1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-20 21:27:52 +08:00

[hearthisat] Add support for more high-quality download links

This commit is contained in:
Philipp Hagemeister 2015-01-22 12:04:07 +01:00
parent e5763a7a7e
commit b55ee18ff3
2 changed files with 45 additions and 12 deletions

View File

@ -4,10 +4,15 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_request from ..compat import (
compat_urllib_request,
compat_urlparse,
)
from ..utils import ( from ..utils import (
HEADRequest,
str_to_int, str_to_int,
urlencode_postdata, urlencode_postdata,
urlhandle_detect_ext,
) )
@ -16,10 +21,10 @@ class HearThisAtIE(InfoExtractor):
_PLAYLIST_URL = 'https://hearthis.at/playlist.php' _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
_TEST = { _TEST = {
'url': 'https://hearthis.at/moofi/dr-kreep', 'url': 'https://hearthis.at/moofi/dr-kreep',
'md5': 'd594c573227a89f4256f0b03e68c80cc', 'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
'info_dict': { 'info_dict': {
'id': '150939', 'id': '150939',
'ext': 'mp3', 'ext': 'wav',
'title': 'Moofi - Dr. Kreep', 'title': 'Moofi - Dr. Kreep',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1421564134, 'timestamp': 1421564134,
@ -67,18 +72,38 @@ class HearThisAtIE(InfoExtractor):
timestamp = str_to_int(self._search_regex( timestamp = str_to_int(self._search_regex(
r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False)) r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
track_url = self._search_regex( formats = []
r'<a[^>]+data-mp3="([^"]+)"', webpage, 'track URL') mp3_url = self._search_regex(
r'(?s)<a class="player-link"\s+(?:[a-zA-Z0-9_:-]+="[^"]+"\s+)*?data-mp3="([^"]+)"',
formats = [{ webpage, 'title', fatal=False)
'format_id': 'mp3', if mp3_url:
'url': track_url, formats.append({
'vcodec': 'none', 'format_id': 'mp3',
}] 'vcodec': 'none',
'acodec': 'mp3',
'url': mp3_url,
})
download_path = self._search_regex(
r'<a class="[^"]*download_fct[^"]*"\s+href="([^"]+)"',
webpage, 'download URL', default=None)
if download_path:
download_url = compat_urlparse.urljoin(url, download_path)
ext_req = HEADRequest(download_url)
ext_handle = self._request_webpage(
ext_req, display_id, note='Determining extension')
ext = urlhandle_detect_ext(ext_handle)
formats.append({
'format_id': 'download',
'vcodec': 'none',
'ext': ext,
'url': download_url,
'preference': 2, # Usually better quality
})
self._sort_formats(formats)
return { return {
'id': track_id, 'id': track_id,
'display-id': display_id, 'display_id': display_id,
'title': title, 'title': title,
'formats': formats, 'formats': formats,
'thumbnail': thumbnail, 'thumbnail': thumbnail,

View File

@ -1612,6 +1612,14 @@ def urlhandle_detect_ext(url_handle):
except AttributeError: # Python < 3 except AttributeError: # Python < 3
getheader = url_handle.info().getheader getheader = url_handle.info().getheader
cd = getheader('Content-Disposition')
if cd:
m = re.match(r'attachment;\s*filename="(?P<filename>[^"]+)"', cd)
if m:
e = determine_ext(m.group('filename'), default_ext=None)
if e:
return e
return getheader('Content-Type').split("/")[1] return getheader('Content-Type').split("/")[1]