type hinting for query, streams, and extract
Browse files- README.md +3 -3
- pytube/extract.py +4 -3
- pytube/query.py +9 -6
- pytube/streams.py +15 -15
README.md
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
<div align="center">
|
3 |
<p align="center">
|
4 |
<img src="https://img.shields.io/pypi/v/pytube3.svg" alt="pypi">
|
5 |
-
<a href="https://travis-ci.
|
6 |
<a href='https://pytube3.readthedocs.io/en/latest/?badge=latest'><img src='https://readthedocs.org/projects/pytube3/badge/?version=latest' alt='Documentation Status' /></a>
|
7 |
<a href="https://coveralls.io/github/hbmartin/pytube3?branch=master"><img src="https://coveralls.io/repos/github/hbmartin/pytube3/badge.svg?branch=master" /></a>
|
8 |
<a href="https://pypi.python.org/pypi/pytube3/"><img src="https://img.shields.io/pypi/pyversions/pytube3.svg" /></a>
|
@@ -239,11 +239,11 @@ Virtual environment is setup with [pipenv](https://pipenv-fork.readthedocs.io/en
|
|
239 |
|
240 |
#### Code Formatting
|
241 |
|
242 |
-
This project is linted with [pyflakes](https://github.com/PyCQA/pyflakes)
|
243 |
|
244 |
#### Testing
|
245 |
|
246 |
-
This project is tested with [pytest](https://docs.pytest.org/en/latest/) and coverage is evaluated with [coveralls](https://coveralls-python.readthedocs.io/en/latest/index.html)
|
247 |
|
248 |
#### Code of Conduct
|
249 |
|
|
|
2 |
<div align="center">
|
3 |
<p align="center">
|
4 |
<img src="https://img.shields.io/pypi/v/pytube3.svg" alt="pypi">
|
5 |
+
<a href="https://travis-ci.com/hbmartin/pytube3/"><img src="https://travis-ci.org/hbmartin/pytube3.svg?branch=master" /></a>
|
6 |
<a href='https://pytube3.readthedocs.io/en/latest/?badge=latest'><img src='https://readthedocs.org/projects/pytube3/badge/?version=latest' alt='Documentation Status' /></a>
|
7 |
<a href="https://coveralls.io/github/hbmartin/pytube3?branch=master"><img src="https://coveralls.io/repos/github/hbmartin/pytube3/badge.svg?branch=master" /></a>
|
8 |
<a href="https://pypi.python.org/pypi/pytube3/"><img src="https://img.shields.io/pypi/pyversions/pytube3.svg" /></a>
|
|
|
239 |
|
240 |
#### Code Formatting
|
241 |
|
242 |
+
This project is linted with [pyflakes](https://github.com/PyCQA/pyflakes), formatted with [Black](https://github.com/ambv/black), and typed with [mypy](https://mypy.readthedocs.io/en/latest/introduction.html)
|
243 |
|
244 |
#### Testing
|
245 |
|
246 |
+
This project is tested with [pytest](https://docs.pytest.org/en/latest/) and coverage is evaluated with [coveralls](https://coveralls-python.readthedocs.io/en/latest/index.html).
|
247 |
|
248 |
#### Code of Conduct
|
249 |
|
pytube/extract.py
CHANGED
@@ -4,6 +4,7 @@ import json
|
|
4 |
from collections import OrderedDict
|
5 |
|
6 |
from html.parser import HTMLParser
|
|
|
7 |
from urllib.parse import quote
|
8 |
from urllib.parse import urlencode
|
9 |
from pytube.exceptions import RegexMatchError
|
@@ -177,14 +178,14 @@ def mime_type_codec(mime_type_codec):
|
|
177 |
return mime_type, [c.strip() for c in codecs.split(",")]
|
178 |
|
179 |
|
180 |
-
def get_ytplayer_config(html, age_restricted=False):
|
181 |
"""Get the YouTube player configuration data from the watch html.
|
182 |
|
183 |
Extract the ``ytplayer_config``, which is json data embedded within the
|
184 |
watch html and serves as the primary source of obtaining the stream
|
185 |
manifest data.
|
186 |
|
187 |
-
:param str
|
188 |
The html contents of the watch page.
|
189 |
:param bool age_restricted:
|
190 |
Is video age restricted.
|
@@ -200,7 +201,7 @@ def get_ytplayer_config(html, age_restricted=False):
|
|
200 |
return json.loads(yt_player_config)
|
201 |
|
202 |
|
203 |
-
def get_vid_descr(html):
|
204 |
html_parser = PytubeHTMLParser()
|
205 |
html_parser.feed(html)
|
206 |
return html_parser.vid_descr
|
|
|
4 |
from collections import OrderedDict
|
5 |
|
6 |
from html.parser import HTMLParser
|
7 |
+
from typing import Any
|
8 |
from urllib.parse import quote
|
9 |
from urllib.parse import urlencode
|
10 |
from pytube.exceptions import RegexMatchError
|
|
|
178 |
return mime_type, [c.strip() for c in codecs.split(",")]
|
179 |
|
180 |
|
181 |
+
def get_ytplayer_config(html: str, age_restricted: bool = False) -> Any:
|
182 |
"""Get the YouTube player configuration data from the watch html.
|
183 |
|
184 |
Extract the ``ytplayer_config``, which is json data embedded within the
|
185 |
watch html and serves as the primary source of obtaining the stream
|
186 |
manifest data.
|
187 |
|
188 |
+
:param str html:
|
189 |
The html contents of the watch page.
|
190 |
:param bool age_restricted:
|
191 |
Is video age restricted.
|
|
|
201 |
return json.loads(yt_player_config)
|
202 |
|
203 |
|
204 |
+
def get_vid_descr(html: str) -> str:
|
205 |
html_parser = PytubeHTMLParser()
|
206 |
html_parser.feed(html)
|
207 |
return html_parser.vid_descr
|
pytube/query.py
CHANGED
@@ -1,5 +1,8 @@
|
|
1 |
# -*- coding: utf-8 -*-
|
2 |
"""This module provides a query interface for media streams and captions."""
|
|
|
|
|
|
|
3 |
|
4 |
|
5 |
class StreamQuery:
|
@@ -210,7 +213,7 @@ class StreamQuery:
|
|
210 |
def get_by_itag(self, itag):
|
211 |
"""Get the corresponding :class:`Stream <Stream>` for a given itag.
|
212 |
|
213 |
-
:param
|
214 |
YouTube format identifier code.
|
215 |
:rtype: :class:`Stream <Stream>` or None
|
216 |
:returns:
|
@@ -251,7 +254,7 @@ class StreamQuery:
|
|
251 |
except IndexError:
|
252 |
pass
|
253 |
|
254 |
-
def count(self):
|
255 |
"""Get the count the query would return.
|
256 |
|
257 |
:rtype: int
|
@@ -259,7 +262,7 @@ class StreamQuery:
|
|
259 |
"""
|
260 |
return len(self.fmt_streams)
|
261 |
|
262 |
-
def all(self):
|
263 |
"""Get all the results represented by this query as a list.
|
264 |
|
265 |
:rtype: list
|
@@ -271,7 +274,7 @@ class StreamQuery:
|
|
271 |
class CaptionQuery:
|
272 |
"""Interface for querying the available captions."""
|
273 |
|
274 |
-
def __init__(self, captions):
|
275 |
"""Construct a :class:`Caption <Caption>`.
|
276 |
|
277 |
param list captions:
|
@@ -281,7 +284,7 @@ class CaptionQuery:
|
|
281 |
self.captions = captions
|
282 |
self.lang_code_index = {c.code: c for c in captions}
|
283 |
|
284 |
-
def get_by_language_code(self, lang_code):
|
285 |
"""Get the :class:`Caption <Caption>` for a given ``lang_code``.
|
286 |
|
287 |
:param str lang_code:
|
@@ -293,7 +296,7 @@ class CaptionQuery:
|
|
293 |
"""
|
294 |
return self.lang_code_index.get(lang_code)
|
295 |
|
296 |
-
def all(self):
|
297 |
"""Get all the results represented by this query as a list.
|
298 |
|
299 |
:rtype: list
|
|
|
1 |
# -*- coding: utf-8 -*-
|
2 |
"""This module provides a query interface for media streams and captions."""
|
3 |
+
from typing import List, Optional
|
4 |
+
|
5 |
+
from pytube import Stream, Caption
|
6 |
|
7 |
|
8 |
class StreamQuery:
|
|
|
213 |
def get_by_itag(self, itag):
|
214 |
"""Get the corresponding :class:`Stream <Stream>` for a given itag.
|
215 |
|
216 |
+
:param int itag:
|
217 |
YouTube format identifier code.
|
218 |
:rtype: :class:`Stream <Stream>` or None
|
219 |
:returns:
|
|
|
254 |
except IndexError:
|
255 |
pass
|
256 |
|
257 |
+
def count(self) -> int:
|
258 |
"""Get the count the query would return.
|
259 |
|
260 |
:rtype: int
|
|
|
262 |
"""
|
263 |
return len(self.fmt_streams)
|
264 |
|
265 |
+
def all(self) -> List[Stream]:
|
266 |
"""Get all the results represented by this query as a list.
|
267 |
|
268 |
:rtype: list
|
|
|
274 |
class CaptionQuery:
|
275 |
"""Interface for querying the available captions."""
|
276 |
|
277 |
+
def __init__(self, captions: List[Caption]):
|
278 |
"""Construct a :class:`Caption <Caption>`.
|
279 |
|
280 |
param list captions:
|
|
|
284 |
self.captions = captions
|
285 |
self.lang_code_index = {c.code: c for c in captions}
|
286 |
|
287 |
+
def get_by_language_code(self, lang_code: str) -> Optional[Caption]:
|
288 |
"""Get the :class:`Caption <Caption>` for a given ``lang_code``.
|
289 |
|
290 |
:param str lang_code:
|
|
|
296 |
"""
|
297 |
return self.lang_code_index.get(lang_code)
|
298 |
|
299 |
+
def all(self) -> List[Caption]:
|
300 |
"""Get all the results represented by this query as a list.
|
301 |
|
302 |
:rtype: list
|
pytube/streams.py
CHANGED
@@ -12,6 +12,7 @@ import io
|
|
12 |
import logging
|
13 |
import os
|
14 |
import pprint
|
|
|
15 |
|
16 |
from pytube import extract
|
17 |
from pytube import request
|
@@ -25,7 +26,7 @@ logger = logging.getLogger(__name__)
|
|
25 |
class Stream(object):
|
26 |
"""Container for stream manifest data."""
|
27 |
|
28 |
-
def __init__(self, stream, player_config_args, monostate):
|
29 |
"""Construct a :class:`Stream <Stream>`.
|
30 |
|
31 |
:param dict stream:
|
@@ -47,7 +48,7 @@ class Stream(object):
|
|
47 |
self.res = None # resolution (e.g.: 480p, 720p, 1080p)
|
48 |
self.url = None # signed download url
|
49 |
|
50 |
-
self._filesize = None # filesize in bytes
|
51 |
self.mime_type = None # content identifier (e.g.: video/mp4)
|
52 |
self.type = None # the part of the mime before the slash
|
53 |
self.subtype = None # the part of the mime after the slash
|
@@ -82,7 +83,7 @@ class Stream(object):
|
|
82 |
# streams return NoneType for audio/video depending.
|
83 |
self.video_codec, self.audio_codec = self.parse_codecs()
|
84 |
|
85 |
-
def set_attributes_from_dict(self, dct):
|
86 |
"""Set class attributes from dictionary items.
|
87 |
|
88 |
:rtype: None
|
@@ -91,17 +92,17 @@ class Stream(object):
|
|
91 |
setattr(self, key, val)
|
92 |
|
93 |
@property
|
94 |
-
def is_adaptive(self):
|
95 |
"""Whether the stream is DASH.
|
96 |
|
97 |
:rtype: bool
|
98 |
"""
|
99 |
# if codecs has two elements (e.g.: ['vp8', 'vorbis']): 2 % 2 = 0
|
100 |
# if codecs has one element (e.g.: ['vp8']) 1 % 2 = 1
|
101 |
-
return len(self.codecs) % 2
|
102 |
|
103 |
@property
|
104 |
-
def is_progressive(self):
|
105 |
"""Whether the stream is progressive.
|
106 |
|
107 |
:rtype: bool
|
@@ -109,7 +110,7 @@ class Stream(object):
|
|
109 |
return not self.is_adaptive
|
110 |
|
111 |
@property
|
112 |
-
def includes_audio_track(self):
|
113 |
"""Whether the stream only contains audio.
|
114 |
|
115 |
:rtype: bool
|
@@ -119,7 +120,7 @@ class Stream(object):
|
|
119 |
return self.type == "audio"
|
120 |
|
121 |
@property
|
122 |
-
def includes_video_track(self):
|
123 |
"""Whether the stream only contains video.
|
124 |
|
125 |
:rtype: bool
|
@@ -128,7 +129,7 @@ class Stream(object):
|
|
128 |
return True
|
129 |
return self.type == "video"
|
130 |
|
131 |
-
def parse_codecs(self):
|
132 |
"""Get the video/audio codecs from list of codecs.
|
133 |
|
134 |
Parse a variable length sized list of codecs and returns a
|
@@ -152,7 +153,7 @@ class Stream(object):
|
|
152 |
return video, audio
|
153 |
|
154 |
@property
|
155 |
-
def filesize(self):
|
156 |
"""File size of the media stream in bytes.
|
157 |
|
158 |
:rtype: int
|
@@ -165,7 +166,7 @@ class Stream(object):
|
|
165 |
return self._filesize
|
166 |
|
167 |
@property
|
168 |
-
def title(self):
|
169 |
"""Get title of video
|
170 |
|
171 |
:rtype: str
|
@@ -187,7 +188,7 @@ class Stream(object):
|
|
187 |
return "Unknown YouTube Video Title"
|
188 |
|
189 |
@property
|
190 |
-
def default_filename(self):
|
191 |
"""Generate filename based on the video title.
|
192 |
|
193 |
:rtype: str
|
@@ -316,7 +317,7 @@ class Stream(object):
|
|
316 |
logger.debug("calling on_complete callback %s", on_complete)
|
317 |
on_complete(self, file_handle)
|
318 |
|
319 |
-
def __repr__(self):
|
320 |
"""Printable object representation.
|
321 |
|
322 |
:rtype: str
|
@@ -335,5 +336,4 @@ class Stream(object):
|
|
335 |
parts.extend(['vcodec="{s.video_codec}"'])
|
336 |
else:
|
337 |
parts.extend(['abr="{s.abr}"', 'acodec="{s.audio_codec}"'])
|
338 |
-
|
339 |
-
return "<Stream: {parts}>".format(parts=parts)
|
|
|
12 |
import logging
|
13 |
import os
|
14 |
import pprint
|
15 |
+
from typing import Dict, Tuple, Optional
|
16 |
|
17 |
from pytube import extract
|
18 |
from pytube import request
|
|
|
26 |
class Stream(object):
|
27 |
"""Container for stream manifest data."""
|
28 |
|
29 |
+
def __init__(self, stream: Dict, player_config_args: Dict, monostate: Dict):
|
30 |
"""Construct a :class:`Stream <Stream>`.
|
31 |
|
32 |
:param dict stream:
|
|
|
48 |
self.res = None # resolution (e.g.: 480p, 720p, 1080p)
|
49 |
self.url = None # signed download url
|
50 |
|
51 |
+
self._filesize: Optional[int] = None # filesize in bytes
|
52 |
self.mime_type = None # content identifier (e.g.: video/mp4)
|
53 |
self.type = None # the part of the mime before the slash
|
54 |
self.subtype = None # the part of the mime after the slash
|
|
|
83 |
# streams return NoneType for audio/video depending.
|
84 |
self.video_codec, self.audio_codec = self.parse_codecs()
|
85 |
|
86 |
+
def set_attributes_from_dict(self, dct: Dict):
|
87 |
"""Set class attributes from dictionary items.
|
88 |
|
89 |
:rtype: None
|
|
|
92 |
setattr(self, key, val)
|
93 |
|
94 |
@property
|
95 |
+
def is_adaptive(self) -> bool:
|
96 |
"""Whether the stream is DASH.
|
97 |
|
98 |
:rtype: bool
|
99 |
"""
|
100 |
# if codecs has two elements (e.g.: ['vp8', 'vorbis']): 2 % 2 = 0
|
101 |
# if codecs has one element (e.g.: ['vp8']) 1 % 2 = 1
|
102 |
+
return bool(len(self.codecs) % 2)
|
103 |
|
104 |
@property
|
105 |
+
def is_progressive(self) -> bool:
|
106 |
"""Whether the stream is progressive.
|
107 |
|
108 |
:rtype: bool
|
|
|
110 |
return not self.is_adaptive
|
111 |
|
112 |
@property
|
113 |
+
def includes_audio_track(self) -> bool:
|
114 |
"""Whether the stream only contains audio.
|
115 |
|
116 |
:rtype: bool
|
|
|
120 |
return self.type == "audio"
|
121 |
|
122 |
@property
|
123 |
+
def includes_video_track(self) -> bool:
|
124 |
"""Whether the stream only contains video.
|
125 |
|
126 |
:rtype: bool
|
|
|
129 |
return True
|
130 |
return self.type == "video"
|
131 |
|
132 |
+
def parse_codecs(self) -> Tuple:
|
133 |
"""Get the video/audio codecs from list of codecs.
|
134 |
|
135 |
Parse a variable length sized list of codecs and returns a
|
|
|
153 |
return video, audio
|
154 |
|
155 |
@property
|
156 |
+
def filesize(self) -> int:
|
157 |
"""File size of the media stream in bytes.
|
158 |
|
159 |
:rtype: int
|
|
|
166 |
return self._filesize
|
167 |
|
168 |
@property
|
169 |
+
def title(self) -> str:
|
170 |
"""Get title of video
|
171 |
|
172 |
:rtype: str
|
|
|
188 |
return "Unknown YouTube Video Title"
|
189 |
|
190 |
@property
|
191 |
+
def default_filename(self) -> str:
|
192 |
"""Generate filename based on the video title.
|
193 |
|
194 |
:rtype: str
|
|
|
317 |
logger.debug("calling on_complete callback %s", on_complete)
|
318 |
on_complete(self, file_handle)
|
319 |
|
320 |
+
def __repr__(self) -> str:
|
321 |
"""Printable object representation.
|
322 |
|
323 |
:rtype: str
|
|
|
336 |
parts.extend(['vcodec="{s.video_codec}"'])
|
337 |
else:
|
338 |
parts.extend(['abr="{s.abr}"', 'acodec="{s.audio_codec}"'])
|
339 |
+
return "<Stream: {parts}>".format(parts=" ".join(parts).format(s=self))
|
|