add self.player_response and lazy caption init
Browse files- pytube/__main__.py +18 -29
- pytube/contrib/playlist.py +5 -2
- pytube/monostate.py +1 -2
- pytube/query.py +1 -0
- pytube/streams.py +1 -1
- pytube/version.py +1 -0
- tests/test_streams.py +4 -10
pytube/__main__.py
CHANGED
@@ -67,12 +67,12 @@ class YouTube:
|
|
67 |
self.watch_html: Optional[str] = None # the html of /watch?v=<video_id>
|
68 |
self.embed_html: Optional[str] = None
|
69 |
self.player_config_args: Dict = {} # inline js in the html containing
|
|
|
70 |
# streams
|
71 |
self.age_restricted: Optional[bool] = None
|
72 |
self.vid_descr: Optional[str] = None
|
73 |
|
74 |
self.fmt_streams: List[Stream] = []
|
75 |
-
self.caption_tracks: List[Caption] = []
|
76 |
|
77 |
# video_id part of /watch?v=<video_id>
|
78 |
self.video_id = extract.video_id(url)
|
@@ -153,11 +153,9 @@ class YouTube:
|
|
153 |
self.initialize_stream_objects(fmt)
|
154 |
|
155 |
# load the player_response object (contains subtitle information)
|
156 |
-
self.
|
157 |
-
|
158 |
-
)
|
159 |
|
160 |
-
self.initialize_caption_objects()
|
161 |
logger.info("init finished successfully")
|
162 |
|
163 |
def prefetch(self) -> None:
|
@@ -173,8 +171,7 @@ class YouTube:
|
|
173 |
self.watch_html = request.get(url=self.watch_url)
|
174 |
if (
|
175 |
self.watch_html is None
|
176 |
-
or '<img class="icon meh" src="/yts/img'
|
177 |
-
not in self.watch_html # noqa: W503
|
178 |
):
|
179 |
raise VideoUnavailable(video_id=self.video_id)
|
180 |
|
@@ -214,26 +211,19 @@ class YouTube:
|
|
214 |
)
|
215 |
self.fmt_streams.append(video)
|
216 |
|
217 |
-
|
218 |
-
|
219 |
-
|
220 |
-
Take the unscrambled player response data, and use it to initialize
|
221 |
-
instances of :class:`Caption <Caption>`.
|
222 |
-
|
223 |
-
:rtype: None
|
224 |
|
|
|
225 |
"""
|
226 |
-
|
227 |
-
|
228 |
-
# https://github.com/nficano/pytube/issues/167
|
229 |
-
caption_tracks = (
|
230 |
-
self.player_config_args.get("player_response", {})
|
231 |
.get("captions", {})
|
232 |
.get("playerCaptionsTracklistRenderer", {})
|
233 |
.get("captionTracks", [])
|
234 |
)
|
235 |
-
for
|
236 |
-
self.caption_tracks.append(Caption(caption_track))
|
237 |
|
238 |
@property
|
239 |
def captions(self) -> CaptionQuery:
|
@@ -258,9 +248,8 @@ class YouTube:
|
|
258 |
:rtype: str
|
259 |
|
260 |
"""
|
261 |
-
player_response = self.player_config_args.get("player_response", {})
|
262 |
thumbnail_details = (
|
263 |
-
player_response.get("videoDetails", {})
|
264 |
.get("thumbnail", {})
|
265 |
.get("thumbnails")
|
266 |
)
|
@@ -278,7 +267,7 @@ class YouTube:
|
|
278 |
|
279 |
"""
|
280 |
return self.player_config_args.get("title") or (
|
281 |
-
self.
|
282 |
.get("videoDetails", {})
|
283 |
.get("title")
|
284 |
)
|
@@ -291,7 +280,7 @@ class YouTube:
|
|
291 |
|
292 |
"""
|
293 |
return self.vid_descr or (
|
294 |
-
self.
|
295 |
.get("videoDetails", {})
|
296 |
.get("shortDescription")
|
297 |
)
|
@@ -304,7 +293,7 @@ class YouTube:
|
|
304 |
|
305 |
"""
|
306 |
return (
|
307 |
-
self.
|
308 |
.get("videoDetails", {})
|
309 |
.get("averageRating")
|
310 |
)
|
@@ -319,7 +308,7 @@ class YouTube:
|
|
319 |
return int(
|
320 |
self.player_config_args.get("length_seconds")
|
321 |
or (
|
322 |
-
self.
|
323 |
.get("videoDetails", {})
|
324 |
.get("lengthSeconds")
|
325 |
)
|
@@ -333,7 +322,7 @@ class YouTube:
|
|
333 |
|
334 |
"""
|
335 |
return int(
|
336 |
-
self.
|
337 |
.get("videoDetails", {})
|
338 |
.get("viewCount")
|
339 |
)
|
@@ -344,7 +333,7 @@ class YouTube:
|
|
344 |
:rtype: str
|
345 |
"""
|
346 |
return (
|
347 |
-
self.
|
348 |
.get("videoDetails", {})
|
349 |
.get("author", "unknown")
|
350 |
)
|
|
|
67 |
self.watch_html: Optional[str] = None # the html of /watch?v=<video_id>
|
68 |
self.embed_html: Optional[str] = None
|
69 |
self.player_config_args: Dict = {} # inline js in the html containing
|
70 |
+
self.player_response: Dict = {}
|
71 |
# streams
|
72 |
self.age_restricted: Optional[bool] = None
|
73 |
self.vid_descr: Optional[str] = None
|
74 |
|
75 |
self.fmt_streams: List[Stream] = []
|
|
|
76 |
|
77 |
# video_id part of /watch?v=<video_id>
|
78 |
self.video_id = extract.video_id(url)
|
|
|
153 |
self.initialize_stream_objects(fmt)
|
154 |
|
155 |
# load the player_response object (contains subtitle information)
|
156 |
+
self.player_response = json.loads(self.player_config_args["player_response"])
|
157 |
+
del self.player_config_args["player_response"]
|
|
|
158 |
|
|
|
159 |
logger.info("init finished successfully")
|
160 |
|
161 |
def prefetch(self) -> None:
|
|
|
171 |
self.watch_html = request.get(url=self.watch_url)
|
172 |
if (
|
173 |
self.watch_html is None
|
174 |
+
or '<img class="icon meh" src="/yts/img' not in self.watch_html
|
|
|
175 |
):
|
176 |
raise VideoUnavailable(video_id=self.video_id)
|
177 |
|
|
|
211 |
)
|
212 |
self.fmt_streams.append(video)
|
213 |
|
214 |
+
@property
|
215 |
+
def caption_tracks(self) -> List[Caption]:
|
216 |
+
"""Get a list of :class:`Caption <Caption>`.
|
|
|
|
|
|
|
|
|
217 |
|
218 |
+
:rtype: List[Caption]
|
219 |
"""
|
220 |
+
raw_tracks = (
|
221 |
+
self.player_response
|
|
|
|
|
|
|
222 |
.get("captions", {})
|
223 |
.get("playerCaptionsTracklistRenderer", {})
|
224 |
.get("captionTracks", [])
|
225 |
)
|
226 |
+
return [Caption(track) for track in raw_tracks]
|
|
|
227 |
|
228 |
@property
|
229 |
def captions(self) -> CaptionQuery:
|
|
|
248 |
:rtype: str
|
249 |
|
250 |
"""
|
|
|
251 |
thumbnail_details = (
|
252 |
+
self.player_response.get("videoDetails", {})
|
253 |
.get("thumbnail", {})
|
254 |
.get("thumbnails")
|
255 |
)
|
|
|
267 |
|
268 |
"""
|
269 |
return self.player_config_args.get("title") or (
|
270 |
+
self.player_response
|
271 |
.get("videoDetails", {})
|
272 |
.get("title")
|
273 |
)
|
|
|
280 |
|
281 |
"""
|
282 |
return self.vid_descr or (
|
283 |
+
self.player_response
|
284 |
.get("videoDetails", {})
|
285 |
.get("shortDescription")
|
286 |
)
|
|
|
293 |
|
294 |
"""
|
295 |
return (
|
296 |
+
self.player_response
|
297 |
.get("videoDetails", {})
|
298 |
.get("averageRating")
|
299 |
)
|
|
|
308 |
return int(
|
309 |
self.player_config_args.get("length_seconds")
|
310 |
or (
|
311 |
+
self.player_response
|
312 |
.get("videoDetails", {})
|
313 |
.get("lengthSeconds")
|
314 |
)
|
|
|
322 |
|
323 |
"""
|
324 |
return int(
|
325 |
+
self.player_response
|
326 |
.get("videoDetails", {})
|
327 |
.get("viewCount")
|
328 |
)
|
|
|
333 |
:rtype: str
|
334 |
"""
|
335 |
return (
|
336 |
+
self.player_response
|
337 |
.get("videoDetails", {})
|
338 |
.get("author", "unknown")
|
339 |
)
|
pytube/contrib/playlist.py
CHANGED
@@ -45,8 +45,7 @@ class Playlist:
|
|
45 |
|
46 |
@staticmethod
|
47 |
def _find_load_more_url(req: str) -> Optional[str]:
|
48 |
-
"""Given an html page or fragment, returns the "load more" url if found.
|
49 |
-
"""
|
50 |
match = re.search(
|
51 |
r"data-uix-load-more-href=\"(/browse_ajax\?" 'action_continuation=.*?)"',
|
52 |
req,
|
@@ -58,6 +57,10 @@ class Playlist:
|
|
58 |
|
59 |
@deprecated("This function will be removed in the future, please use .video_urls")
|
60 |
def parse_links(self) -> List[str]: # pragma: no cover
|
|
|
|
|
|
|
|
|
61 |
return self.video_urls
|
62 |
|
63 |
def _paginate(self, until_watch_id: Optional[str] = None) -> Iterable[List[str]]:
|
|
|
45 |
|
46 |
@staticmethod
|
47 |
def _find_load_more_url(req: str) -> Optional[str]:
|
48 |
+
"""Given an html page or fragment, returns the "load more" url if found."""
|
|
|
49 |
match = re.search(
|
50 |
r"data-uix-load-more-href=\"(/browse_ajax\?" 'action_continuation=.*?)"',
|
51 |
req,
|
|
|
57 |
|
58 |
@deprecated("This function will be removed in the future, please use .video_urls")
|
59 |
def parse_links(self) -> List[str]: # pragma: no cover
|
60 |
+
""" Deprecated function for returning list of URLs
|
61 |
+
|
62 |
+
:return: List[str]
|
63 |
+
"""
|
64 |
return self.video_urls
|
65 |
|
66 |
def _paginate(self, until_watch_id: Optional[str] = None) -> Iterable[List[str]]:
|
pytube/monostate.py
CHANGED
@@ -1,9 +1,8 @@
|
|
|
|
1 |
import io
|
2 |
from typing import Any, Optional
|
3 |
from typing_extensions import Protocol
|
4 |
|
5 |
-
# from __future__ import annotations
|
6 |
-
|
7 |
|
8 |
class OnProgress(Protocol):
|
9 |
def __call__(
|
|
|
1 |
+
# -*- coding: utf-8 -*-
|
2 |
import io
|
3 |
from typing import Any, Optional
|
4 |
from typing_extensions import Protocol
|
5 |
|
|
|
|
|
6 |
|
7 |
class OnProgress(Protocol):
|
8 |
def __call__(
|
pytube/query.py
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
# -*- coding: utf-8 -*-
|
|
|
2 |
"""This module provides a query interface for media streams and captions."""
|
3 |
from typing import List, Optional
|
4 |
|
|
|
1 |
# -*- coding: utf-8 -*-
|
2 |
+
|
3 |
"""This module provides a query interface for media streams and captions."""
|
4 |
from typing import List, Optional
|
5 |
|
pytube/streams.py
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
# -*- coding: utf-8 -*-
|
|
|
2 |
"""
|
3 |
This module contains a container for stream manifest data.
|
4 |
|
@@ -169,7 +170,6 @@ class Stream:
|
|
169 |
:returns:
|
170 |
An os file system compatible filename.
|
171 |
"""
|
172 |
-
|
173 |
filename = safe_filename(self.title)
|
174 |
return f"{filename}.{self.subtype}"
|
175 |
|
|
|
1 |
# -*- coding: utf-8 -*-
|
2 |
+
|
3 |
"""
|
4 |
This module contains a container for stream manifest data.
|
5 |
|
|
|
170 |
:returns:
|
171 |
An os file system compatible filename.
|
172 |
"""
|
|
|
173 |
filename = safe_filename(self.title)
|
174 |
return f"{filename}.{self.subtype}"
|
175 |
|
pytube/version.py
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
__version__ = "9.6.1"
|
2 |
|
3 |
if __name__ == "__main__":
|
|
|
1 |
+
# -*- coding: utf-8 -*-
|
2 |
__version__ = "9.6.1"
|
3 |
|
4 |
if __name__ == "__main__":
|
tests/test_streams.py
CHANGED
@@ -199,29 +199,23 @@ def test_on_complete_hook(cipher_signature, mocker):
|
|
199 |
|
200 |
def test_author(cipher_signature):
|
201 |
expected = "Test author"
|
202 |
-
cipher_signature.
|
203 |
-
"player_response": {"videoDetails": {"author": expected}}
|
204 |
-
}
|
205 |
assert cipher_signature.author == expected
|
206 |
|
207 |
expected = "unknown"
|
208 |
-
cipher_signature.
|
209 |
assert cipher_signature.author == expected
|
210 |
|
211 |
|
212 |
def test_thumbnail_when_in_details(cipher_signature):
|
213 |
expected = "some url"
|
214 |
-
cipher_signature.
|
215 |
-
"player_response": {
|
216 |
-
"videoDetails": {"thumbnail": {"thumbnails": [{"url": expected}]}}
|
217 |
-
}
|
218 |
-
}
|
219 |
assert cipher_signature.thumbnail_url == expected
|
220 |
|
221 |
|
222 |
def test_thumbnail_when_not_in_details(cipher_signature):
|
223 |
expected = "https://img.youtube.com/vi/9bZkp7q19f0/maxresdefault.jpg"
|
224 |
-
cipher_signature.
|
225 |
assert cipher_signature.thumbnail_url == expected
|
226 |
|
227 |
|
|
|
199 |
|
200 |
def test_author(cipher_signature):
|
201 |
expected = "Test author"
|
202 |
+
cipher_signature.player_response = {"videoDetails": {"author": expected}}
|
|
|
|
|
203 |
assert cipher_signature.author == expected
|
204 |
|
205 |
expected = "unknown"
|
206 |
+
cipher_signature.player_response = {}
|
207 |
assert cipher_signature.author == expected
|
208 |
|
209 |
|
210 |
def test_thumbnail_when_in_details(cipher_signature):
|
211 |
expected = "some url"
|
212 |
+
cipher_signature.player_response = {"videoDetails": {"thumbnail": {"thumbnails": [{"url": expected}]}}}
|
|
|
|
|
|
|
|
|
213 |
assert cipher_signature.thumbnail_url == expected
|
214 |
|
215 |
|
216 |
def test_thumbnail_when_not_in_details(cipher_signature):
|
217 |
expected = "https://img.youtube.com/vi/9bZkp7q19f0/maxresdefault.jpg"
|
218 |
+
cipher_signature.player_response = {}
|
219 |
assert cipher_signature.thumbnail_url == expected
|
220 |
|
221 |
|