def parse(podcast_url):
response = requests.get(podcast_url)
podcast = Podcast(response.content)
urls_to_download = []
for item in podcast.items:
urls_to_download.append(item)
return urls_to_download
def subscribe(feed_url):
print 'Subscribing to feed at ' + feed_url
response = requests.get(feed_url)
# print response.headers
if response.status_code != 200:
print 'URL not valid (%d)' % response.status_code
sys.exit(2)
podcast = Podcast(response.content)
if not podcast.is_valid_podcast:
print 'URL is not a podcast feed.'
sys.exit(2)
etag = None
last_modified = None
if response.headers.get('etag'):
etag = response.headers['etag']
elif response.headers.get('Last-Modified'):
last_modified = response.headers['Last-Modified']
print 'Show Title: ' + podcast.title
print 'There are %d items in feed.' % len(podcast.items)
subs = load_subscriptions()
add_subscription(subs, podcast.title, feed_url, etag, last_modified)
save_subscriptions(subs)
print 'Subscribed.'
def add_podcast():
submit_rss_final = request.form['RSS_url_final']
note = requests.get(submit_rss_final)
quick = Podcast(note.content)
podfeed_new = pod(quick.title, request.form['RSS_url_final'],
parser.parse(quick.items[0].published_date),
json.dumps(make_disp_title(quick.title)))
db.session.add(podfeed_new)
db.session.commit()
submit_rss_final = request.form['RSS_url_final']
episode_count = len(quick.items)
#add error check for feeds that have 2 levels of links.
for x in range(int(episode_count)):
entry_new = episode(quick.items[x].title,
parser.parse(quick.items[x].published_date),
podfeed_new.id, quick.items[x].enclosure_url)
db.session.add(entry_new)
db.session.commit()
update_hjson()
set_seq()
return redirect(url_for('show_all'))
def update_pod(pod_id):
the_pod = pod.query.filter_by(id=pod_id).first()
d = feedparser.parse(the_pod.address)
pod_date = requests.get(the_pod.address)
date_helper = Podcast(pod_date.content)
#fix time naivete
utc = pytz.UTC
last_update = (the_pod.update_date)
last_update = last_update.replace(tzinfo=None)
try:
current_update = parser.parse(d['entries'][0]['published'],
ignoretz=True)
except IndexError:
current_update = parser.parse((date_helper.items[0].published_date),
ignoretz=True)
update_response = False
if last_update < current_update:
the_pod.update_date = current_update
db.session.commit()
update_response = True
feed_titles = []
episode_count = len(date_helper.items)
for x in range(int(episode_count)):
current_entry = date_helper.items[x].title
#print(current_entry + 'PPPP')
feed_titles.append(current_entry)
if_exists = db.session.query(
episode.query.filter_by(
title=current_entry).exists()).scalar()
#print(if_exists)
if not (if_exists == True):
entry_new = episode(
date_helper.items[x].title,
parser.parse(date_helper.items[0].published_date),
the_pod.id, date_helper.items[x].enclosure_url)
db.session.add(entry_new)
db.session.commit()
trim_these = episode.query.filter_by(pod_id=pod_id).all()
episode_count = (len(trim_these))
for x in range(int(episode_count)):
if trim_these[x].title not in feed_titles:
#print(trim_these[x].title)
db.session.delete(trim_these[x])
db.session.commit()
def parse():
response = requests.get(url_to_parse)
podcast = Podcast(response.content)
urls_to_download = []
for item in podcast.items:
pprint.pprint(item.enclosure_url)
print(type(item.enclosure_url))
urls_to_download.append(item.enclosure_url)
data = {'urls': list(urls_to_download)}
return data
def get_raw_feed(feed_url):
response = requests.get(feed_URL)
if response.status_code == 200:
pass
else:
return "Response Error"
podcast = Podcast(response.content)
def get_context_data(self, **kwargs):
feed_url = self.request.GET.get('feed')
context = super(PodcastView, self).get_context_data(**kwargs)
if feed_url:
response = requests.get(feed_url)
podcast = Podcast(response.content)
if podcast.items:
context.update({'podcast': podcast})
context.update({'feed_url': feed_url})
return context
def download_metadata(data_path):
with open(data_path, "r") as f:
shows = csv.DictReader(f)
for row in shows:
url = row["feed_url"]
try:
response = requests.get(url, timeout=1.0)
podcast = Podcast(response.content)
except:
continue
for episode in podcast.items:
title = _sentences(episode.title)
if episode.description:
description = _sentences(episode.description)
print_episode(title, description)
def pod_lookup(pod_num):
url = 'https://drinkingbros.libsyn.com/rss'
response = requests.get(url)
podcast = Podcast(response.content)
select_pod = podcast.items[pod_num]
pod_title = select_pod.title
pod_desc_uf = select_pod.description
pod_desc_f1 = pod_desc_uf.split("<p>")
# pod_desc_f2 = pod_desc_f1.normalize("NFKD", correct_desc_f1[1])
pod_desc_f2 = pod_desc_f1[1]
pod_desc_f3 = pod_desc_f2.replace("</p>", "")
pod_desc = pod_desc_f3
pod_date = select_pod.date_time.strftime('%Y-%m-%d')
return pod_title, pod_desc, pod_date
def refresh_feed(feed_url):
subs = load_subscriptions()
etag = etag_for_sub(subs, feed_url)
last_modified = last_modified_for_sub(subs, feed_url)
headers = {
'If-None-Match': etag,
'Last-Modified': last_modified
}
r = requests.get(feed_url, headers)
if r.status_code == 200:
new_etag = r.headers.get('ETag')
new_last_modified = r.headers.get('Last-Modified')
save_etag_for_sub(subs, feed_url, new_etag)
save_last_modified_for_sub(subs, feed_url, new_last_modified)
save_subscriptions(subs)
podcast = Podcast(r.content)
download_new_episodes(podcast, 1)
def find_rss():
show_modal = True
submit_rss = request.form['RSS_url']
print(submit_rss)
try:
note = requests.get(submit_rss)
print('made it')
quick = Podcast(note.content)
cast_name = quick.title
cast_desc = quick.subtitle
except:
rss_error = True
return render_template('app.html',
modal_cond=show_modal,
rss_err=rss_error)
return render_template('app.html',
feed_address=submit_rss,
rss_cast_title=cast_name,
rss_cast_desc=cast_desc,
modal_cond=show_modal)
def get_podcasts(args: dict) -> None:
# if batch
if args['file_name'] != "":
# open the file and read urls
args['urls'] = read_batch_file(args['file_name'])
# overwrite the urls dict with the urls from the file
for url in args['urls']:
# validate url
if is_valid_url(url):
# download content
feed = safe_request(url)
# put into podcast object
podcast = Podcast(feed.content)
# prints download info
if args['all']:
message('Downloading ' + podcast.title +
' podcast from --- to ' + args['date_to'])
else:
message('Downloading ' + podcast.title + ' podcast from ' +
args['date_from'] + ' to ' + args['date_to'])
# for items in podcast feed
for item in podcast.items:
if not args['all']:
# if within date specified
if ((datetime.strptime(args['date_from'], '%d/%m/%y') <=
item.date_time <= datetime.strptime(
args['date_to'], '%d/%m/%y'))):
download(item, args)
else:
download(item, args)
else:
message(url + ' is not a valid rss url, cannot download podcasts')
def process_podcast(pod: str, url: str, headers: dict, fromdate,
args: Options):
# if --podcast is used we will only process a matching name
if args.podcast:
if not args.podcast == pod:
return # continue
try:
request = urllib.request.Request(url, headers=headers)
content = urllib.request.urlopen(request)
podcast = Podcast(content.read())
except (urllib.error.HTTPError, urllib.error.URLError) as err:
message("Podcast: {}".format(pod), wait=True)
message("Connection error: {}".format(err))
return # continue
for item in podcast.items:
try:
process_podcast_item(pod, item, headers, fromdate, args)
except SkipPodcast:
break
def main(argv):
url = ""
try:
opts, args = getopt.getopt(argv, "hu:", ["url="])
except getopt.GetoptError:
print 'podcast-coverart-fetcher.py -u <rss_feed_url>'
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print 'podcast-coverart-fetcher.py -u <rss_feed_url>'
sys.exit()
elif opt in ("-u", "--url"):
url = arg
if url != "":
# fetching and parsing the feed
print url
print 'fetching podcast feed...'
response = requests.get(url)
print 'parsing podcast feed...'
podcast = Podcast(response.content)
# downloading the coverart
coverart_url = podcast.itune_image
print coverart_url
print 'following redirects...'
response = requests.get(coverart_url)
coverart_url = response.url # url after redirects
print coverart_url
print 'downloading coverart image...'
coverart = urllib.URLopener()
filename = coverart_url.rsplit('/', 1)[-1]
coverart.retrieve(coverart_url, filename)
print 'coverart downloaded successfully: ' + filename
else:
print 'please provide a podcast rss feed URL.'
print 'podcast-coverart-fetcher.py -u <rss_feed_url>'
def getPodcastEpisodes(self,pod):
name,loc = pod.split("#@!")
response = requests.get(loc)
podcast = Podcast(response.content)
os.system('cls')
print ("-------------------------------------------------------------")
print (podcast.title)
print ("-------------------------------------------------------------")
i = 1
for episodes in podcast.items:
print (str(i) + ": " + episodes.title)
i = i+1
selection = int(input("Enter Podcast No. : "))
os.system("cls")
print ("-------------------------------------------------------------")
print (podcast.items[selection-1].title)
print ("-------------------------------------------------------------")
print (podcast.items[selection-1].itunes_subtitle)
remoteurl = podcast.items[selection-1].enclosure_url
print (remoteurl)
print ("downloading")
urlretrieve (remoteurl)
print ("downloadComplete")
def get_context_data(self, **kwargs):
feed_url = self.request.GET.get('feed')
episode_n = int(self.request.GET.get('episode'))
context = super(PodcastDetailView, self).get_context_data(**kwargs)
if feed_url:
response = requests.get(feed_url)
podcast = Podcast(response.content)
if podcast.items:
context.update({
'podcast': {
'itune_image': podcast.itune_image,
'itunes_author_name': podcast.itunes_author_name
}
})
context.update({'current_item': podcast.items[episode_n]})
context.update({
'recent_items':
podcast.items[episode_n + 1:episode_n + 3]
})
context.update({'feed_url': feed_url})
return context
def __init__(self, url):
self.url = url
feed_response = requests.get(url)
Podcast.__init__(self, feed_response.content)
def get_podcast(feed):
response = requests.get(feed)
return Podcast(response.content)
fromStart = value["fromStart"]
pdcsts.append(PodcastEntry(value["amount"], value["url"], value["folderName"], voffset, fromStart))
return pdcsts
if __name__ == '__main__':
podcasts = getListOfPodcasts()
for podcastIndex in range(len(podcasts)):
offSet = 1
numberToGet = 0
podcast = podcasts[podcastIndex]
logger.log("Found podcast with URL %s and amount %d" % (podcast.link, podcast.amount))
response = requests.get(podcast.link)
show = Podcast(response.content)
if podcast.amount > 0:
numberToGet = podcast.amount
elif podcast.amount < 0:
numberToGet = len(show.items)
else:
logger.log("Requested no podcasts to be downloaded. This entry is considered a place holder and is ignored")
logger.log("Downloading %d episode(s)" % numberToGet)
if podcast.fromStart:
show.items.reverse()
if podcast.offset:
offSet = podcast.offset
weekday_order = {
"Mon": 0,
"Tue": 1,
"Wed": 2,
"Thu": 3,
"Fri": 4,
"Sat": 5,
"Sun": 6
}
x = range(len(weekday_order))
podcast_list = []
for shows in outline:
podcast_url = shows.xmlUrl
response = requests.get(podcast_url)
podcast = Podcast(response.content)
podcast_list.append(MyPodcast(podcast.title))
print(podcast.title)
weekday_time = [0] * 7
for episode in podcast.items:
# print(episode.title.encode("utf-8"))
duration = episode.itunes_duration
if duration is not None:
weekday, day, month, year, *_ = episode.published_date.replace(
",", "").split()
today = datetime.date.today()
margin = datetime.timedelta(weeks=week_margin)
date = datetime.datetime.strptime(day + month + year,
def total_pods():
url = 'https://drinkingbros.libsyn.com/rss'
response = requests.get(url)
podcast = Podcast(response.content)
all_pods = podcast.items[:]
return all_pods
def _get_episodes_to_download_from_rss(page) -> List[Episode]:
episodes = []
pod_feed = Podcast(page)
for item in pod_feed.items:
episodes.append(Episode(item.enclosure_url, item.title))
return episodes
