=str(datetime.timedelta(seconds = episode['total_time'])), \
description=episode['description'], uri_link=episode['enclosures'][0]['url']) for episode in parsed['episodes']]
return new
def fetch_feed_title():
if request.method == 'POST':
posted_data = json.loads(json.dumps(request.json))
url = posted_data['url']
parsed = podcastparser.parse(url, urlopen(url))
json_data = [{ "title": parsed['title'] }]
return json.dumps(json_data)
def __init__(self, url):
self.url = url
# get the 5 last episodes from podcast at url (podcastparser sorts by published date)
self.pc = podcastparser.parse(self.url,
stream=urllib.urlopen(self.url),
max_episodes=5)
self.episodes = []
def _parse_feed(self, url, etag, modified, autodiscovery=True):
headers = {}
if modified is not None:
headers['If-Modified-Since'] = modified
if etag is not None:
headers['If-None-Match'] = etag
if url.startswith('file://'):
is_local = True
url = url[len('file://'):]
stream = open(url)
else:
is_local = False
try:
stream = util.urlopen(url, headers)
except HTTPError as e:
return self._check_statuscode(e, e.geturl())
data = stream
if autodiscovery and not is_local and stream.headers.get(
'content-type', '').startswith('text/html'):
# Not very robust attempt to detect encoding: http://stackoverflow.com/a/1495675/1072626
charset = stream.headers.get_param('charset')
if charset is None:
charset = 'utf-8' # utf-8 appears hard-coded elsewhere in this codebase
# We use StringIO in case the stream needs to be read again
data = StringIO(stream.read().decode(charset))
ad = FeedAutodiscovery(url)
ad.feed(data.getvalue())
if ad._resolved_url:
try:
self._parse_feed(ad._resolved_url, None, None, False)
return Result(NEW_LOCATION, ad._resolved_url)
except Exception as e:
logger.warn('Feed autodiscovery failed', exc_info=True)
# Second, try to resolve the URL
url = self._resolve_url(url)
if url:
return Result(NEW_LOCATION, url)
# Reset the stream so podcastparser can give it a go
data.seek(0)
try:
feed = podcastparser.parse(url, data)
except ValueError as e:
raise InvalidFeed('Could not parse feed: {msg}'.format(msg=e))
if is_local:
feed['headers'] = {}
return Result(UPDATED_FEED, feed)
else:
feed['headers'] = stream.headers
return self._check_statuscode(stream, feed)
def parseFeed(url):
"""
docstring
"""
with urlopen(url) as response:
try:
return podcastparser.parse(url, response)
except podcastparser.FeedParseError:
return False
def _parse_feed(self, url, etag, modified, autodiscovery=True):
headers = {}
if modified is not None:
headers['If-Modified-Since'] = modified
if etag is not None:
headers['If-None-Match'] = etag
if url.startswith('file://'):
is_local = True
url = url[len('file://'):]
stream = open(url)
else:
is_local = False
try:
stream = util.urlopen(url, headers)
except HTTPError as e:
return self._check_statuscode(e, e.geturl())
data = stream
if autodiscovery and not is_local and stream.headers.get('content-type', '').startswith('text/html'):
# Not very robust attempt to detect encoding: http://stackoverflow.com/a/1495675/1072626
charset = stream.headers.get_param('charset')
if charset is None:
charset = 'utf-8' # utf-8 appears hard-coded elsewhere in this codebase
# We use StringIO in case the stream needs to be read again
data = StringIO(stream.read().decode(charset))
ad = FeedAutodiscovery(url)
ad.feed(data.getvalue())
if ad._resolved_url:
try:
self._parse_feed(ad._resolved_url, None, None, False)
return Result(NEW_LOCATION, ad._resolved_url)
except Exception as e:
logger.warn('Feed autodiscovery failed', exc_info=True)
# Second, try to resolve the URL
url = self._resolve_url(url)
if url:
return Result(NEW_LOCATION, url)
# Reset the stream so podcastparser can give it a go
data.seek(0)
try:
feed = podcastparser.parse(url, data)
except ValueError as e:
raise InvalidFeed('Could not parse feed: {msg}'.format(msg=e))
if is_local:
feed['headers'] = {}
return Result(UPDATED_FEED, feed)
else:
feed['headers'] = stream.headers
return self._check_statuscode(stream, feed)
def play():
feedurl = 'http://feeds.lds.org/ScriptureStories'
parsed = podcastparser.parse(feedurl, urllib.request.urlopen(feedurl))
episode = random.choice(parsed['episodes'])
url = episode['enclosures'][0]['url']
url = requests.get(url, allow_redirects=False).headers['location']
url = url.replace('http', 'https')
speech = f"Playing Scripture Story {episode['title']}"
_infodump(f"{speech} ({url})")
return audio(speech).play(url) #, offset=93000)
def test_find_episode(self):
feed_url = "https://feeds.megaphone.fm/theweeds"
podcast = podcastparser.parse(feed_url,
path.join(here, "data", "theweeds.rss"))
title = "The reparations primary"
stream_url = "https://traffic.megaphone.fm/VMP2975209749.mp3"
item = utils.find_episode(podcast["episodes"], title, stream_url)
self.assertEqual(item["guid"], "9aa25a44-ff17-11e8-89e8-dbfe1fc6a68f")
self.assertEqual(item["total_time"], 3466)
self.assertEqual(item["published"], 1553022019)
def handle_latest_episode_intent(self, message):
utter = message.data['utterance']
self.enclosure.mouth_think()
podcast_names = [self.settings["nameone"], self.settings["nametwo"], self.settings["namethree"]]
podcast_urls = [self.settings["feedone"], self.settings["feedtwo"], self.settings["feedthree"]]
#check if the user specified a podcast to check for a new podcast
for index, name in enumerate(podcast_names):
#skip if podcast slot left empty
if not name:
continue
if name.lower() in utter.lower():
parsed_feed = pp.parse(podcast_urls[index],
urllib.urlopen(podcast_urls[index]))
last_episode = (parsed_feed['episodes'][0]['title'])
speech_string = "The latest episode of " + name + " is " + last_episode
break
else:
#if no podcast names are provided, list all new episodes
new_episodes = []
for index, url in enumerate(podcast_urls):
#skip if url slot left empty
if not url:
continue
parsed_feed = pp.parse(podcast_urls[index],
urllib.urlopen(podcast_urls[index]))
last_episode = (parsed_feed['episodes'][0]['title'])
new_episodes.append(last_episode)
#skip if i[0] slot left empty
elements = [": ".join(i) for i in zip(podcast_names, new_episodes) if i[0]]
speech_string = "The latest episodes are the following: "
speech_string += ", ".join(elements[:-2] + [" and ".join(elements[-2:])])
self.speak(speech_string)
def main():
console.clear()
url = None
if appex.is_running_extension():
url = appex.get_url()
elif len(sys.argv) > 1:
url = unquote(sys.argv[1])
if url is None:
print("No URL found")
webbrowser.open("overcast://")
return
console.show_activity()
print(url)
parser = OvercastParser()
reminders = Reminders()
data = requests.get(url).text
parser.feed(data)
(itunes_id, stream_url, overcast_id, title) = parser.close()
print(title)
feed_url = extract_feed_id(itunes_id)
print(feed_url)
podcast = podcastparser.parse(feed_url, urllib.request.urlopen(feed_url))
print(podcast["link"])
item = utils.find_episode(podcast["episodes"], title, stream_url)
print(item)
result = {
"title": title,
"itunes_channel_id": itunes_id,
"enclosure_url": stream_url,
"overcast_id": overcast_id,
"guid": item["guid"],
"channel_link": podcast["link"],
"duration": item["total_time"],
"published_time": item["published"],
}
reminders.add(json.dumps(result))
print("Added to reminders")
console.hide_activity()
webbrowser.open("overcast://")
def test_parse_rss(rss_filename):
basename, _ = os.path.splitext(rss_filename)
json_filename = basename + '.json'
# read parameters to podcastparser.parse() from a separate file
param_filename = basename + '.param.json'
params = {}
if os.path.exists(param_filename):
params = json.load(open(param_filename))
expected = json.load(open(json_filename))
parsed = podcastparser.parse('file://' + rss_filename,
open(rss_filename), **params)
assert_equal(expected, parsed)
def parseFeed(url):
"""
docstring
"""
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
with urlopen(req) as response:
try:
return podcastparser.parse(url, response)
except podcastparser.FeedParseError:
return False
except HTTPError:
return False
except URLError:
return False
def test_parse_rss(rss_filename):
basename, _ = os.path.splitext(rss_filename)
json_filename = basename + '.json'
# read parameters to podcastparser.parse() from a separate file
param_filename = basename + '.param.json'
params = {}
if os.path.exists(param_filename):
params = json.load(open(param_filename))
expected = json.load(open(json_filename))
parsed = podcastparser.parse('file://' + rss_filename,
open(rss_filename), **params)
assert_equal.__self__.maxDiff = None
assert_equal(expected, parsed)
def parse(url, max_episodes=0):
with getfile(url) as file:
parsed = podcastparser.parse(url, file, max_episodes)
podcast = podcast_ripper.Podcast(parsed.get('title', 'Unknown'),
parsed.get('link', ''),
parsed.get('description', ''))
for episode in parsed['episodes']:
if len(episode['enclosures']) > 0:
episode = podcast_ripper.Episode(
episode['title'], episode['published'],
episode['enclosures'][0]['url'])
podcast.episodes.append(episode)
return podcast
def _parse_feed(self, url, etag, modified, autodiscovery=True):
headers = {}
if modified is not None:
headers['If-Modified-Since'] = modified
if etag is not None:
headers['If-None-Match'] = etag
if url.startswith('file://'):
is_local = True
url = url[len('file://'):]
stream = open(url)
else:
is_local = False
try:
stream = util.urlopen(url, headers)
except HTTPError as e:
return self._check_statuscode(e, e.geturl())
if not is_local and stream.headers.get('content-type',
'').startswith('text/html'):
if autodiscovery:
ad = FeedAutodiscovery(url)
ad.feed(stream.read())
if ad._resolved_url:
try:
self._parse_feed(ad._resolved_url, None, None, False)
return Result(NEW_LOCATION, ad._resolved_url)
except Exception as e:
logger.warn('Feed autodiscovery failed', exc_info=True)
# Second, try to resolve the URL
url = self._resolve_url(url)
if url:
return Result(NEW_LOCATION, url)
raise InvalidFeed('Got HTML document instead')
feed = podcastparser.parse(url, stream)
if is_local:
feed['headers'] = {}
return Result(UPDATED_FEED, feed)
else:
feed['headers'] = stream.headers
return self._check_statuscode(stream, feed)
def test_parse_rss(rss_filename):
basename, _ = os.path.splitext(rss_filename)
json_filename = basename + '.json'
# read parameters to podcastparser.parse() from a separate file
param_filename = basename + '.param.json'
params = {}
if os.path.exists(param_filename):
params = json.load(open(param_filename))
expected = json.load(open(json_filename))
normalized_rss_filename = rss_filename
if os.sep == '\\':
normalized_rss_filename = normalized_rss_filename.replace(os.sep, '/')
parsed = podcastparser.parse('file://' + normalized_rss_filename,
open(rss_filename), **params)
assert_equal.__self__.maxDiff = None
assert_equal(expected, parsed)
def test_parse_rss(self, rss_filename):
basename, _ = os.path.splitext(rss_filename)
json_filename = basename + '.json'
# read parameters to podcastparser.parse() from a separate file
param_filename = basename + '.param.json'
params = {}
if os.path.exists(param_filename):
params = json.load(open(param_filename))
expected = json.load(open(json_filename))
normalized_rss_filename = rss_filename
if os.sep == '\\':
normalized_rss_filename = normalized_rss_filename.replace(
os.sep, '/')
parsed = podcastparser.parse('file://' + normalized_rss_filename,
open(rss_filename), **params)
assert expected == parsed
def parse(feedurl, count, root, override, managed):
feed = podcastparser.parse(feedurl, urllib.request.urlopen(feedurl))
for _, cast in zip(range(count), feed['episodes']):
for item in cast['enclosures']:
extension = os.path.splitext(item['url'])[1]
if managed:
directory = root + '/' + feed['title']
if not os.path.isdir(directory):
os.mkdir(directory)
else:
directory = root
filename = directory + '/' + cast['title'] + extension
path = os.path.abspath(filename)
if (not os.path.isfile(path)) or (override):
download(item['url'], path, cast['title'])
else:
print('{}: File already exists'.format(cast['title']))
def get_anchor_links_rss(newest=False):
parsed = podcastparser.parse(anchor_fm_rss,
urllib.request.urlopen(anchor_fm_rss))
total_episodes = len(parsed['episodes'])
if newest: # just get the newest episode
return parsed['episodes'][0], total_episodes
episodes = parsed['episodes'][:10]
anchor_links = []
anchor_titles = []
anchor_descriptions = []
for episode in episodes:
anchor_links.append(episode['link'])
anchor_titles.append(episode['title'])
anchor_descriptions.append(
format_description(episode['description_html']))
return anchor_links, anchor_titles, anchor_descriptions, total_episodes
def update_using_feedservice(urls):
import podcastparser
from urllib.request import urlopen, Request
podcasts = []
for url in urls:
try:
feed = podcastparser.parse(
url, urlopen(Request(url, headers=REQUEST_HEADERS)), 5)
except Exception as error: # pylint: disable=broad-except
_LOGGER.error("Could not update %s - %s", url, error)
feed = None
if feed is None:
_LOGGER.info("Feed not updated: %s", url)
continue
# Handle permanent redirects
if feed.get("new_location", False):
new_url = feed["new_location"]
_LOGGER.info("Redirect %s => %s", url, new_url)
url = new_url
# Error handling
if feed.get("errors", False):
_LOGGER.error("Error parsing feed: %s", repr(feed["errors"]))
continue
# Update per-podcast metadata
podcast = {
"title": feed.get("title", ""),
"link": feed.get("link", url),
"description": feed.get("description", ""),
"cover_url": feed.get("logo", ""),
"episodes": [parse_entry(entry) for entry in feed["episodes"]],
}
podcasts.append(podcast)
return podcasts
def make_playlist(feedurl, get_newest=False):
# fetch podcast feed
podcast = podcastparser.parse(feedurl, urllib.urlopen(feedurl), max_episodes=10)
# create a name
name = podcast['title'].encode('utf-8')
name = name.replace(' ', '_')
name = ''.join(['Podcast_',name])
# extract episodes
episodes = podcast['episodes']
content = get_episodes(episodes)
# create playlist
filename = pls_generator(name, content)
if get_newest:
return filename, content[0]
else:
return filename
def getMP3Lists(podcastURL):
print "-------------------------------------------------------"
print "Getting MP3 Links"
u = urllib2.urlopen(podcastURL)
# Save the output to the xml file
localFile = open('mp3s.xml','w')
localFile.write(u.read())
localFile.close()
print "-------------------------------------------------------"
del podcastMP3Array[:]
# Parse the content through podcastparser
parsed = podcastparser.parse(podcastURL, urllib.urlopen(podcastURL))
print "Found: " + str(len(parsed))
for i in range(len(parsed)):
podcastMP3Array.append(parsed['episodes'][i]['enclosures'][0]['url'])
print " "+parsed['episodes'][i]['enclosures'][0]['url']
print "-------------------------------------------------------"
def _parse_feed(self, url, etag, modified, autodiscovery=True):
headers = {}
if modified is not None:
headers['If-Modified-Since'] = modified
if etag is not None:
headers['If-None-Match'] = etag
if url.startswith('file://'):
is_local = True
url = url[len('file://'):]
stream = open(url)
else:
is_local = False
try:
stream = util.urlopen(url, headers)
except HTTPError as e:
return self._check_statuscode(e, e.geturl())
if stream.headers.get('content-type', '').startswith('text/html'):
if autodiscovery:
ad = FeedAutodiscovery(url)
ad.feed(stream.read())
if ad._resolved_url:
try:
self._parse_feed(ad._resolved_url, None, None, False)
return Result(NEW_LOCATION, ad._resolved_url)
except Exception as e:
logger.warn('Feed autodiscovery failed', exc_info=True)
# Second, try to resolve the URL
url = self._resolve_url(url)
if url:
return Result(NEW_LOCATION, url)
raise InvalidFeed('Got HTML document instead')
feed = podcastparser.parse(url, stream)
feed['headers'] = stream.headers
return self._check_statuscode(stream, feed)
def handle_play_podcast_intent(self, message):
utter = message.data['utterance']
podcast_names = [
self.settings["nameone"], self.settings["nametwo"],
self.settings["namethree"]
]
podcast_urls = [
self.settings["feedone"], self.settings["feedtwo"],
self.settings["feedthree"]
]
listen_url = self.chosen_podcast(utter, podcast_names, podcast_urls)
#if misheard, retry and return false if Mycroft could not hear the name of the podcast
try_count = 0
while (listen_url == "" and try_count < 2):
try_count += 1
response = self.get_response('nomatch')
listen_url = self.chosen_podcast(response, podcast_names,
podcast_urls)
if try_count == 1 and listen_url == "":
self.speak_dialog('not.found')
return False
#normalise feed and parse it
normalised_feed = pp.normalize_feed_url(listen_url)
parsed_feed = pp.parse(normalised_feed,
urllib.urlopen(normalised_feed))
#Check what episode the user wants
episode_index = 0
#This block adds functionality for the user to choose an episode
while (True):
episode_title = parsed_feed['episodes'][episode_index]['title']
podcast_title = parsed_feed['title']
data_dict = {
"podcast_title": podcast_title,
"episode_title": episode_title
}
if episode_index == 0:
response = self.get_response('play.previous',
data=data_dict,
on_fail='please.repeat')
else:
response = self.get_response('play.next.previous',
data=data_dict,
on_fail='please.repeat')
#error check
if response is None:
break
if "stop" in response:
self.speak("Operation cancelled.")
return False
elif "play" in response:
break
elif "previous" in response:
episode_index += 1
elif "next" in response:
#ensure index doesnt go below zero
if episode_index != 0:
episode_index -= 1
self.speak("Playing podcast.")
time.sleep(1)
#some feeds have different formats, these two were the most common ones I found so it will try them both
try:
episode = (
parsed_feed["episodes"][episode_index]["enclosures"][0]["url"])
except:
self.speak_dialog('badrss')
#check for any redirects
episode = urllib.urlopen(episode)
redirected_episode = episode.geturl()
# if audio service module is available use it
if self.audioservice:
self.audioservice.play(redirected_episode,
message.data['utterance'])
else: # othervice use normal mp3 playback
self.process = play_mp3(redirected_episode)
self.enclosure.mouth_text(episode_title)
def podlist(self, media):
"""Get podcast infos(parsed)."""
parsed = podcastparser.parse(media, urllib.urlopen(media))
return parsed
def load_feed(path):
print('loading ', path, '...')
return podcastparser.parse(path, downloaded(path))
def test_fail_parse(self, feed):
with pytest.raises(podcastparser.FeedParseError):
podcastparser.parse('file://example.com/feed.xml', StringIO(feed))
except IndexError as e:
pod_items = 5
# SET a user agent string because some podcast sites throw a 403 forbidden, if no UA set
hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/534.30 (KHTML, like Gecko) Ubuntu/10.10 Chromium/12.0.742.112 Chrome/12.0.742.112 Safari/534.30',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding': 'none',
'Accept-Language': 'en-US,en;q=0.8',
'Connection': 'keep-alive'}
feedrequest = urllib2.Request(feedurl, headers=hdr)
# GET the dictonary object from Podcastparser
try:
data = podcastparser.parse(feedurl, urllib2.urlopen(feedrequest), int(pod_items))
except podcastparser.FeedParseError:
print("Podcast Parser Error: Please file a bug report at github.com/gpodder/podcastparser")
sys.exit()
pod_title = data["title"]
pod_timeformat = "%m/%d/%Y"
pod_m3u = "#EXTM3U\n"
# Let's do this, metaverse from podcastparser.py ...
# total_time,
# description
def infospodcast(self, url, max_episodes=0):
"""Get podcast shows list (parsed)."""
parsed = podcastparser.parse(url, urllib.urlopen(url))
return parsed
def fetch_feed_details(url):
parsed = podcastparser.parse(url, urlopen(url))
#print(parsed)
feed_det = [dict(link=parsed['link'], title=parsed['title'], cover_url=parsed['cover_url'], description=parsed['description'])]
#print(feed_det)
return feed_det
def function():
"""Get podcast infos(parsed)."""
parsed = podcastparser.parse(media, urllib.urlopen(media))
return parsed
def load_feed(path):
print('loading ', path, '...')
return podcastparser.parse(path, downloaded(path))
# read arguments from the command line
args, unknown = parser.parse_known_args()
print("<rss version=\"2.0\" xmlns:atom=\"http://www.w3.org/2005/Atom\">")
print("<channel>")
print("<title>%s</title>" % (args.title))
print("<link>%s</link>" % (args.link))
print("<image>")
print("<url>%s</url>" % (args.image))
print("</image>")
print("\n")
for i in range(len(unknown)):
feedurl = unknown[i]
feed = podcastparser.parse(feedurl,
urllib.request.urlopen(feedurl),
max_episodes=7)
feedtitle = feed.get('title', '')
feedlink = feed.get('link', '')
feeddesc = feed.get('description', '')
for ep in feed['episodes']:
eptitle = ep['title']
epdesc = ep['description']
eppubdate = datetime.utcfromtimestamp(int(
ep['published'])).strftime('%a, %d %b %Y %T')
enclosure = ep['enclosures'][0]
epurl = enclosure['url'].split("?")[0]
guid = hashlib.md5(epurl.encode() + eppubdate.encode())
print("<item>")
print("<title>%s: %s</title>" %
os.mkdir(temp_dir)
for url in feed_list:
##should do some kind of validation for blank lines etc
podcast_url = url.strip().split("|")[0]
request = urllib.request.Request(podcast_url)
request.add_header("User-Agent", user_agent)
if len(url.strip().split("|")) == 3:
podcast_username = url.strip().split("|")[1]
podcast_password = url.strip().split("|")[2]
auth_str = bytes(podcast_username + ":" + podcast_password,'utf-8')
base64string = base64.b64encode(auth_str).strip().decode('ascii')
header = "Basic " + base64string
request.add_header("Authorization", header)
try:
podcast = podcastparser.parse(podcast_url, urllib.request.urlopen(request))
except KeyboardInterrupt:
quit()
except:
feed_log.write(podcast_url + '\n')
feed_log.flush()
print ("failed to parse: " + podcast_url)
continue
podcast_name = podcast['title']
podcast_dir = base_directory + podcast_name + "/"
if os.path.isdir(podcast_dir) == False:
os.mkdir(podcast_dir)
def test_fail_parse(feed):
with assert_raises(podcastparser.FeedParseError):
podcastparser.parse('file://example.com/feed.xml', StringIO(feed))
