File size: 20,591 Bytes
44bafb2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 |
"""This module contains all non-cipher related data extraction logic."""
import logging
import urllib.parse
import re
from collections import OrderedDict
from datetime import datetime
from typing import Any, Dict, List, Optional, Tuple
from urllib.parse import parse_qs, quote, urlencode, urlparse
from pytubefix.cipher import Cipher
from pytubefix.exceptions import HTMLParseError, LiveStreamError, RegexMatchError
from pytubefix.helpers import regex_search
from pytubefix.metadata import YouTubeMetadata
from pytubefix.parser import parse_for_object, parse_for_all_objects
logger = logging.getLogger(__name__)
def publish_date(watch_html: str):
"""Extract publish date and return it as a datetime object
:param str watch_html:
The html contents of the watch page.
:rtype: datetime
:returns:
Publish date of the video as a datetime object with timezone.
"""
try:
result = re.search(
r"(?<=itemprop=\"datePublished\" content=\")\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}[+-]\d{2}:\d{2}",
watch_html
)
if result:
return datetime.fromisoformat(result.group(0))
except AttributeError:
return None
def recording_available(watch_html):
"""Check if live stream recording is available.
:param str watch_html:
The html contents of the watch page.
:rtype: bool
:returns:
Whether or not the content is private.
"""
unavailable_strings = [
'This live stream recording is not available.'
]
for string in unavailable_strings:
if string in watch_html:
return False
return True
def is_private(watch_html):
"""Check if content is private.
:param str watch_html:
The html contents of the watch page.
:rtype: bool
:returns:
Whether or not the content is private.
"""
private_strings = [
"This is a private video. Please sign in to verify that you may see it.",
"\"simpleText\":\"Private video\"",
"This video is private."
]
for string in private_strings:
if string in watch_html:
return True
return False
def is_age_restricted(watch_html: str) -> bool:
"""Check if content is age restricted.
:param str watch_html:
The html contents of the watch page.
:rtype: bool
:returns:
Whether or not the content is age restricted.
"""
try:
regex_search(r"og:restrictions:age", watch_html, group=0)
except RegexMatchError:
return False
return True
def playability_status(player_response: dict) -> Tuple[Any, Any]:
"""Return the playability status and status explanation of a video.
For example, a video may have a status of LOGIN_REQUIRED, and an explanation
of "This is a private video. Please sign in to verify that you may see it."
This explanation is what gets incorporated into the media player overlay.
:param str player_response:
Content of the player's response.
:rtype: bool
:returns:
Playability status and reason of the video.
"""
status_dict = player_response.get('playabilityStatus', {})
# if 'liveStreamability' in status_dict:
# We used liveStreamability to know if the video was live,
# however some clients still return this parameter even if the video is already available
if 'videoDetails' in player_response: # Private videos do not contain videoDetails
if 'isLive' in player_response['videoDetails']:
return 'LIVE_STREAM', 'Video is a live stream.'
if 'status' in status_dict:
if 'reason' in status_dict:
return status_dict['status'], [status_dict['reason']]
if 'messages' in status_dict:
return status_dict['status'], status_dict['messages']
return None, [None]
def signature_timestamp(js: str) -> str:
return regex_search(r"signatureTimestamp:(\d*)", js, group=1)
def visitor_data(response_context: str) -> str:
return regex_search(r"visitor_data[',\"\s]+value['\"]:\s?['\"]([a-zA-Z0-9_%-]+)['\"]", response_context, group=1)
def video_id(url: str) -> str:
"""Extract the ``video_id`` from a YouTube url.
This function supports the following patterns:
- :samp:`https://youtube.com/watch?v={video_id}`
- :samp:`https://youtube.com/embed/{video_id}`
- :samp:`https://youtu.be/{video_id}`
:param str url:
A YouTube url containing a video id.
:rtype: str
:returns:
YouTube video id.
"""
return regex_search(r"(?:v=|\/)([0-9A-Za-z_-]{11}).*", url, group=1)
def playlist_id(url: str) -> str:
"""Extract the ``playlist_id`` from a YouTube url.
This function supports the following patterns:
- :samp:`https://youtube.com/playlist?list={playlist_id}`
- :samp:`https://youtube.com/watch?v={video_id}&list={playlist_id}`
:param str url:
A YouTube url containing a playlist id.
:rtype: str
:returns:
YouTube playlist id.
"""
parsed = urllib.parse.urlparse(url)
return parse_qs(parsed.query)['list'][0]
def channel_name(url: str) -> str:
"""Extract the ``channel_name`` or ``channel_id`` from a YouTube url.
This function supports the following patterns:
- :samp:`https://youtube.com/c/{channel_name}/*`
- :samp:`https://youtube.com/channel/{channel_id}/*
- :samp:`https://youtube.com/u/{channel_name}/*`
- :samp:`https://youtube.com/user/{channel_id}/*
- :samp:`https://youtube.com/@{channel_id}/*
:param str url:
A YouTube url containing a channel name.
:rtype: str
:returns:
YouTube channel name.
"""
patterns = [
r"(?:\/(c)\/([%\d\w_\-]+)(\/.*)?)",
r"(?:\/(channel)\/([%\w\d_\-]+)(\/.*)?)",
r"(?:\/(u)\/([%\d\w_\-]+)(\/.*)?)",
r"(?:\/(user)\/([%\w\d_\-]+)(\/.*)?)",
r"(?:\/(\@)([%\d\w_\-\.]+)(\/.*)?)"
]
for pattern in patterns:
regex = re.compile(pattern)
function_match = regex.search(url)
if function_match:
logger.debug("finished regex search, matched: %s", pattern)
uri_style = function_match.group(1)
uri_identifier = function_match.group(2)
return f'/{uri_style}/{uri_identifier}' if uri_style != '@' else f'/{uri_style}{uri_identifier}'
raise RegexMatchError(
caller="channel_name", pattern="patterns"
)
def video_info_url(video_id: str, watch_url: str) -> str:
"""Construct the video_info url.
:param str video_id:
A YouTube video identifier.
:param str watch_url:
A YouTube watch url.
:rtype: str
:returns:
:samp:`https://youtube.com/get_video_info` with necessary GET
parameters.
"""
params = OrderedDict(
[
("video_id", video_id),
("ps", "default"),
("eurl", quote(watch_url)),
("hl", "en_US"),
("html5", "1"),
("c", "TVHTML5"),
("cver", "7.20201028"),
]
)
return _video_info_url(params)
def video_info_url_age_restricted(video_id: str, embed_html: str) -> str:
"""Construct the video_info url.
:param str video_id:
A YouTube video identifier.
:param str embed_html:
The html contents of the embed page (for age restricted videos).
:rtype: str
:returns:
:samp:`https://youtube.com/get_video_info` with necessary GET
parameters.
"""
try:
sts = regex_search(r'"sts"\s*:\s*(\d+)', embed_html, group=1)
except RegexMatchError:
sts = ""
# Here we use ``OrderedDict`` so that the output is consistent between
# Python 2.7+.
eurl = f"https://youtube.googleapis.com/v/{video_id}"
params = OrderedDict(
[
("video_id", video_id),
("eurl", eurl),
("sts", sts),
("html5", "1"),
("c", "TVHTML5"),
("cver", "7.20201028"),
]
)
return _video_info_url(params)
def _video_info_url(params: OrderedDict) -> str:
return f"https://www.youtube.com/get_video_info?{urlencode(params)}"
def js_url(html: str) -> str:
"""Get the base JavaScript url.
Construct the base JavaScript url, which contains the decipher
"transforms".
:param str html:
The html contents of the watch page.
"""
try:
base_js = get_ytplayer_config(html)['assets']['js']
except (KeyError, RegexMatchError):
base_js = get_ytplayer_js(html)
return f"https://youtube.com{base_js}"
def mime_type_codec(mime_type_codec: str) -> Tuple[str, List[str]]:
"""Parse the type data.
Breaks up the data in the ``type`` key of the manifest, which contains the
mime type and codecs serialized together, and splits them into separate
elements.
**Example**:
mime_type_codec('audio/webm; codecs="opus"') -> ('audio/webm', ['opus'])
:param str mime_type_codec:
String containing mime type and codecs.
:rtype: tuple
:returns:
The mime type and a list of codecs.
"""
pattern = r"(\w+\/\w+)\;\scodecs=\"([a-zA-Z-0-9.,\s]*)\""
regex = re.compile(pattern)
results = regex.search(mime_type_codec)
if not results:
raise RegexMatchError(caller="mime_type_codec", pattern=pattern)
mime_type, codecs = results.groups()
return mime_type, [c.strip() for c in codecs.split(",")]
def get_ytplayer_js(html: str) -> Any:
"""Get the YouTube player base JavaScript path.
:param str html
The html contents of the watch page.
:rtype: str
:returns:
Path to YouTube's base.js file.
"""
js_url_patterns = [
r"(/s/player/[\w\d]+/[\w\d_/.]+/base\.js)"
]
for pattern in js_url_patterns:
regex = re.compile(pattern)
function_match = regex.search(html)
if function_match:
logger.debug("finished regex search, matched: %s", pattern)
yt_player_js = function_match.group(1)
logger.debug("player JS: " + yt_player_js)
return yt_player_js
raise RegexMatchError(
caller="get_ytplayer_js", pattern="js_url_patterns"
)
def get_ytplayer_config(html: str) -> Any:
"""Get the YouTube player configuration data from the watch html.
Extract the ``ytplayer_config``, which is json data embedded within the
watch html and serves as the primary source of obtaining the stream
manifest data.
:param str html:
The html contents of the watch page.
:rtype: str
:returns:
Substring of the html containing the encoded manifest data.
"""
logger.debug("finding initial function name")
config_patterns = [
r"ytplayer\.config\s*=\s*",
r"ytInitialPlayerResponse\s*=\s*"
]
for pattern in config_patterns:
# Try each pattern consecutively if they don't find a match
try:
return parse_for_object(html, pattern)
except HTMLParseError as e:
logger.debug(f'Pattern failed: {pattern}')
logger.debug(e)
continue
# setConfig() needs to be handled a little differently.
# We want to parse the entire argument to setConfig()
# and use then load that as json to find PLAYER_CONFIG
# inside of it.
setconfig_patterns = [
r"yt\.setConfig\(.*['\"]PLAYER_CONFIG['\"]:\s*"
]
for pattern in setconfig_patterns:
# Try each pattern consecutively if they don't find a match
try:
return parse_for_object(html, pattern)
except HTMLParseError:
continue
raise RegexMatchError(
caller="get_ytplayer_config", pattern="config_patterns, setconfig_patterns"
)
def get_ytcfg(html: str) -> str:
"""Get the entirety of the ytcfg object.
This is built over multiple pieces, so we have to find all matches and
combine the dicts together.
:param str html:
The html contents of the watch page.
:rtype: str
:returns:
Substring of the html containing the encoded manifest data.
"""
ytcfg = {}
ytcfg_patterns = [
r"ytcfg\s=\s",
r"ytcfg\.set\("
]
for pattern in ytcfg_patterns:
# Try each pattern consecutively and try to build a cohesive object
try:
found_objects = parse_for_all_objects(html, pattern)
for obj in found_objects:
ytcfg.update(obj)
except HTMLParseError:
continue
if ytcfg: # there is at least one item
return ytcfg
raise RegexMatchError(
caller="get_ytcfg", pattern="ytcfg_pattenrs"
)
def apply_po_token(stream_manifest: Dict, vid_info: Dict, po_token: str) -> None:
"""Apply the proof of origin token to the stream manifest
:param dict stream_manifest:
Details of the media streams available.
:param str po_token:
Proof of Origin Token.
"""
logger.debug(f'Applying poToken')
for i, stream in enumerate(stream_manifest):
try:
url: str = stream["url"]
except KeyError:
live_stream = (
vid_info.get("playabilityStatus", {}, )
.get("liveStreamability")
)
if live_stream:
raise LiveStreamError("UNKNOWN")
parsed_url = urlparse(url)
# Convert query params off url to dict
query_params = parse_qs(urlparse(url).query)
query_params = {
k: v[0] for k, v in query_params.items()
}
query_params['pot'] = po_token
url = f'{parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path}?{urlencode(query_params)}'
stream_manifest[i]["url"] = url
def apply_signature(stream_manifest: Dict, vid_info: Dict, js: str, url_js: str) -> None:
"""Apply the decrypted signature to the stream manifest.
:param dict stream_manifest:
Details of the media streams available.
:param str js:
The contents of the base.js asset file.
:param str url_js:
Full base.js url
"""
cipher = Cipher(js=js, js_url=url_js)
discovered_n = dict()
for i, stream in enumerate(stream_manifest):
try:
url: str = stream["url"]
except KeyError:
live_stream = (
vid_info.get("playabilityStatus", {}, )
.get("liveStreamability")
)
if live_stream:
raise LiveStreamError("UNKNOWN")
parsed_url = urlparse(url)
# Convert query params off url to dict
query_params = parse_qs(urlparse(url).query)
query_params = {
k: v[0] for k, v in query_params.items()
}
# 403 Forbidden fix.
if "signature" in url or (
"s" not in stream and ("&sig=" in url or "&lsig=" in url)
):
# For certain videos, YouTube will just provide them pre-signed, in
# which case there's no real magic to download them and we can skip
# the whole signature descrambling entirely.
logger.debug("signature found, skip decipher")
else:
signature = cipher.get_signature(ciphered_signature=stream["s"])
logger.debug(
"finished descrambling signature for itag=%s", stream["itag"]
)
query_params['sig'] = signature
if 'n' in query_params.keys():
# For WEB-based clients, YouTube sends an "n" parameter that throttles download speed.
# To decipher the value of "n", we must interpret the player's JavaScript.
initial_n = query_params['n']
logger.debug(f'Parameter n is: {initial_n}')
# Check if any previous stream decrypted the parameter
if initial_n not in discovered_n:
discovered_n[initial_n] = cipher.get_throttling(initial_n)
else:
logger.debug('Parameter n found skipping decryption')
new_n = discovered_n[initial_n]
query_params['n'] = new_n
logger.debug(f'Parameter n deciphered: {new_n}')
url = f'{parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path}?{urlencode(query_params)}' # noqa:E501
stream_manifest[i]["url"] = url
def apply_descrambler(stream_data: Dict) -> Optional[List[Dict]]:
"""Apply various in-place transforms to YouTube's media stream data.
Creates a ``list`` of dictionaries by string splitting on commas, then
taking each list item, parsing it as a query string, converting it to a
``dict`` and unquoting the value.
:param dict stream_data:
Dictionary containing query string encoded values.
**Example**:
>>> d = {'foo': 'bar=1&var=test,em=5&t=url%20encoded'}
>>> apply_descrambler(d, 'foo')
>>> print(d)
{'foo': [{'bar': '1', 'var': 'test'}, {'em': '5', 't': 'url encoded'}]}
"""
if 'url' in stream_data:
return None
# Merge formats and adaptiveFormats into a single list
formats: list[Dict] = []
if 'formats' in stream_data.keys():
formats.extend(stream_data['formats'])
if 'adaptiveFormats' in stream_data.keys():
formats.extend(stream_data['adaptiveFormats'])
# Extract url and s from signatureCiphers as necessary
for data in formats:
if 'url' not in data and 'signatureCipher' in data:
cipher_url = parse_qs(data['signatureCipher'])
data['url'] = cipher_url['url'][0]
data['s'] = cipher_url['s'][0]
data['is_sabr'] = False
elif 'url' not in data and 'signatureCipher' not in data:
data['url'] = stream_data['serverAbrStreamingUrl']
data['is_sabr'] = True
data['is_otf'] = data.get('type') == 'FORMAT_STREAM_TYPE_OTF'
logger.debug("applying descrambler")
return formats
def initial_data(watch_html: str) -> dict:
"""Extract the ytInitialData json from the watch_html page.
This mostly contains metadata necessary for rendering the page on-load,
such as video information, copyright notices, etc.
@param watch_html: Html of the watch page
@return:
"""
patterns = [
r"window\[['\"]ytInitialData['\"]]\s*=\s*",
r"ytInitialData\s*=\s*"
]
for pattern in patterns:
try:
return parse_for_object(watch_html, pattern)
except HTMLParseError:
pass
raise RegexMatchError(caller='initial_data', pattern='initial_data_pattern')
def initial_player_response(watch_html: str) -> str:
"""Extract the ytInitialPlayerResponse json from the watch_html page.
This mostly contains metadata necessary for rendering the page on-load,
such as video information, copyright notices, etc.
@param watch_html: Html of the watch page
@return:
"""
patterns = [
r"window\[['\"]ytInitialPlayerResponse['\"]]\s*=\s*",
r"ytInitialPlayerResponse\s*=\s*"
]
for pattern in patterns:
try:
return parse_for_object(watch_html, pattern)
except HTMLParseError:
pass
raise RegexMatchError(
caller='initial_player_response',
pattern='initial_player_response_pattern'
)
def metadata(initial_data) -> Optional[YouTubeMetadata]:
"""Get the informational metadata for the video.
e.g.:
[
{
'Song': '강남스타일(Gangnam Style)',
'Artist': 'PSY',
'Album': 'PSY SIX RULES Pt.1',
'Licensed to YouTube by': 'YG Entertainment Inc. [...]'
}
]
:rtype: YouTubeMetadata
"""
try:
metadata_rows: List = initial_data["contents"]["twoColumnWatchNextResults"][
"results"]["results"]["contents"][1]["videoSecondaryInfoRenderer"][
"metadataRowContainer"]["metadataRowContainerRenderer"]["rows"]
except (KeyError, IndexError):
# If there's an exception accessing this data, it probably doesn't exist.
return YouTubeMetadata([])
# Rows appear to only have "metadataRowRenderer" or "metadataRowHeaderRenderer"
# and we only care about the former, so we filter the others
metadata_rows = filter(
lambda x: "metadataRowRenderer" in x.keys(),
metadata_rows
)
# We then access the metadataRowRenderer key in each element
# and build a metadata object from this new list
metadata_rows = [x["metadataRowRenderer"] for x in metadata_rows]
return YouTubeMetadata(metadata_rows)
|