Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[mixcloud] Add support for new frontend #14132

Closed
wants to merge 7 commits into from
Closed

[mixcloud] Add support for new frontend #14132

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
20dbcfc
[compat] Add compat_zip
ishitatsuyuki Sep 6, 2017
d5a11b4
[mixcloud] Add handling for new frontend
ishitatsuyuki Sep 6, 2017
7ab078e
Address review issues
ishitatsuyuki Sep 13, 2017
6dd969a
Add fallback known-plaintext
ishitatsuyuki Sep 15, 2017
b507277
Ensure data variables are assigned
ishitatsuyuki Sep 15, 2017
a26f294
Address review issue (try 2)
ishitatsuyuki Sep 20, 2017
79ec7fb
Reduce code duplication
ishitatsuyuki Sep 21, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Address review issues
  • Loading branch information
@ishitatsuyuki
ishitatsuyuki committed Sep 13, 2017
commit 7ab078eae9d34687e0a3db3e76e79cff6316a677
51 changes: 24 additions & 27 deletions youtube_dl/extractor/mixcloud.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
ExtractorError,
OnDemandPagedList,
str_to_int,
)
try_get)


class MixcloudIE(InfoExtractor):
Expand Down Expand Up @@ -81,12 +81,8 @@ def _real_extract(self, url):
full_info_json = self._parse_json(self._html_search_regex(
r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>', webpage, 'play info'), 'play info')
for item in full_info_json:
item_data = item.get("cloudcast", {}) \
.get("data", {}) \
.get("cloudcastLookup", {})
if item_data \
.get("streamInfo", {}) \
.get("url", "") != "":
item_data = try_get(item, lambda x: x['cloudcast']['data']['cloudcastLookup'])
if try_get(item_data, lambda x: x['streamInfo']['url']) not in ['', None]:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if try_get(item_data, lambda x: x['streamInfo']['url']) is enough.

info_json = item_data
break

Expand All @@ -108,7 +104,7 @@ def _real_extract(self, url):
kpa_target = encrypted_play_info
else:
kp = 'https://'
kpa_target = base64.b64decode(info_json["streamInfo"]["url"])
kpa_target = base64.b64decode(info_json['streamInfo']['url'])
partial_key = self._decrypt_xor_cipher(kpa_target, kp)
for quote in ["'", '"']:
key = self._search_regex(r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)), js,
Expand Down Expand Up @@ -142,25 +138,26 @@ def _real_extract(self, url):

else:
title = info_json['name']
thumbnail = 'https://thumbnailer.mixcloud.com/unsafe/600x600/' + info_json['picture']['urlRoot']
uploader = info_json['owner']['displayName']
uploader_id = info_json['owner']['username']
description = info_json['description']
view_count = info_json['plays']
formats = [
{
'format_id': 'normal',
'url': self._decrypt_xor_cipher(key, base64.b64decode(info_json['streamInfo']['url']))
},
{
'format_id': 'hls',
'url': self._decrypt_xor_cipher(key, base64.b64decode(info_json['streamInfo']['hlsUrl']))
},
{
'format_id': 'dash',
'url': self._decrypt_xor_cipher(key, base64.b64decode(info_json['streamInfo']['dashUrl']))
}
]
thumbnail = try_get(info_json,
lambda x: 'https://thumbnailer.mixcloud.com/unsafe/600x600/' + x['picture']['urlRoot'])
uploader = try_get(info_json, lambda x: x['owner']['displayName'])
uploader_id = try_get(info_json, lambda x: x['owner']['username'])
description = try_get(info_json, lambda x: x['description'])
view_count = try_get(info_json, lambda x: x['plays'])
formats = [{
'format_id': 'normal',
'url': self._decrypt_xor_cipher(key, base64.b64decode(info_json['streamInfo']['url']))
}]

hls_encrypted = try_get(info_json, lambda x: x['streamInfo']['hlsUrl'])
if hls_encrypted is not None:
hls_url = self._decrypt_xor_cipher(key, base64.b64decode(hls_encrypted))
formats.extend(self._extract_m3u8_formats(hls_url, title))

dash_encrypted = try_get(info_json, lambda x: x['streamInfo']['dashUrl'])
if dash_encrypted is not None:
dash_url = self._decrypt_xor_cipher(key, base64.b64decode(dash_encrypted))
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

157, 160-162, 165-167 code duplication.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What would you suggest then? The duplication is minimal.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Extracting duplicate code into a function obviously.

formats.extend(self._extract_mpd_formats(dash_url, title))

return {
'id': track_id,
Expand Down