def scrap_youtube_id(self, title):
url = "http://www.youtube.com/results?search_query=%s" % urllib.quote_plus(title)
page = requests.get(url, timeout=15)
if 'Aucune vid' in page.content:
logger.warning("No video found for %s" % str(self))
return None
else:
youtube_id = re.findall('href="\/watch\?v=(.*?)[&;"]', page.content)[0]
logger.info("Found %s for song %s" % (youtube_id, str(self)))
return youtube_id
def download(self, youtube_dl_bin, working_directory):
if not self.youtube_id:
logger.warning("Song %(self)s has no youtube id" % locals())
else:
url = "https://www.youtube.com/watch?v=%s" % self.youtube_id
tmp_fn = self.tmp_filename(working_directory).encode("utf8")
fn = self.filename(working_directory).encode("utf8")
if not os.path.exists(fn):
os_query("""%(youtube_dl_bin)s --quiet --extract-audio --audio-format mp3 "%(url)s" -o "%(tmp_fn)s" """ % locals())
logger.info("Downloaded %(self)s" % locals())
else:
logger.info("Skipped %(self)s, already downloaded" % locals())
def search_youtube_id(self, title):
try:
if not self.accessToken:
self.get_access_token()
headers = {'Authorization': 'Bearer ' + self.accessToken}
url = 'https://www.googleapis.com/youtube/v3/search'
r = requests.get(url, params={'part': 'snippet',
'q': title,
'type': 'video'}, headers=headers)
items = r.json()['items']
if len(items) == 0:
youtube_id = None
logger.warning("No video found for %s" % title)
else:
youtube_id = items[0]['id']['videoId']
logger.info("Found %s for song %s" % (youtube_id, title))
return youtube_id
except:
logger.warning('YouTube API search error, fallback on scraper')
return self.scrap_youtube_id(title)
