Compare commits
93 Commits
2017.02.17
...
2017.02.24
Author | SHA1 | Date | |
---|---|---|---|
204efc8509 | |||
5d3a51e1b9 | |||
ad3033037c | |||
f3bc281239 | |||
441d7a32e5 | |||
51ed496307 | |||
68f17a9c2d | |||
39e7277ed1 | |||
42dcdbe11c | |||
6b097cff27 | |||
f2f7961820 | |||
be5df5ee31 | |||
f2980fddeb | |||
0f57447de7 | |||
19f3821821 | |||
8e1409fd80 | |||
050f143c12 | |||
fafc2bf5a9 | |||
b3175982c3 | |||
89db639dfe | |||
d0d9ade486 | |||
28572a1a0b | |||
0f3d41b44d | |||
d5fd9a3be3 | |||
ada77fa544 | |||
9e03aa75c7 | |||
30eaa3a702 | |||
c59f703610 | |||
bc61c80c14 | |||
345b24538b | |||
63a29b6118 | |||
b5869560a4 | |||
527ef85fe9 | |||
58ad6995cd | |||
a86e416088 | |||
71e9577b94 | |||
0d427c8304 | |||
139d8ac106 | |||
abd29a2ced | |||
31615ac279 | |||
fc320a40d9 | |||
7345d6d465 | |||
86466a8b6f | |||
33dc173cdc | |||
3444844b04 | |||
8c6c88c7da | |||
159aaaa9d0 | |||
eea0716cae | |||
336a76551b | |||
dc0a869e5e | |||
e39b5d4ab8 | |||
e469ab2528 | |||
890d44b005 | |||
6926304472 | |||
3ccdde8cb7 | |||
da42ff0668 | |||
82f662182b | |||
2cc7fcd338 | |||
6d4c259765 | |||
c78dd35491 | |||
8ffb8e63fe | |||
983e9b7746 | |||
8936f68a0b | |||
c58b7ffef4 | |||
f1a78ee4ef | |||
de64e23c56 | |||
553f6dbac7 | |||
0aa10994f4 | |||
4248dad92b | |||
0a840f584c | |||
0016b84e16 | |||
18a0defab0 | |||
5d3fbf77d9 | |||
80b59020e0 | |||
71631862f4 | |||
89cc7fe770 | |||
04d906eae3 | |||
8ab8066cf0 | |||
01b1aa9ff4 | |||
ff4007891f | |||
28200e654b | |||
e633f21a96 | |||
d392005a79 | |||
773f291dcb | |||
bf5b9d859a | |||
049a0f4d6d | |||
ac33accd96 | |||
e84888b432 | |||
02d9b82a23 | |||
a2e3286676 | |||
f75caf059e | |||
bdabbc220c | |||
70bcc444a9 |
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.17*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.17**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.24.1*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
|
||||
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.24.1**
|
||||
|
||||
### Before submitting an *issue* make sure you have:
|
||||
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
|
||||
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] youtube-dl version 2017.02.17
|
||||
[debug] youtube-dl version 2017.02.24.1
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
93
ChangeLog
93
ChangeLog
@ -1,3 +1,96 @@
|
||||
version 2017.02.24.1
|
||||
|
||||
Extractors
|
||||
* [noco] Modernize
|
||||
* [noco] Switch login URL to https (#12246)
|
||||
+ [thescene] Extract more metadata
|
||||
* [thescene] Fix extraction (#12235)
|
||||
+ [tubitv] Use geo bypass mechanism
|
||||
* [openload] Fix extraction (#10408)
|
||||
+ [ivi] Raise GeoRestrictedError
|
||||
|
||||
|
||||
version 2017.02.24
|
||||
|
||||
Core
|
||||
* [options] Hide deprecated options from --help
|
||||
* [options] Deprecate --autonumber-size
|
||||
+ [YoutubeDL] Add support for string formatting operations in output template
|
||||
(#5185, #5748, #6841, #9929, #9966 #9978, #12189)
|
||||
|
||||
Extractors
|
||||
+ [lynda:course] Add webpage extraction fallback (#12238)
|
||||
* [go] Sign all uplynk URLs and use geo bypass only for free videos
|
||||
(#12087, #12210)
|
||||
+ [skylinewebcams] Add support for skylinewebcams.com (#12221)
|
||||
+ [instagram] Add support for multi video posts (#12226)
|
||||
+ [crunchyroll] Extract playlist entries ids
|
||||
* [mgtv] Fix extraction
|
||||
+ [sohu] Raise GeoRestrictedError
|
||||
+ [leeco] Raise GeoRestrictedError and use geo bypass mechanism
|
||||
|
||||
|
||||
version 2017.02.22
|
||||
|
||||
Extractors
|
||||
* [crunchyroll] Fix descriptions with double quotes (#12124)
|
||||
* [dailymotion] Make comment count optional (#12209)
|
||||
+ [vidzi] Add support for vidzi.cc (#12213)
|
||||
+ [24video] Add support for 24video.tube (#12217)
|
||||
+ [crackle] Use geo bypass mechanism
|
||||
+ [viewster] Use geo verification headers
|
||||
+ [tfo] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [telequebec] Use geo bypass mechanism
|
||||
+ [limelight] Extract PlaylistService errors and improve geo restriction
|
||||
detection
|
||||
|
||||
|
||||
version 2017.02.21
|
||||
|
||||
Core
|
||||
* [extractor/common] Allow calling _initialize_geo_bypass from extractors
|
||||
(#11970)
|
||||
+ [adobepass] Add support for Time Warner Cable (#12191)
|
||||
+ [travis] Run tests in parallel
|
||||
+ [downloader/ism] Honor HTTP headers when downloading fragments
|
||||
+ [downloader/dash] Honor HTTP headers when downloading fragments
|
||||
+ [utils] Add GeoUtils class for working with geo tools and GeoUtils.random_ipv4
|
||||
+ Add option --geo-bypass-country for explicit geo bypass on behalf of
|
||||
specified country
|
||||
+ Add options to control geo bypass mechanism --geo-bypass and --no-geo-bypass
|
||||
+ Add experimental geo restriction bypass mechanism based on faking
|
||||
X-Forwarded-For HTTP header
|
||||
+ [utils] Introduce GeoRestrictedError for geo restricted videos
|
||||
+ [utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
|
||||
|
||||
Extractors
|
||||
+ [ninecninemedia] Use geo bypass mechanism
|
||||
* [spankbang] Make uploader optional (#12193)
|
||||
+ [iprima] Improve geo restriction detection and disable geo bypass
|
||||
* [iprima] Modernize
|
||||
* [commonmistakes] Disable UnicodeBOM extractor test for python 3.2
|
||||
+ [prosiebensat1] Throw ExtractionError on unsupported page type (#12180)
|
||||
* [nrk] Update _API_HOST and relax _VALID_URL
|
||||
+ [tv4] Bypass geo restriction and improve detection
|
||||
* [tv4] Switch to hls3 protocol (#12177)
|
||||
+ [viki] Improve geo restriction detection
|
||||
+ [vgtv] Improve geo restriction detection
|
||||
+ [srgssr] Improve geo restriction detection
|
||||
+ [vbox7] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [svt] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [pbs] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [ondemandkorea] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [nrk] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [itv] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [go] Improve geo restriction detection and use geo bypass mechanism
|
||||
+ [dramafever] Improve geo restriction detection and use geo bypass mechanism
|
||||
* [brightcove:legacy] Restrict videoPlayer value (#12040)
|
||||
+ [tvn24] Add support for tvn24.pl and tvn24bis.pl (#11679)
|
||||
+ [thisav] Add support for HTML5 media (#11771)
|
||||
* [metacafe] Bypass family filter (#10371)
|
||||
* [viceland] Improve info extraction
|
||||
|
||||
|
||||
version 2017.02.17
|
||||
|
||||
Extractors
|
||||
|
182
README.md
182
README.md
@ -99,11 +99,21 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
||||
--source-address IP Client-side IP address to bind to
|
||||
-4, --force-ipv4 Make all connections via IPv4
|
||||
-6, --force-ipv6 Make all connections via IPv6
|
||||
|
||||
## Geo Restriction:
|
||||
--geo-verification-proxy URL Use this proxy to verify the IP address for
|
||||
some geo-restricted sites. The default
|
||||
proxy specified by --proxy (or none, if the
|
||||
options is not present) is used for the
|
||||
actual downloading.
|
||||
--geo-bypass Bypass geographic restriction via faking
|
||||
X-Forwarded-For HTTP header (experimental)
|
||||
--no-geo-bypass Do not bypass geographic restriction via
|
||||
faking X-Forwarded-For HTTP header
|
||||
(experimental)
|
||||
--geo-bypass-country CODE Force bypass geographic restriction with
|
||||
explicitly provided two-letter ISO 3166-2
|
||||
country code (experimental)
|
||||
|
||||
## Video Selection:
|
||||
--playlist-start NUMBER Playlist video to start at (default is 1)
|
||||
@ -140,17 +150,19 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
||||
check if the key is not present, key >
|
||||
NUMBER (like "comment_count > 12", also
|
||||
works with >=, <, <=, !=, =) to compare
|
||||
against a number, and & to require multiple
|
||||
matches. Values which are not known are
|
||||
excluded unless you put a question mark (?)
|
||||
after the operator. For example, to only
|
||||
match videos that have been liked more than
|
||||
100 times and disliked less than 50 times
|
||||
(or the dislike functionality is not
|
||||
available at the given service), but who
|
||||
also have a description, use --match-filter
|
||||
"like_count > 100 & dislike_count <? 50 &
|
||||
description" .
|
||||
against a number, key = 'LITERAL' (like
|
||||
"uploader = 'Mike Smith'", also works with
|
||||
!=) to match against a string literal and &
|
||||
to require multiple matches. Values which
|
||||
are not known are excluded unless you put a
|
||||
question mark (?) after the operator. For
|
||||
example, to only match videos that have
|
||||
been liked more than 100 times and disliked
|
||||
less than 50 times (or the dislike
|
||||
functionality is not available at the given
|
||||
service), but who also have a description,
|
||||
use --match-filter "like_count > 100 &
|
||||
dislike_count <? 50 & description" .
|
||||
--no-playlist Download only the video, if the URL refers
|
||||
to a video and a playlist.
|
||||
--yes-playlist Download the playlist, if the URL refers to
|
||||
@ -205,21 +217,11 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
||||
--id Use only video ID in file name
|
||||
-o, --output TEMPLATE Output filename template, see the "OUTPUT
|
||||
TEMPLATE" for all the info
|
||||
--autonumber-size NUMBER Specify the number of digits in
|
||||
%(autonumber)s when it is present in output
|
||||
filename template or --auto-number option
|
||||
is given (default is 5)
|
||||
--autonumber-start NUMBER Specify the start value for %(autonumber)s
|
||||
(default is 1)
|
||||
--restrict-filenames Restrict filenames to only ASCII
|
||||
characters, and avoid "&" and spaces in
|
||||
filenames
|
||||
-A, --auto-number [deprecated; use -o
|
||||
"%(autonumber)s-%(title)s.%(ext)s" ] Number
|
||||
downloaded files starting from 00000
|
||||
-t, --title [deprecated] Use title in file name
|
||||
(default)
|
||||
-l, --literal [deprecated] Alias of --title
|
||||
-w, --no-overwrites Do not overwrite files
|
||||
-c, --continue Force resume of partially downloaded files.
|
||||
By default, youtube-dl will resume
|
||||
@ -474,87 +476,89 @@ The `-o` option allows users to indicate a template for the output file names.
|
||||
|
||||
**tl;dr:** [navigate me to examples](#output-template-examples).
|
||||
|
||||
The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are:
|
||||
The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are:
|
||||
|
||||
- `id`: Video identifier
|
||||
- `title`: Video title
|
||||
- `url`: Video URL
|
||||
- `ext`: Video filename extension
|
||||
- `alt_title`: A secondary title of the video
|
||||
- `display_id`: An alternative identifier for the video
|
||||
- `uploader`: Full name of the video uploader
|
||||
- `license`: License name the video is licensed under
|
||||
- `creator`: The creator of the video
|
||||
- `release_date`: The date (YYYYMMDD) when the video was released
|
||||
- `timestamp`: UNIX timestamp of the moment the video became available
|
||||
- `upload_date`: Video upload date (YYYYMMDD)
|
||||
- `uploader_id`: Nickname or id of the video uploader
|
||||
- `location`: Physical location where the video was filmed
|
||||
- `duration`: Length of the video in seconds
|
||||
- `view_count`: How many users have watched the video on the platform
|
||||
- `like_count`: Number of positive ratings of the video
|
||||
- `dislike_count`: Number of negative ratings of the video
|
||||
- `repost_count`: Number of reposts of the video
|
||||
- `average_rating`: Average rating give by users, the scale used depends on the webpage
|
||||
- `comment_count`: Number of comments on the video
|
||||
- `age_limit`: Age restriction for the video (years)
|
||||
- `format`: A human-readable description of the format
|
||||
- `format_id`: Format code specified by `--format`
|
||||
- `format_note`: Additional info about the format
|
||||
- `width`: Width of the video
|
||||
- `height`: Height of the video
|
||||
- `resolution`: Textual description of width and height
|
||||
- `tbr`: Average bitrate of audio and video in KBit/s
|
||||
- `abr`: Average audio bitrate in KBit/s
|
||||
- `acodec`: Name of the audio codec in use
|
||||
- `asr`: Audio sampling rate in Hertz
|
||||
- `vbr`: Average video bitrate in KBit/s
|
||||
- `fps`: Frame rate
|
||||
- `vcodec`: Name of the video codec in use
|
||||
- `container`: Name of the container format
|
||||
- `filesize`: The number of bytes, if known in advance
|
||||
- `filesize_approx`: An estimate for the number of bytes
|
||||
- `protocol`: The protocol that will be used for the actual download
|
||||
- `extractor`: Name of the extractor
|
||||
- `extractor_key`: Key name of the extractor
|
||||
- `epoch`: Unix epoch when creating the file
|
||||
- `autonumber`: Five-digit number that will be increased with each download, starting at zero
|
||||
- `playlist`: Name or id of the playlist that contains the video
|
||||
- `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist
|
||||
- `playlist_id`: Playlist identifier
|
||||
- `playlist_title`: Playlist title
|
||||
- `id` (string): Video identifier
|
||||
- `title` (string): Video title
|
||||
- `url` (string): Video URL
|
||||
- `ext` (string): Video filename extension
|
||||
- `alt_title` (string): A secondary title of the video
|
||||
- `display_id` (string): An alternative identifier for the video
|
||||
- `uploader` (string): Full name of the video uploader
|
||||
- `license` (string): License name the video is licensed under
|
||||
- `creator` (string): The creator of the video
|
||||
- `release_date` (string): The date (YYYYMMDD) when the video was released
|
||||
- `timestamp` (numeric): UNIX timestamp of the moment the video became available
|
||||
- `upload_date` (string): Video upload date (YYYYMMDD)
|
||||
- `uploader_id` (string): Nickname or id of the video uploader
|
||||
- `location` (string): Physical location where the video was filmed
|
||||
- `duration` (numeric): Length of the video in seconds
|
||||
- `view_count` (numeric): How many users have watched the video on the platform
|
||||
- `like_count` (numeric): Number of positive ratings of the video
|
||||
- `dislike_count` (numeric): Number of negative ratings of the video
|
||||
- `repost_count` (numeric): Number of reposts of the video
|
||||
- `average_rating` (numeric): Average rating give by users, the scale used depends on the webpage
|
||||
- `comment_count` (numeric): Number of comments on the video
|
||||
- `age_limit` (numeric): Age restriction for the video (years)
|
||||
- `format` (string): A human-readable description of the format
|
||||
- `format_id` (string): Format code specified by `--format`
|
||||
- `format_note` (string): Additional info about the format
|
||||
- `width` (numeric): Width of the video
|
||||
- `height` (numeric): Height of the video
|
||||
- `resolution` (string): Textual description of width and height
|
||||
- `tbr` (numeric): Average bitrate of audio and video in KBit/s
|
||||
- `abr` (numeric): Average audio bitrate in KBit/s
|
||||
- `acodec` (string): Name of the audio codec in use
|
||||
- `asr` (numeric): Audio sampling rate in Hertz
|
||||
- `vbr` (numeric): Average video bitrate in KBit/s
|
||||
- `fps` (numeric): Frame rate
|
||||
- `vcodec` (string): Name of the video codec in use
|
||||
- `container` (string): Name of the container format
|
||||
- `filesize` (numeric): The number of bytes, if known in advance
|
||||
- `filesize_approx` (numeric): An estimate for the number of bytes
|
||||
- `protocol` (string): The protocol that will be used for the actual download
|
||||
- `extractor` (string): Name of the extractor
|
||||
- `extractor_key` (string): Key name of the extractor
|
||||
- `epoch` (numeric): Unix epoch when creating the file
|
||||
- `autonumber` (numeric): Five-digit number that will be increased with each download, starting at zero
|
||||
- `playlist` (string): Name or id of the playlist that contains the video
|
||||
- `playlist_index` (numeric): Index of the video in the playlist padded with leading zeros according to the total length of the playlist
|
||||
- `playlist_id` (string): Playlist identifier
|
||||
- `playlist_title` (string): Playlist title
|
||||
|
||||
|
||||
Available for the video that belongs to some logical chapter or section:
|
||||
- `chapter`: Name or title of the chapter the video belongs to
|
||||
- `chapter_number`: Number of the chapter the video belongs to
|
||||
- `chapter_id`: Id of the chapter the video belongs to
|
||||
- `chapter` (string): Name or title of the chapter the video belongs to
|
||||
- `chapter_number` (numeric): Number of the chapter the video belongs to
|
||||
- `chapter_id` (string): Id of the chapter the video belongs to
|
||||
|
||||
Available for the video that is an episode of some series or programme:
|
||||
- `series`: Title of the series or programme the video episode belongs to
|
||||
- `season`: Title of the season the video episode belongs to
|
||||
- `season_number`: Number of the season the video episode belongs to
|
||||
- `season_id`: Id of the season the video episode belongs to
|
||||
- `episode`: Title of the video episode
|
||||
- `episode_number`: Number of the video episode within a season
|
||||
- `episode_id`: Id of the video episode
|
||||
- `series` (string): Title of the series or programme the video episode belongs to
|
||||
- `season` (string): Title of the season the video episode belongs to
|
||||
- `season_number` (numeric): Number of the season the video episode belongs to
|
||||
- `season_id` (string): Id of the season the video episode belongs to
|
||||
- `episode` (string): Title of the video episode
|
||||
- `episode_number` (numeric): Number of the video episode within a season
|
||||
- `episode_id` (string): Id of the video episode
|
||||
|
||||
Available for the media that is a track or a part of a music album:
|
||||
- `track`: Title of the track
|
||||
- `track_number`: Number of the track within an album or a disc
|
||||
- `track_id`: Id of the track
|
||||
- `artist`: Artist(s) of the track
|
||||
- `genre`: Genre(s) of the track
|
||||
- `album`: Title of the album the track belongs to
|
||||
- `album_type`: Type of the album
|
||||
- `album_artist`: List of all artists appeared on the album
|
||||
- `disc_number`: Number of the disc or other physical medium the track belongs to
|
||||
- `release_year`: Year (YYYY) when the album was released
|
||||
- `track` (string): Title of the track
|
||||
- `track_number` (numeric): Number of the track within an album or a disc
|
||||
- `track_id` (string): Id of the track
|
||||
- `artist` (string): Artist(s) of the track
|
||||
- `genre` (string): Genre(s) of the track
|
||||
- `album` (string): Title of the album the track belongs to
|
||||
- `album_type` (string): Type of the album
|
||||
- `album_artist` (string): List of all artists appeared on the album
|
||||
- `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
|
||||
- `release_year` (numeric): Year (YYYY) when the album was released
|
||||
|
||||
Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`.
|
||||
|
||||
For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj`, this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
|
||||
|
||||
For numeric sequences you can use numeric related formatting, for example, `%(view_count)05d` will result in a string with view count padded with zeros up to 5 characters, like in `00042`.
|
||||
|
||||
Output templates can also contain arbitrary hierarchical path, e.g. `-o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s'` which will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you.
|
||||
|
||||
To use percent literals in an output template use `%%`. To output to stdout use `-o -`.
|
||||
|
@ -1,6 +1,7 @@
|
||||
from __future__ import unicode_literals, print_function
|
||||
|
||||
from inspect import getsource
|
||||
import io
|
||||
import os
|
||||
from os.path import dirname as dirn
|
||||
import sys
|
||||
@ -95,5 +96,5 @@ module_contents.append(
|
||||
|
||||
module_src = '\n'.join(module_contents) + '\n'
|
||||
|
||||
with open(lazy_extractors_filename, 'wt') as f:
|
||||
with io.open(lazy_extractors_filename, 'wt', encoding='utf-8') as f:
|
||||
f.write(module_src)
|
||||
|
@ -1,8 +1,9 @@
|
||||
#!/bin/bash
|
||||
|
||||
DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter"
|
||||
DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter|youtube_lists"
|
||||
|
||||
test_set=""
|
||||
multiprocess_args=""
|
||||
|
||||
case "$YTDL_TEST_SET" in
|
||||
core)
|
||||
@ -10,10 +11,11 @@ case "$YTDL_TEST_SET" in
|
||||
;;
|
||||
download)
|
||||
test_set="-I test_(?!$DOWNLOAD_TESTS).+\.py"
|
||||
multiprocess_args="--processes=4 --process-timeout=540"
|
||||
;;
|
||||
*)
|
||||
break
|
||||
;;
|
||||
esac
|
||||
|
||||
nosetests test --verbose $test_set
|
||||
nosetests test --verbose $test_set $multiprocess_args
|
||||
|
@ -680,6 +680,7 @@
|
||||
- **Shared**: shared.sx
|
||||
- **ShowRoomLive**
|
||||
- **Sina**
|
||||
- **SkylineWebcams**
|
||||
- **skynewsarabia:article**
|
||||
- **skynewsarabia:video**
|
||||
- **SkySports**
|
||||
@ -804,6 +805,7 @@
|
||||
- **TVCArticle**
|
||||
- **tvigle**: Интернет-телевидение Tvigle.ru
|
||||
- **tvland.com**
|
||||
- **TVN24**
|
||||
- **TVNoe**
|
||||
- **tvp**: Telewizja Polska
|
||||
- **tvp:embed**: Telewizja Polska
|
||||
|
5
setup.py
5
setup.py
@ -107,8 +107,8 @@ setup(
|
||||
url='https://github.com/rg3/youtube-dl',
|
||||
author='Ricardo Garcia',
|
||||
author_email='ytdl@yt-dl.org',
|
||||
maintainer='Philipp Hagemeister',
|
||||
maintainer_email='phihag@phihag.de',
|
||||
maintainer='Sergey M.',
|
||||
maintainer_email='dstftw@gmail.com',
|
||||
packages=[
|
||||
'youtube_dl',
|
||||
'youtube_dl.extractor', 'youtube_dl.downloader',
|
||||
@ -130,6 +130,7 @@ setup(
|
||||
'Programming Language :: Python :: 3.3',
|
||||
'Programming Language :: Python :: 3.4',
|
||||
'Programming Language :: Python :: 3.5',
|
||||
'Programming Language :: Python :: 3.6',
|
||||
],
|
||||
|
||||
cmdclass={'build_lazy_extractors': build_lazy_extractors},
|
||||
|
@ -526,6 +526,7 @@ class TestYoutubeDL(unittest.TestCase):
|
||||
'id': '1234',
|
||||
'ext': 'mp4',
|
||||
'width': None,
|
||||
'height': 1080,
|
||||
}
|
||||
|
||||
def fname(templ):
|
||||
@ -535,6 +536,19 @@ class TestYoutubeDL(unittest.TestCase):
|
||||
self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
|
||||
# Replace missing fields with 'NA'
|
||||
self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
|
||||
self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
|
||||
self.assertEqual(fname('%(height)6d.%(ext)s'), ' 1080.mp4')
|
||||
self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080 .mp4')
|
||||
self.assertEqual(fname('%(height)06d.%(ext)s'), '001080.mp4')
|
||||
self.assertEqual(fname('%(height) 06d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height) 06d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height)0 6d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height)0 6d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%(height) 0 6d.%(ext)s'), ' 01080.mp4')
|
||||
self.assertEqual(fname('%%(height)06d.%(ext)s'), '%(height)06d.mp4')
|
||||
self.assertEqual(fname('%(width)06d.%(ext)s'), 'NA.mp4')
|
||||
self.assertEqual(fname('%(width)06d.%%(ext)s'), 'NA.%(ext)s')
|
||||
self.assertEqual(fname('%%(width)06d.%(ext)s'), '%(width)06d.mp4')
|
||||
|
||||
def test_format_note(self):
|
||||
ydl = YoutubeDL()
|
||||
|
@ -65,6 +65,10 @@ defs = gettestcases()
|
||||
|
||||
|
||||
class TestDownload(unittest.TestCase):
|
||||
# Parallel testing in nosetests. See
|
||||
# http://nose.readthedocs.org/en/latest/doc_tests/test_multiprocess/multiprocess.html
|
||||
_multiprocess_shared_ = True
|
||||
|
||||
maxDiff = None
|
||||
|
||||
def setUp(self):
|
||||
@ -73,7 +77,7 @@ class TestDownload(unittest.TestCase):
|
||||
# Dynamically generate tests
|
||||
|
||||
|
||||
def generator(test_case):
|
||||
def generator(test_case, tname):
|
||||
|
||||
def test_template(self):
|
||||
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
|
||||
@ -102,6 +106,7 @@ def generator(test_case):
|
||||
return
|
||||
|
||||
params = get_params(test_case.get('params', {}))
|
||||
params['outtmpl'] = tname + '_' + params['outtmpl']
|
||||
if is_playlist and 'playlist' not in test_case:
|
||||
params.setdefault('extract_flat', 'in_playlist')
|
||||
params.setdefault('skip_download', True)
|
||||
@ -146,7 +151,7 @@ def generator(test_case):
|
||||
raise
|
||||
|
||||
if try_num == RETRIES:
|
||||
report_warning('Failed due to network errors, skipping...')
|
||||
report_warning('%s failed due to network errors, skipping...' % tname)
|
||||
return
|
||||
|
||||
print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num))
|
||||
@ -221,12 +226,12 @@ def generator(test_case):
|
||||
|
||||
# And add them to TestDownload
|
||||
for n, test_case in enumerate(defs):
|
||||
test_method = generator(test_case)
|
||||
tname = 'test_' + str(test_case['name'])
|
||||
i = 1
|
||||
while hasattr(TestDownload, tname):
|
||||
tname = 'test_%s_%d' % (test_case['name'], i)
|
||||
i += 1
|
||||
test_method = generator(test_case, tname)
|
||||
test_method.__name__ = str(tname)
|
||||
setattr(TestDownload, test_method.__name__, test_method)
|
||||
del test_method
|
||||
|
@ -33,6 +33,7 @@ from .compat import (
|
||||
compat_get_terminal_size,
|
||||
compat_http_client,
|
||||
compat_kwargs,
|
||||
compat_numeric_types,
|
||||
compat_os_name,
|
||||
compat_str,
|
||||
compat_tokenize_tokenize,
|
||||
@ -56,6 +57,8 @@ from .utils import (
|
||||
ExtractorError,
|
||||
format_bytes,
|
||||
formatSeconds,
|
||||
GeoRestrictedError,
|
||||
ISO3166Utils,
|
||||
locked_file,
|
||||
make_HTTPS_handler,
|
||||
MaxDownloadsReached,
|
||||
@ -272,6 +275,12 @@ class YoutubeDL(object):
|
||||
If it returns None, the video is downloaded.
|
||||
match_filter_func in utils.py is one example for this.
|
||||
no_color: Do not emit color codes in output.
|
||||
geo_bypass: Bypass geographic restriction via faking X-Forwarded-For
|
||||
HTTP header (experimental)
|
||||
geo_bypass_country:
|
||||
Two-letter ISO 3166-2 country code that will be used for
|
||||
explicit geographic restriction bypassing via faking
|
||||
X-Forwarded-For HTTP header (experimental)
|
||||
|
||||
The following options determine which downloader is picked:
|
||||
external_downloader: Executable of the external downloader to call.
|
||||
@ -319,11 +328,21 @@ class YoutubeDL(object):
|
||||
self.params.update(params)
|
||||
self.cache = Cache(self)
|
||||
|
||||
if self.params.get('cn_verification_proxy') is not None:
|
||||
self.report_warning('--cn-verification-proxy is deprecated. Use --geo-verification-proxy instead.')
|
||||
def check_deprecated(param, option, suggestion):
|
||||
if self.params.get(param) is not None:
|
||||
self.report_warning(
|
||||
'%s is deprecated. Use %s instead.' % (option, suggestion))
|
||||
return True
|
||||
return False
|
||||
|
||||
if check_deprecated('cn_verification_proxy', '--cn-verification-proxy', '--geo-verification-proxy'):
|
||||
if self.params.get('geo_verification_proxy') is None:
|
||||
self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
|
||||
|
||||
check_deprecated('autonumber_size', '--autonumber-size', 'output template with %(autonumber)0Nd, where N in the number of digits')
|
||||
check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
|
||||
check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
|
||||
|
||||
if params.get('bidi_workaround', False):
|
||||
try:
|
||||
import pty
|
||||
@ -585,10 +604,7 @@ class YoutubeDL(object):
|
||||
autonumber_size = self.params.get('autonumber_size')
|
||||
if autonumber_size is None:
|
||||
autonumber_size = 5
|
||||
autonumber_templ = '%0' + str(autonumber_size) + 'd'
|
||||
template_dict['autonumber'] = autonumber_templ % (self.params.get('autonumber_start', 1) - 1 + self._num_downloads)
|
||||
if template_dict.get('playlist_index') is not None:
|
||||
template_dict['playlist_index'] = '%0*d' % (len(str(template_dict['n_entries'])), template_dict['playlist_index'])
|
||||
template_dict['autonumber'] = self.params.get('autonumber_start', 1) - 1 + self._num_downloads
|
||||
if template_dict.get('resolution') is None:
|
||||
if template_dict.get('width') and template_dict.get('height'):
|
||||
template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
|
||||
@ -601,12 +617,61 @@ class YoutubeDL(object):
|
||||
compat_str(v),
|
||||
restricted=self.params.get('restrictfilenames'),
|
||||
is_id=(k == 'id'))
|
||||
template_dict = dict((k, sanitize(k, v))
|
||||
template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
|
||||
for k, v in template_dict.items()
|
||||
if v is not None and not isinstance(v, (list, tuple, dict)))
|
||||
template_dict = collections.defaultdict(lambda: 'NA', template_dict)
|
||||
|
||||
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
|
||||
|
||||
# For fields playlist_index and autonumber convert all occurrences
|
||||
# of %(field)s to %(field)0Nd for backward compatibility
|
||||
field_size_compat_map = {
|
||||
'playlist_index': len(str(template_dict['n_entries'])),
|
||||
'autonumber': autonumber_size,
|
||||
}
|
||||
FIELD_SIZE_COMPAT_RE = r'(?<!%)%\((?P<field>autonumber|playlist_index)\)s'
|
||||
mobj = re.search(FIELD_SIZE_COMPAT_RE, outtmpl)
|
||||
if mobj:
|
||||
outtmpl = re.sub(
|
||||
FIELD_SIZE_COMPAT_RE,
|
||||
r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
|
||||
outtmpl)
|
||||
|
||||
NUMERIC_FIELDS = set((
|
||||
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
|
||||
'upload_year', 'upload_month', 'upload_day',
|
||||
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
|
||||
'average_rating', 'comment_count', 'age_limit',
|
||||
'start_time', 'end_time',
|
||||
'chapter_number', 'season_number', 'episode_number',
|
||||
'track_number', 'disc_number', 'release_year',
|
||||
'playlist_index',
|
||||
))
|
||||
|
||||
# Missing numeric fields used together with integer presentation types
|
||||
# in format specification will break the argument substitution since
|
||||
# string 'NA' is returned for missing fields. We will patch output
|
||||
# template for missing fields to meet string presentation type.
|
||||
for numeric_field in NUMERIC_FIELDS:
|
||||
if numeric_field not in template_dict:
|
||||
# As of [1] format syntax is:
|
||||
# %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
|
||||
# 1. https://docs.python.org/2/library/stdtypes.html#string-formatting
|
||||
FORMAT_RE = r'''(?x)
|
||||
(?<!%)
|
||||
%
|
||||
\({0}\) # mapping key
|
||||
(?:[#0\-+ ]+)? # conversion flags (optional)
|
||||
(?:\d+)? # minimum field width (optional)
|
||||
(?:\.\d+)? # precision (optional)
|
||||
[hlL]? # length modifier (optional)
|
||||
[diouxXeEfFgGcrs%] # conversion type
|
||||
'''
|
||||
outtmpl = re.sub(
|
||||
FORMAT_RE.format(numeric_field),
|
||||
r'%({0})s'.format(numeric_field), outtmpl)
|
||||
|
||||
tmpl = compat_expanduser(outtmpl)
|
||||
filename = tmpl % template_dict
|
||||
# Temporary fix for #4787
|
||||
@ -707,6 +772,14 @@ class YoutubeDL(object):
|
||||
return self.process_ie_result(ie_result, download, extra_info)
|
||||
else:
|
||||
return ie_result
|
||||
except GeoRestrictedError as e:
|
||||
msg = e.msg
|
||||
if e.countries:
|
||||
msg += '\nThis video is available in %s.' % ', '.join(
|
||||
map(ISO3166Utils.short2full, e.countries))
|
||||
msg += '\nYou might want to use a VPN or a proxy server (with --proxy) to workaround.'
|
||||
self.report_error(msg)
|
||||
break
|
||||
except ExtractorError as e: # An error we somewhat expected
|
||||
self.report_error(compat_str(e), e.format_traceback())
|
||||
break
|
||||
@ -847,8 +920,14 @@ class YoutubeDL(object):
|
||||
if self.params.get('playlistrandom', False):
|
||||
random.shuffle(entries)
|
||||
|
||||
x_forwarded_for = ie_result.get('__x_forwarded_for_ip')
|
||||
|
||||
for i, entry in enumerate(entries, 1):
|
||||
self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
|
||||
# This __x_forwarded_for_ip thing is a bit ugly but requires
|
||||
# minimal changes
|
||||
if x_forwarded_for:
|
||||
entry['__x_forwarded_for_ip'] = x_forwarded_for
|
||||
extra = {
|
||||
'n_entries': n_entries,
|
||||
'playlist': playlist,
|
||||
@ -1233,6 +1312,11 @@ class YoutubeDL(object):
|
||||
if cookies:
|
||||
res['Cookie'] = cookies
|
||||
|
||||
if 'X-Forwarded-For' not in res:
|
||||
x_forwarded_for_ip = info_dict.get('__x_forwarded_for_ip')
|
||||
if x_forwarded_for_ip:
|
||||
res['X-Forwarded-For'] = x_forwarded_for_ip
|
||||
|
||||
return res
|
||||
|
||||
def _calc_cookies(self, info_dict):
|
||||
@ -1375,6 +1459,9 @@ class YoutubeDL(object):
|
||||
full_format_info = info_dict.copy()
|
||||
full_format_info.update(format)
|
||||
format['http_headers'] = self._calc_headers(full_format_info)
|
||||
# Remove private housekeeping stuff
|
||||
if '__x_forwarded_for_ip' in info_dict:
|
||||
del info_dict['__x_forwarded_for_ip']
|
||||
|
||||
# TODO Central sorting goes here
|
||||
|
||||
|
@ -414,6 +414,11 @@ def _real_main(argv=None):
|
||||
'cn_verification_proxy': opts.cn_verification_proxy,
|
||||
'geo_verification_proxy': opts.geo_verification_proxy,
|
||||
'config_location': opts.config_location,
|
||||
'geo_bypass': opts.geo_bypass,
|
||||
'geo_bypass_country': opts.geo_bypass_country,
|
||||
# just for deprecation check
|
||||
'autonumber': opts.autonumber if opts.autonumber is True else None,
|
||||
'usetitle': opts.usetitle if opts.usetitle is True else None,
|
||||
}
|
||||
|
||||
with YoutubeDL(ydl_opts) as ydl:
|
||||
|
@ -2760,6 +2760,10 @@ else:
|
||||
compat_kwargs = lambda kwargs: kwargs
|
||||
|
||||
|
||||
compat_numeric_types = ((int, float, long, complex) if sys.version_info[0] < 3
|
||||
else (int, float, complex))
|
||||
|
||||
|
||||
if sys.version_info < (2, 7):
|
||||
def compat_socket_create_connection(address, timeout, source_address=None):
|
||||
host, port = address
|
||||
@ -2895,6 +2899,7 @@ __all__ = [
|
||||
'compat_input',
|
||||
'compat_itertools_count',
|
||||
'compat_kwargs',
|
||||
'compat_numeric_types',
|
||||
'compat_ord',
|
||||
'compat_os_name',
|
||||
'compat_parse_qs',
|
||||
|
@ -43,7 +43,10 @@ class DashSegmentsFD(FragmentFD):
|
||||
count = 0
|
||||
while count <= fragment_retries:
|
||||
try:
|
||||
success = ctx['dl'].download(target_filename, {'url': segment_url})
|
||||
success = ctx['dl'].download(target_filename, {
|
||||
'url': segment_url,
|
||||
'http_headers': info_dict.get('http_headers'),
|
||||
})
|
||||
if not success:
|
||||
return False
|
||||
down, target_sanitized = sanitize_open(target_filename, 'rb')
|
||||
|
@ -238,7 +238,10 @@ class IsmFD(FragmentFD):
|
||||
count = 0
|
||||
while count <= fragment_retries:
|
||||
try:
|
||||
success = ctx['dl'].download(target_filename, {'url': segment_url})
|
||||
success = ctx['dl'].download(target_filename, {
|
||||
'url': segment_url,
|
||||
'http_headers': info_dict.get('http_headers'),
|
||||
})
|
||||
if not success:
|
||||
return False
|
||||
down, target_sanitized = sanitize_open(target_filename, 'rb')
|
||||
|
@ -31,6 +31,11 @@ MSO_INFO = {
|
||||
'username_field': 'user',
|
||||
'password_field': 'passwd',
|
||||
},
|
||||
'TWC': {
|
||||
'name': 'Time Warner Cable | Spectrum',
|
||||
'username_field': 'Ecom_User_ID',
|
||||
'password_field': 'Ecom_Password',
|
||||
},
|
||||
'thr030': {
|
||||
'name': '3 Rivers Communications'
|
||||
},
|
||||
|
@ -191,6 +191,10 @@ class BrightcoveLegacyIE(InfoExtractor):
|
||||
# These fields hold the id of the video
|
||||
videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList')
|
||||
if videoPlayer is not None:
|
||||
if isinstance(videoPlayer, list):
|
||||
videoPlayer = videoPlayer[0]
|
||||
if not (videoPlayer.isdigit() or videoPlayer.startswith('ref:')):
|
||||
return None
|
||||
params['@videoPlayer'] = videoPlayer
|
||||
linkBase = find_param('linkBaseURL')
|
||||
if linkBase is not None:
|
||||
|
@ -6,6 +6,7 @@ import hashlib
|
||||
import json
|
||||
import netrc
|
||||
import os
|
||||
import random
|
||||
import re
|
||||
import socket
|
||||
import sys
|
||||
@ -39,6 +40,8 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
fix_xml_ampersands,
|
||||
float_or_none,
|
||||
GeoRestrictedError,
|
||||
GeoUtils,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
parse_iso8601,
|
||||
@ -320,17 +323,34 @@ class InfoExtractor(object):
|
||||
_real_extract() methods and define a _VALID_URL regexp.
|
||||
Probably, they should also be added to the list of extractors.
|
||||
|
||||
_GEO_BYPASS attribute may be set to False in order to disable
|
||||
geo restriction bypass mechanisms for a particular extractor.
|
||||
Though it won't disable explicit geo restriction bypass based on
|
||||
country code provided with geo_bypass_country. (experimental)
|
||||
|
||||
_GEO_COUNTRIES attribute may contain a list of presumably geo unrestricted
|
||||
countries for this extractor. One of these countries will be used by
|
||||
geo restriction bypass mechanism right away in order to bypass
|
||||
geo restriction, of course, if the mechanism is not disabled. (experimental)
|
||||
|
||||
NB: both these geo attributes are experimental and may change in future
|
||||
or be completely removed.
|
||||
|
||||
Finally, the _WORKING attribute should be set to False for broken IEs
|
||||
in order to warn the users and skip the tests.
|
||||
"""
|
||||
|
||||
_ready = False
|
||||
_downloader = None
|
||||
_x_forwarded_for_ip = None
|
||||
_GEO_BYPASS = True
|
||||
_GEO_COUNTRIES = None
|
||||
_WORKING = True
|
||||
|
||||
def __init__(self, downloader=None):
|
||||
"""Constructor. Receives an optional downloader."""
|
||||
self._ready = False
|
||||
self._x_forwarded_for_ip = None
|
||||
self.set_downloader(downloader)
|
||||
|
||||
@classmethod
|
||||
@ -359,15 +379,59 @@ class InfoExtractor(object):
|
||||
|
||||
def initialize(self):
|
||||
"""Initializes an instance (authentication, etc)."""
|
||||
self._initialize_geo_bypass(self._GEO_COUNTRIES)
|
||||
if not self._ready:
|
||||
self._real_initialize()
|
||||
self._ready = True
|
||||
|
||||
def _initialize_geo_bypass(self, countries):
|
||||
"""
|
||||
Initialize geo restriction bypass mechanism.
|
||||
|
||||
This method is used to initialize geo bypass mechanism based on faking
|
||||
X-Forwarded-For HTTP header. A random country from provided country list
|
||||
is selected and a random IP belonging to this country is generated. This
|
||||
IP will be passed as X-Forwarded-For HTTP header in all subsequent
|
||||
HTTP requests.
|
||||
|
||||
This method will be used for initial geo bypass mechanism initialization
|
||||
during the instance initialization with _GEO_COUNTRIES.
|
||||
|
||||
You may also manually call it from extractor's code if geo countries
|
||||
information is not available beforehand (e.g. obtained during
|
||||
extraction) or due to some another reason.
|
||||
"""
|
||||
if not self._x_forwarded_for_ip:
|
||||
country_code = self._downloader.params.get('geo_bypass_country', None)
|
||||
# If there is no explicit country for geo bypass specified and
|
||||
# the extractor is known to be geo restricted let's fake IP
|
||||
# as X-Forwarded-For right away.
|
||||
if (not country_code and
|
||||
self._GEO_BYPASS and
|
||||
self._downloader.params.get('geo_bypass', True) and
|
||||
countries):
|
||||
country_code = random.choice(countries)
|
||||
if country_code:
|
||||
self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code)
|
||||
if self._downloader.params.get('verbose', False):
|
||||
self._downloader.to_stdout(
|
||||
'[debug] Using fake IP %s (%s) as X-Forwarded-For.'
|
||||
% (self._x_forwarded_for_ip, country_code.upper()))
|
||||
|
||||
def extract(self, url):
|
||||
"""Extracts URL information and returns it in list of dicts."""
|
||||
try:
|
||||
self.initialize()
|
||||
return self._real_extract(url)
|
||||
for _ in range(2):
|
||||
try:
|
||||
self.initialize()
|
||||
ie_result = self._real_extract(url)
|
||||
if self._x_forwarded_for_ip:
|
||||
ie_result['__x_forwarded_for_ip'] = self._x_forwarded_for_ip
|
||||
return ie_result
|
||||
except GeoRestrictedError as e:
|
||||
if self.__maybe_fake_ip_and_retry(e.countries):
|
||||
continue
|
||||
raise
|
||||
except ExtractorError:
|
||||
raise
|
||||
except compat_http_client.IncompleteRead as e:
|
||||
@ -375,6 +439,21 @@ class InfoExtractor(object):
|
||||
except (KeyError, StopIteration) as e:
|
||||
raise ExtractorError('An extractor error has occurred.', cause=e)
|
||||
|
||||
def __maybe_fake_ip_and_retry(self, countries):
|
||||
if (not self._downloader.params.get('geo_bypass_country', None) and
|
||||
self._GEO_BYPASS and
|
||||
self._downloader.params.get('geo_bypass', True) and
|
||||
not self._x_forwarded_for_ip and
|
||||
countries):
|
||||
country_code = random.choice(countries)
|
||||
self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code)
|
||||
if self._x_forwarded_for_ip:
|
||||
self.report_warning(
|
||||
'Video is geo restricted. Retrying extraction with fake IP %s (%s) as X-Forwarded-For.'
|
||||
% (self._x_forwarded_for_ip, country_code.upper()))
|
||||
return True
|
||||
return False
|
||||
|
||||
def set_downloader(self, downloader):
|
||||
"""Sets the downloader for this IE."""
|
||||
self._downloader = downloader
|
||||
@ -434,6 +513,15 @@ class InfoExtractor(object):
|
||||
if isinstance(url_or_request, (compat_str, str)):
|
||||
url_or_request = url_or_request.partition('#')[0]
|
||||
|
||||
# Some sites check X-Forwarded-For HTTP header in order to figure out
|
||||
# the origin of the client behind proxy. This allows bypassing geo
|
||||
# restriction by faking this header's value to IP that belongs to some
|
||||
# geo unrestricted country. We will do so once we encounter any
|
||||
# geo restriction error.
|
||||
if self._x_forwarded_for_ip:
|
||||
if 'X-Forwarded-For' not in headers:
|
||||
headers['X-Forwarded-For'] = self._x_forwarded_for_ip
|
||||
|
||||
urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query)
|
||||
if urlh is False:
|
||||
assert not fatal
|
||||
@ -609,10 +697,8 @@ class InfoExtractor(object):
|
||||
expected=True)
|
||||
|
||||
@staticmethod
|
||||
def raise_geo_restricted(msg='This video is not available from your location due to geo restriction'):
|
||||
raise ExtractorError(
|
||||
'%s. You might want to use --proxy to workaround.' % msg,
|
||||
expected=True)
|
||||
def raise_geo_restricted(msg='This video is not available from your location due to geo restriction', countries=None):
|
||||
raise GeoRestrictedError(msg, countries=countries)
|
||||
|
||||
# Methods for following #608
|
||||
@staticmethod
|
||||
|
@ -1,5 +1,7 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import sys
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
@ -33,7 +35,9 @@ class UnicodeBOMIE(InfoExtractor):
|
||||
IE_DESC = False
|
||||
_VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
|
||||
|
||||
_TESTS = [{
|
||||
# Disable test for python 3.2 since BOM is broken in re in this version
|
||||
# (see https://github.com/rg3/youtube-dl/issues/9751)
|
||||
_TESTS = [] if (3, 0) < sys.version_info <= (3, 3) else [{
|
||||
'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
@ -6,6 +6,7 @@ from ..utils import int_or_none
|
||||
|
||||
|
||||
class CrackleIE(InfoExtractor):
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
|
||||
|
@ -123,7 +123,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
|
||||
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
|
||||
'info_dict': {
|
||||
'id': '645513',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
|
||||
'description': 'md5:2d17137920c64f2f49981a7797d275ef',
|
||||
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
|
||||
@ -192,6 +192,21 @@ class CrunchyrollIE(CrunchyrollBaseIE):
|
||||
# geo-restricted (US), 18+ maturity wall, non-premium available
|
||||
'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# A description with double quotes
|
||||
'url': 'http://www.crunchyroll.com/11eyes/episode-1-piros-jszaka-red-night-535080',
|
||||
'info_dict': {
|
||||
'id': '535080',
|
||||
'ext': 'mp4',
|
||||
'title': '11eyes Episode 1 – Piros éjszaka - Red Night',
|
||||
'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".',
|
||||
'uploader': 'Marvelous AQL Inc.',
|
||||
'upload_date': '20091021',
|
||||
},
|
||||
'params': {
|
||||
# Just test metadata extraction
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
_FORMAT_IDS = {
|
||||
@ -362,9 +377,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
|
||||
webpage, 'video_title')
|
||||
video_title = re.sub(r' {2,}', ' ', video_title)
|
||||
video_description = self._html_search_regex(
|
||||
r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
|
||||
webpage, 'description', default=None)
|
||||
video_description = self._parse_json(self._html_search_regex(
|
||||
r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id,
|
||||
webpage, 'description', default='{}'), video_id).get('description')
|
||||
if video_description:
|
||||
video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
|
||||
video_upload_date = self._html_search_regex(
|
||||
@ -519,11 +534,11 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
|
||||
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
|
||||
webpage, 'title')
|
||||
episode_paths = re.findall(
|
||||
r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
|
||||
r'(?s)<li id="showview_videos_media_(\d+)"[^>]+>.*?<a href="([^"]+)"',
|
||||
webpage)
|
||||
entries = [
|
||||
self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
|
||||
for ep in episode_paths
|
||||
self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll', ep_id)
|
||||
for ep_id, ep in episode_paths
|
||||
]
|
||||
entries.reverse()
|
||||
|
||||
|
@ -66,7 +66,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
'uploader_id': 'xijv66',
|
||||
'age_limit': 0,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
}
|
||||
},
|
||||
# Vevo video
|
||||
@ -140,7 +139,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
|
||||
view_count = str_to_int(view_count_str)
|
||||
comment_count = int_or_none(self._search_regex(
|
||||
r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
|
||||
webpage, 'comment count', fatal=False))
|
||||
webpage, 'comment count', default=None))
|
||||
|
||||
player_v5 = self._search_regex(
|
||||
[r'buildPlayer\(({.+?})\);\n', # See https://github.com/rg3/youtube-dl/issues/7826
|
||||
|
@ -20,6 +20,7 @@ from ..utils import (
|
||||
class DramaFeverBaseIE(AMPIE):
|
||||
_LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
|
||||
_NETRC_MACHINE = 'dramafever'
|
||||
_GEO_COUNTRIES = ['US', 'CA']
|
||||
|
||||
_CONSUMER_SECRET = 'DA59dtVXYLxajktV'
|
||||
|
||||
@ -116,8 +117,9 @@ class DramaFeverIE(DramaFeverBaseIE):
|
||||
'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError):
|
||||
raise ExtractorError(
|
||||
'Currently unavailable in your country.', expected=True)
|
||||
self.raise_geo_restricted(
|
||||
msg='Currently unavailable in your country',
|
||||
countries=self._GEO_COUNTRIES)
|
||||
raise
|
||||
|
||||
series_id, episode_number = video_id.split('.')
|
||||
|
@ -852,6 +852,7 @@ from .shared import (
|
||||
from .showroomlive import ShowRoomLiveIE
|
||||
from .sina import SinaIE
|
||||
from .sixplay import SixPlayIE
|
||||
from .skylinewebcams import SkylineWebcamsIE
|
||||
from .skynewsarabia import (
|
||||
SkyNewsArabiaIE,
|
||||
SkyNewsArabiaArticleIE,
|
||||
@ -1009,6 +1010,7 @@ from .tvc import (
|
||||
)
|
||||
from .tvigle import TvigleIE
|
||||
from .tvland import TVLandIE
|
||||
from .tvn24 import TVN24IE
|
||||
from .tvnoe import TVNoeIE
|
||||
from .tvp import (
|
||||
TVPEmbedIE,
|
||||
|
@ -78,40 +78,60 @@ class GoIE(AdobePassIE):
|
||||
ext = determine_ext(asset_url)
|
||||
if ext == 'm3u8':
|
||||
video_type = video_data.get('type')
|
||||
if video_type == 'lf':
|
||||
data = {
|
||||
'video_id': video_data['id'],
|
||||
'video_type': video_type,
|
||||
'brand': brand,
|
||||
'device': '001',
|
||||
}
|
||||
if video_data.get('accesslevel') == '1':
|
||||
requestor_id = site_info['requestor_id']
|
||||
resource = self._get_mvpd_resource(
|
||||
requestor_id, title, video_id, None)
|
||||
auth = self._extract_mvpd_auth(
|
||||
url, video_id, requestor_id, resource)
|
||||
data.update({
|
||||
'token': auth,
|
||||
'token_type': 'ap',
|
||||
'adobe_requestor_id': requestor_id,
|
||||
})
|
||||
entitlement = self._download_json(
|
||||
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
|
||||
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
|
||||
errors = entitlement.get('errors', {}).get('errors', [])
|
||||
if errors:
|
||||
error_message = ', '.join([error['message'] for error in errors])
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
asset_url += '?' + entitlement['uplynkData']['sessionKey']
|
||||
data = {
|
||||
'video_id': video_data['id'],
|
||||
'video_type': video_type,
|
||||
'brand': brand,
|
||||
'device': '001',
|
||||
}
|
||||
if video_data.get('accesslevel') == '1':
|
||||
requestor_id = site_info['requestor_id']
|
||||
resource = self._get_mvpd_resource(
|
||||
requestor_id, title, video_id, None)
|
||||
auth = self._extract_mvpd_auth(
|
||||
url, video_id, requestor_id, resource)
|
||||
data.update({
|
||||
'token': auth,
|
||||
'token_type': 'ap',
|
||||
'adobe_requestor_id': requestor_id,
|
||||
})
|
||||
else:
|
||||
self._initialize_geo_bypass(['US'])
|
||||
entitlement = self._download_json(
|
||||
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
|
||||
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
|
||||
errors = entitlement.get('errors', {}).get('errors', [])
|
||||
if errors:
|
||||
for error in errors:
|
||||
if error.get('code') == 1002:
|
||||
self.raise_geo_restricted(
|
||||
error['message'], countries=['US'])
|
||||
error_message = ', '.join([error['message'] for error in errors])
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
|
||||
asset_url += '?' + entitlement['uplynkData']['sessionKey']
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
f = {
|
||||
'format_id': format_id,
|
||||
'url': asset_url,
|
||||
'ext': ext,
|
||||
})
|
||||
}
|
||||
if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url):
|
||||
f.update({
|
||||
'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE',
|
||||
'preference': 1,
|
||||
})
|
||||
else:
|
||||
mobj = re.search(r'/(\d+)x(\d+)/', asset_url)
|
||||
if mobj:
|
||||
height = int(mobj.group(2))
|
||||
f.update({
|
||||
'format_id': ('%s-' % format_id if format_id else '') + '%dP' % height,
|
||||
'width': int(mobj.group(1)),
|
||||
'height': height,
|
||||
})
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
|
@ -3,6 +3,7 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
get_element_by_attribute,
|
||||
int_or_none,
|
||||
@ -50,6 +51,33 @@ class InstagramIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# multi video post
|
||||
'url': 'https://www.instagram.com/p/BQ0eAlwhDrw/',
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'id': 'BQ0dSaohpPW',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video 1',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': 'BQ0dTpOhuHT',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video 2',
|
||||
},
|
||||
}, {
|
||||
'info_dict': {
|
||||
'id': 'BQ0dT7RBFeF',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video 3',
|
||||
},
|
||||
}],
|
||||
'info_dict': {
|
||||
'id': 'BQ0eAlwhDrw',
|
||||
'title': 'Post by instagram',
|
||||
'description': 'md5:0f9203fc6a2ce4d228da5754bcf54957',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://instagram.com/p/-Cmh1cukG2/',
|
||||
'only_matching': True,
|
||||
@ -113,6 +141,32 @@ class InstagramIE(InfoExtractor):
|
||||
'timestamp': int_or_none(comment.get('created_at')),
|
||||
} for comment in media.get(
|
||||
'comments', {}).get('nodes', []) if comment.get('text')]
|
||||
if not video_url:
|
||||
edges = try_get(
|
||||
media, lambda x: x['edge_sidecar_to_children']['edges'],
|
||||
list) or []
|
||||
if edges:
|
||||
entries = []
|
||||
for edge_num, edge in enumerate(edges, start=1):
|
||||
node = try_get(edge, lambda x: x['node'], dict)
|
||||
if not node:
|
||||
continue
|
||||
node_video_url = try_get(node, lambda x: x['video_url'], compat_str)
|
||||
if not node_video_url:
|
||||
continue
|
||||
entries.append({
|
||||
'id': node.get('shortcode') or node['id'],
|
||||
'title': 'Video %d' % edge_num,
|
||||
'url': node_video_url,
|
||||
'thumbnail': node.get('display_url'),
|
||||
'width': int_or_none(try_get(node, lambda x: x['dimensions']['width'])),
|
||||
'height': int_or_none(try_get(node, lambda x: x['dimensions']['height'])),
|
||||
'view_count': int_or_none(node.get('video_view_count')),
|
||||
})
|
||||
return self.playlist_result(
|
||||
entries, video_id,
|
||||
'Post by %s' % uploader_id if uploader_id else None,
|
||||
description)
|
||||
|
||||
if not video_url:
|
||||
video_url = self._og_search_video_url(webpage, secure=False)
|
||||
|
@ -8,12 +8,12 @@ from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
js_to_json,
|
||||
sanitized_Request,
|
||||
)
|
||||
|
||||
|
||||
class IPrimaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
|
||||
_GEO_BYPASS = False
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://play.iprima.cz/gondici-s-r-o-33',
|
||||
@ -29,6 +29,10 @@ class IPrimaIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://play.iprima.cz/particka/particka-92',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# geo restricted
|
||||
'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -38,11 +42,13 @@ class IPrimaIE(InfoExtractor):
|
||||
|
||||
video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id')
|
||||
|
||||
req = sanitized_Request(
|
||||
'http://play.iprima.cz/prehravac/init?_infuse=1'
|
||||
'&_ts=%s&productId=%s' % (round(time.time()), video_id))
|
||||
req.add_header('Referer', url)
|
||||
playerpage = self._download_webpage(req, video_id, note='Downloading player')
|
||||
playerpage = self._download_webpage(
|
||||
'http://play.iprima.cz/prehravac/init',
|
||||
video_id, note='Downloading player', query={
|
||||
'_infuse': 1,
|
||||
'_ts': round(time.time()),
|
||||
'productId': video_id,
|
||||
}, headers={'Referer': url})
|
||||
|
||||
formats = []
|
||||
|
||||
@ -82,7 +88,7 @@ class IPrimaIE(InfoExtractor):
|
||||
extract_formats(src)
|
||||
|
||||
if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
|
||||
self.raise_geo_restricted()
|
||||
self.raise_geo_restricted(countries=['CZ'])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
@ -24,6 +24,7 @@ from ..utils import (
|
||||
|
||||
class ITVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
|
||||
_GEO_COUNTRIES = ['GB']
|
||||
_TEST = {
|
||||
'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
|
||||
'info_dict': {
|
||||
@ -98,7 +99,11 @@ class ITVIE(InfoExtractor):
|
||||
headers=headers, data=etree.tostring(req_env))
|
||||
playlist = xpath_element(resp_env, './/Playlist')
|
||||
if playlist is None:
|
||||
fault_code = xpath_text(resp_env, './/faultcode')
|
||||
fault_string = xpath_text(resp_env, './/faultstring')
|
||||
if fault_code == 'InvalidGeoRegion':
|
||||
self.raise_geo_restricted(
|
||||
msg=fault_string, countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string))
|
||||
title = xpath_text(playlist, 'EpisodeTitle', fatal=True)
|
||||
video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)
|
||||
|
@ -16,6 +16,8 @@ class IviIE(InfoExtractor):
|
||||
IE_DESC = 'ivi.ru'
|
||||
IE_NAME = 'ivi'
|
||||
_VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
|
||||
_GEO_BYPASS = False
|
||||
_GEO_COUNTRIES = ['RU']
|
||||
|
||||
_TESTS = [
|
||||
# Single movie
|
||||
@ -91,7 +93,11 @@ class IviIE(InfoExtractor):
|
||||
|
||||
if 'error' in video_json:
|
||||
error = video_json['error']
|
||||
if error['origin'] == 'NoRedisValidData':
|
||||
origin = error['origin']
|
||||
if origin == 'NotAllowedForLocation':
|
||||
self.raise_geo_restricted(
|
||||
msg=error['message'], countries=self._GEO_COUNTRIES)
|
||||
elif origin == 'NoRedisValidData':
|
||||
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
||||
raise ExtractorError(
|
||||
'Unable to download video %s: %s' % (video_id, error['message']),
|
||||
|
@ -30,7 +30,7 @@ from ..utils import (
|
||||
class LeIE(InfoExtractor):
|
||||
IE_DESC = '乐视网'
|
||||
_VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|(?:sports\.le|(?:www\.)?lesports)\.com/(?:match|video))/(?P<id>\d+)\.html'
|
||||
|
||||
_GEO_COUNTRIES = ['CN']
|
||||
_URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
|
||||
|
||||
_TESTS = [{
|
||||
@ -126,10 +126,9 @@ class LeIE(InfoExtractor):
|
||||
if playstatus['status'] == 0:
|
||||
flag = playstatus['flag']
|
||||
if flag == 1:
|
||||
msg = 'Country %s auth error' % playstatus['country']
|
||||
self.raise_geo_restricted()
|
||||
else:
|
||||
msg = 'Generic error. flag = %d' % flag
|
||||
raise ExtractorError(msg, expected=True)
|
||||
raise ExtractorError('Generic error. flag = %d' % flag, expected=True)
|
||||
|
||||
def _real_extract(self, url):
|
||||
media_id = self._match_id(url)
|
||||
|
@ -4,11 +4,13 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
unsmuggle_url,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
@ -20,9 +22,17 @@ class LimelightBaseIE(InfoExtractor):
|
||||
headers = {}
|
||||
if referer:
|
||||
headers['Referer'] = referer
|
||||
return self._download_json(
|
||||
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
|
||||
item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
|
||||
try:
|
||||
return self._download_json(
|
||||
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
|
||||
item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission']
|
||||
if error == 'CountryDisabled':
|
||||
self.raise_geo_restricted()
|
||||
raise ExtractorError(error, expected=True)
|
||||
raise
|
||||
|
||||
def _call_api(self, organization_id, item_id, method):
|
||||
return self._download_json(
|
||||
@ -213,6 +223,7 @@ class LimelightMediaIE(LimelightBaseIE):
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
video_id = self._match_id(url)
|
||||
self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
|
||||
|
||||
pc, mobile, metadata = self._extract(
|
||||
video_id, 'getPlaylistByMediaId',
|
||||
|
@ -260,9 +260,24 @@ class LyndaCourseIE(LyndaBaseIE):
|
||||
course_path = mobj.group('coursepath')
|
||||
course_id = mobj.group('courseid')
|
||||
|
||||
item_template = 'https://www.lynda.com/%s/%%s-4.html' % course_path
|
||||
|
||||
course = self._download_json(
|
||||
'https://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
|
||||
course_id, 'Downloading course JSON')
|
||||
course_id, 'Downloading course JSON', fatal=False)
|
||||
|
||||
if not course:
|
||||
webpage = self._download_webpage(url, course_id)
|
||||
entries = [
|
||||
self.url_result(
|
||||
item_template % video_id, ie=LyndaIE.ie_key(),
|
||||
video_id=video_id)
|
||||
for video_id in re.findall(
|
||||
r'data-video-id=["\'](\d+)', webpage)]
|
||||
return self.playlist_result(
|
||||
entries, course_id,
|
||||
self._og_search_title(webpage, fatal=False),
|
||||
self._og_search_description(webpage))
|
||||
|
||||
if course.get('Status') == 'NotFound':
|
||||
raise ExtractorError(
|
||||
@ -283,7 +298,7 @@ class LyndaCourseIE(LyndaBaseIE):
|
||||
if video_id:
|
||||
entries.append({
|
||||
'_type': 'url_transparent',
|
||||
'url': 'https://www.lynda.com/%s/%s-4.html' % (course_path, video_id),
|
||||
'url': item_template % video_id,
|
||||
'ie_key': LyndaIE.ie_key(),
|
||||
'chapter': chapter.get('Title'),
|
||||
'chapter_number': int_or_none(chapter.get('ChapterIndex')),
|
||||
|
@ -6,12 +6,12 @@ from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_urllib_parse_urlencode,
|
||||
)
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
urlencode_postdata,
|
||||
get_element_by_attribute,
|
||||
mimetype2ext,
|
||||
)
|
||||
@ -50,6 +50,21 @@ class MetacafeIE(InfoExtractor):
|
||||
},
|
||||
'skip': 'Page is temporarily unavailable.',
|
||||
},
|
||||
# metacafe video with family filter
|
||||
{
|
||||
'url': 'http://www.metacafe.com/watch/2155630/adult_art_by_david_hart_156/',
|
||||
'md5': 'b06082c5079bbdcde677a6291fbdf376',
|
||||
'info_dict': {
|
||||
'id': '2155630',
|
||||
'ext': 'mp4',
|
||||
'title': 'Adult Art By David Hart 156',
|
||||
'uploader': '63346',
|
||||
'description': 'md5:9afac8fc885252201ad14563694040fc',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
# AnyClip video
|
||||
{
|
||||
'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
|
||||
@ -112,22 +127,6 @@ class MetacafeIE(InfoExtractor):
|
||||
def report_disclaimer(self):
|
||||
self.to_screen('Retrieving disclaimer')
|
||||
|
||||
def _confirm_age(self):
|
||||
# Retrieve disclaimer
|
||||
self.report_disclaimer()
|
||||
self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
|
||||
|
||||
# Confirm age
|
||||
self.report_age_confirmation()
|
||||
self._download_webpage(
|
||||
self._FILTER_POST, None, False, 'Unable to confirm age',
|
||||
data=urlencode_postdata({
|
||||
'filters': '0',
|
||||
'submit': "Continue - I'm over 18",
|
||||
}), headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded',
|
||||
})
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract id and simplified title from URL
|
||||
video_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
@ -143,13 +142,15 @@ class MetacafeIE(InfoExtractor):
|
||||
if prefix == 'cb':
|
||||
return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
|
||||
|
||||
# self._confirm_age()
|
||||
headers = {
|
||||
# Disable family filter
|
||||
'Cookie': 'user=%s; ' % compat_urllib_parse_urlencode({'ffilter': False})
|
||||
}
|
||||
|
||||
# AnyClip videos require the flashversion cookie so that we get the link
|
||||
# to the mp4 file
|
||||
headers = {}
|
||||
if video_id.startswith('an-'):
|
||||
headers['Cookie'] = 'flashVersion=0;'
|
||||
headers['Cookie'] += 'flashVersion=0; '
|
||||
|
||||
# Retrieve video webpage to extract further information
|
||||
webpage = self._download_webpage(url, video_id, headers=headers)
|
||||
|
@ -2,16 +2,17 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class MGTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
|
||||
IE_DESC = '芒果TV'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
|
||||
'md5': '1bdadcf760a0b90946ca68ee9a2db41a',
|
||||
'md5': 'b1ffc0fc163152acf6beaa81832c9ee7',
|
||||
'info_dict': {
|
||||
'id': '3116640',
|
||||
'ext': 'mp4',
|
||||
@ -21,48 +22,45 @@ class MGTVIE(InfoExtractor):
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
# no tbr extracted from stream_url
|
||||
'url': 'http://www.mgtv.com/v/1/1/f/3324755.html',
|
||||
'url': 'http://www.mgtv.com/b/301817/3826653.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
api_data = self._download_json(
|
||||
'http://v.api.mgtv.com/player/video', video_id,
|
||||
'http://pcweb.api.mgtv.com/player/video', video_id,
|
||||
query={'video_id': video_id},
|
||||
headers=self.geo_verification_headers())['data']
|
||||
info = api_data['info']
|
||||
title = info['title'].strip()
|
||||
stream_domain = api_data['stream_domain'][0]
|
||||
|
||||
formats = []
|
||||
for idx, stream in enumerate(api_data['stream']):
|
||||
stream_url = stream.get('url')
|
||||
if not stream_url:
|
||||
stream_path = stream.get('url')
|
||||
if not stream_path:
|
||||
continue
|
||||
format_data = self._download_json(
|
||||
stream_domain + stream_path, video_id,
|
||||
note='Download video info for format #%d' % idx)
|
||||
format_url = format_data.get('info')
|
||||
if not format_url:
|
||||
continue
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'(\d+)\.mp4', stream_url, 'tbr', default=None))
|
||||
|
||||
def extract_format(stream_url, format_id, idx, query={}):
|
||||
format_info = self._download_json(
|
||||
stream_url, video_id,
|
||||
note='Download video info for format %s' % (format_id or '#%d' % idx),
|
||||
query=query)
|
||||
return {
|
||||
'format_id': format_id,
|
||||
'url': format_info['info'],
|
||||
'ext': 'mp4',
|
||||
'tbr': tbr,
|
||||
}
|
||||
|
||||
formats.append(extract_format(
|
||||
stream_url, 'hls-%d' % tbr if tbr else None, idx * 2))
|
||||
formats.append(extract_format(stream_url.replace(
|
||||
'/playlist.m3u8', ''), 'http-%d' % tbr if tbr else None, idx * 2 + 1, {'pno': 1031}))
|
||||
r'_(\d+)_mp4/', format_url, 'tbr', default=None))
|
||||
formats.append({
|
||||
'format_id': compat_str(tbr or idx),
|
||||
'url': format_url,
|
||||
'ext': 'mp4',
|
||||
'tbr': tbr,
|
||||
'protocol': 'm3u8_native',
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': info['title'].strip(),
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'description': info.get('desc'),
|
||||
'duration': int_or_none(info.get('duration')),
|
||||
|
@ -19,6 +19,7 @@ class NineCNineMediaBaseIE(InfoExtractor):
|
||||
|
||||
class NineCNineMediaStackIE(NineCNineMediaBaseIE):
|
||||
IE_NAME = '9c9media:stack'
|
||||
_GEO_COUNTRIES = ['CA']
|
||||
_VALID_URL = r'9c9media:stack:(?P<destination_code>[^:]+):(?P<content_id>\d+):(?P<content_package>\d+):(?P<id>\d+)'
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -23,7 +23,7 @@ from ..utils import (
|
||||
|
||||
class NocoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
|
||||
_LOGIN_URL = 'http://noco.tv/do.php'
|
||||
_LOGIN_URL = 'https://noco.tv/do.php'
|
||||
_API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
|
||||
_SUB_LANG_TEMPLATE = '&sub_lang=%s'
|
||||
_NETRC_MACHINE = 'noco'
|
||||
@ -69,16 +69,17 @@ class NocoIE(InfoExtractor):
|
||||
if username is None:
|
||||
return
|
||||
|
||||
login_form = {
|
||||
'a': 'login',
|
||||
'cookie': '1',
|
||||
'username': username,
|
||||
'password': password,
|
||||
}
|
||||
request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
|
||||
request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
|
||||
|
||||
login = self._download_json(request, None, 'Logging in as %s' % username)
|
||||
login = self._download_json(
|
||||
self._LOGIN_URL, None, 'Logging in as %s' % username,
|
||||
data=urlencode_postdata({
|
||||
'a': 'login',
|
||||
'cookie': '1',
|
||||
'username': username,
|
||||
'password': password,
|
||||
}),
|
||||
headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
|
||||
})
|
||||
|
||||
if 'erreur' in login:
|
||||
raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
|
||||
|
@ -1,7 +1,6 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import random
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
@ -15,24 +14,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class NRKBaseIE(InfoExtractor):
|
||||
_faked_ip = None
|
||||
|
||||
def _download_webpage_handle(self, *args, **kwargs):
|
||||
# NRK checks X-Forwarded-For HTTP header in order to figure out the
|
||||
# origin of the client behind proxy. This allows to bypass geo
|
||||
# restriction by faking this header's value to some Norway IP.
|
||||
# We will do so once we encounter any geo restriction error.
|
||||
if self._faked_ip:
|
||||
# NB: str is intentional
|
||||
kwargs.setdefault(str('headers'), {})['X-Forwarded-For'] = self._faked_ip
|
||||
return super(NRKBaseIE, self)._download_webpage_handle(*args, **kwargs)
|
||||
|
||||
def _fake_ip(self):
|
||||
# Use fake IP from 37.191.128.0/17 in order to workaround geo
|
||||
# restriction
|
||||
def octet(lb=0, ub=255):
|
||||
return random.randint(lb, ub)
|
||||
self._faked_ip = '37.191.%d.%d' % (octet(128), octet())
|
||||
_GEO_COUNTRIES = ['NO']
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@ -44,8 +26,6 @@ class NRKBaseIE(InfoExtractor):
|
||||
title = data.get('fullTitle') or data.get('mainTitle') or data['title']
|
||||
video_id = data.get('id') or video_id
|
||||
|
||||
http_headers = {'X-Forwarded-For': self._faked_ip} if self._faked_ip else {}
|
||||
|
||||
entries = []
|
||||
|
||||
conviva = data.get('convivaStatistics') or {}
|
||||
@ -90,7 +70,6 @@ class NRKBaseIE(InfoExtractor):
|
||||
'duration': duration,
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
'http_headers': http_headers,
|
||||
})
|
||||
|
||||
if not entries:
|
||||
@ -107,19 +86,17 @@ class NRKBaseIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
if not entries:
|
||||
message_type = data.get('messageType', '')
|
||||
# Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
|
||||
if 'IsGeoBlocked' in message_type and not self._faked_ip:
|
||||
self.report_warning(
|
||||
'Video is geo restricted, trying to fake IP')
|
||||
self._fake_ip()
|
||||
return self._real_extract(url)
|
||||
|
||||
MESSAGES = {
|
||||
'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
|
||||
'ProgramRightsHasExpired': 'Programmet har gått ut',
|
||||
'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
|
||||
}
|
||||
message_type = data.get('messageType', '')
|
||||
# Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
|
||||
if 'IsGeoBlocked' in message_type:
|
||||
self.raise_geo_restricted(
|
||||
msg=MESSAGES.get('ProgramIsGeoBlocked'),
|
||||
countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError(
|
||||
'%s said: %s' % (self.IE_NAME, MESSAGES.get(
|
||||
message_type, message_type)),
|
||||
@ -188,12 +165,12 @@ class NRKIE(NRKBaseIE):
|
||||
https?://
|
||||
(?:
|
||||
(?:www\.)?nrk\.no/video/PS\*|
|
||||
v8-psapi\.nrk\.no/mediaelement/
|
||||
v8[-.]psapi\.nrk\.no/mediaelement/
|
||||
)
|
||||
)
|
||||
(?P<id>[^/?#&]+)
|
||||
(?P<id>[^?#&]+)
|
||||
'''
|
||||
_API_HOST = 'v8.psapi.nrk.no'
|
||||
_API_HOST = 'v8-psapi.nrk.no'
|
||||
_TESTS = [{
|
||||
# video
|
||||
'url': 'http://www.nrk.no/video/PS*150533',
|
||||
@ -219,6 +196,9 @@ class NRKIE(NRKBaseIE):
|
||||
}, {
|
||||
'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
|
||||
'only_matching': True,
|
||||
|
@ -10,6 +10,7 @@ from ..utils import (
|
||||
|
||||
class OnDemandKoreaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ondemandkorea\.com/(?P<id>[^/]+)\.html'
|
||||
_GEO_COUNTRIES = ['US', 'CA']
|
||||
_TEST = {
|
||||
'url': 'http://www.ondemandkorea.com/ask-us-anything-e43.html',
|
||||
'info_dict': {
|
||||
@ -35,7 +36,8 @@ class OnDemandKoreaIE(InfoExtractor):
|
||||
|
||||
if 'msg_block_01.png' in webpage:
|
||||
self.raise_geo_restricted(
|
||||
'This content is not available in your region')
|
||||
msg='This content is not available in your region',
|
||||
countries=self._GEO_COUNTRIES)
|
||||
|
||||
if 'This video is only available to ODK PLUS members.' in webpage:
|
||||
raise ExtractorError(
|
||||
|
@ -72,16 +72,21 @@ class OpenloadIE(InfoExtractor):
|
||||
raise ExtractorError('File not found', expected=True)
|
||||
|
||||
ol_id = self._search_regex(
|
||||
'<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>',
|
||||
'<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
|
||||
webpage, 'openload ID')
|
||||
|
||||
first_two_chars = int(float(ol_id[0:][:2]))
|
||||
first_char = int(ol_id[0])
|
||||
urlcode = []
|
||||
num = 2
|
||||
num = 1
|
||||
|
||||
while num < len(ol_id):
|
||||
key = int(float(ol_id[num + 3:][:2]))
|
||||
urlcode.append((key, compat_chr(int(float(ol_id[num:][:3])) - first_two_chars)))
|
||||
i = ord(ol_id[num])
|
||||
key = 0
|
||||
if i <= 90:
|
||||
key = i - 65
|
||||
elif i >= 97:
|
||||
key = 25 + i - 97
|
||||
urlcode.append((key, compat_chr(int(ol_id[num + 2:num + 5]) // int(ol_id[num + 1]) - first_char)))
|
||||
num += 5
|
||||
|
||||
video_url = 'https://openload.co/stream/' + ''.join(
|
||||
|
@ -193,6 +193,8 @@ class PBSIE(InfoExtractor):
|
||||
)
|
||||
''' % '|'.join(list(zip(*_STATIONS))[0])
|
||||
|
||||
_GEO_COUNTRIES = ['US']
|
||||
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
|
||||
@ -489,11 +491,13 @@ class PBSIE(InfoExtractor):
|
||||
headers=self.geo_verification_headers())
|
||||
|
||||
if redirect_info['status'] == 'error':
|
||||
message = self._ERRORS.get(
|
||||
redirect_info['http_code'], redirect_info['message'])
|
||||
if redirect_info['http_code'] == 403:
|
||||
self.raise_geo_restricted(
|
||||
msg=message, countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError(
|
||||
'%s said: %s' % (
|
||||
self.IE_NAME,
|
||||
self._ERRORS.get(redirect_info['http_code'], redirect_info['message'])),
|
||||
expected=True)
|
||||
'%s said: %s' % (self.IE_NAME, message), expected=True)
|
||||
|
||||
format_url = redirect_info.get('url')
|
||||
if not format_url:
|
||||
|
@ -424,3 +424,6 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
|
||||
return self._extract_clip(url, webpage)
|
||||
elif page_type == 'playlist':
|
||||
return self._extract_playlist(url, webpage)
|
||||
else:
|
||||
raise ExtractorError(
|
||||
'Unsupported page type %s' % page_type, expected=True)
|
||||
|
42
youtube_dl/extractor/skylinewebcams.py
Normal file
42
youtube_dl/extractor/skylinewebcams.py
Normal file
@ -0,0 +1,42 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class SkylineWebcamsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?skylinewebcams\.com/[^/]+/webcam/(?:[^/]+/)+(?P<id>[^/]+)\.html'
|
||||
_TEST = {
|
||||
'url': 'https://www.skylinewebcams.com/it/webcam/italia/lazio/roma/scalinata-piazza-di-spagna-barcaccia.html',
|
||||
'info_dict': {
|
||||
'id': 'scalinata-piazza-di-spagna-barcaccia',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^Live Webcam Scalinata di Piazza di Spagna - La Barcaccia [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'description': 'Roma, veduta sulla Scalinata di Piazza di Spagna e sulla Barcaccia',
|
||||
'is_live': True,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
stream_url = self._search_regex(
|
||||
r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage,
|
||||
'stream url', group='url')
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': stream_url,
|
||||
'ext': 'mp4',
|
||||
'title': self._live_title(title),
|
||||
'description': description,
|
||||
'is_live': True,
|
||||
}
|
@ -108,12 +108,11 @@ class SohuIE(InfoExtractor):
|
||||
if vid_data['play'] != 1:
|
||||
if vid_data.get('status') == 12:
|
||||
raise ExtractorError(
|
||||
'Sohu said: There\'s something wrong in the video.',
|
||||
'%s said: There\'s something wrong in the video.' % self.IE_NAME,
|
||||
expected=True)
|
||||
else:
|
||||
raise ExtractorError(
|
||||
'Sohu said: The video is only licensed to users in Mainland China.',
|
||||
expected=True)
|
||||
self.raise_geo_restricted(
|
||||
'%s said: The video is only licensed to users in Mainland China.' % self.IE_NAME)
|
||||
|
||||
formats_json = {}
|
||||
for format_id in ('nor', 'high', 'super', 'ori', 'h2644k', 'h2654k'):
|
||||
|
@ -23,6 +23,10 @@ class SpankBangIE(InfoExtractor):
|
||||
# 480p only
|
||||
'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# no uploader
|
||||
'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -48,7 +52,7 @@ class SpankBangIE(InfoExtractor):
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
uploader = self._search_regex(
|
||||
r'class="user"[^>]*><img[^>]+>([^<]+)',
|
||||
webpage, 'uploader', fatal=False)
|
||||
webpage, 'uploader', default=None)
|
||||
|
||||
age_limit = self._rta_search(webpage)
|
||||
|
||||
|
@ -14,6 +14,8 @@ from ..utils import (
|
||||
|
||||
class SRGSSRIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
|
||||
_GEO_BYPASS = False
|
||||
_GEO_COUNTRIES = ['CH']
|
||||
|
||||
_ERRORS = {
|
||||
'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
|
||||
@ -40,8 +42,12 @@ class SRGSSRIE(InfoExtractor):
|
||||
media_id)[media_type.capitalize()]
|
||||
|
||||
if media_data.get('block') and media_data['block'] in self._ERRORS:
|
||||
raise ExtractorError('%s said: %s' % (
|
||||
self.IE_NAME, self._ERRORS[media_data['block']]), expected=True)
|
||||
message = self._ERRORS[media_data['block']]
|
||||
if media_data['block'] == 'GEOBLOCK':
|
||||
self.raise_geo_restricted(
|
||||
msg=message, countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError(
|
||||
'%s said: %s' % (self.IE_NAME, message), expected=True)
|
||||
|
||||
return media_data
|
||||
|
||||
|
@ -13,6 +13,8 @@ from ..utils import (
|
||||
|
||||
|
||||
class SVTBaseIE(InfoExtractor):
|
||||
_GEO_COUNTRIES = ['SE']
|
||||
|
||||
def _extract_video(self, video_info, video_id):
|
||||
formats = []
|
||||
for vr in video_info['videoReferences']:
|
||||
@ -38,7 +40,9 @@ class SVTBaseIE(InfoExtractor):
|
||||
'url': vurl,
|
||||
})
|
||||
if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
|
||||
self.raise_geo_restricted('This video is only available in Sweden')
|
||||
self.raise_geo_restricted(
|
||||
'This video is only available in Sweden',
|
||||
countries=self._GEO_COUNTRIES)
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
|
@ -2,7 +2,10 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
smuggle_url,
|
||||
)
|
||||
|
||||
|
||||
class TeleQuebecIE(InfoExtractor):
|
||||
@ -28,7 +31,7 @@ class TeleQuebecIE(InfoExtractor):
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': media_id,
|
||||
'url': 'limelight:media:' + media_data['streamInfo']['sourceId'],
|
||||
'url': smuggle_url('limelight:media:' + media_data['streamInfo']['sourceId'], {'geo_countries': ['CA']}),
|
||||
'title': media_data['title'],
|
||||
'description': media_data.get('descriptions', [{'text': None}])[0].get('text'),
|
||||
'duration': int_or_none(media_data.get('durationInMilliseconds'), 1000),
|
||||
|
@ -8,10 +8,12 @@ from ..utils import (
|
||||
HEADRequest,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
clean_html,
|
||||
)
|
||||
|
||||
|
||||
class TFOIE(InfoExtractor):
|
||||
_GEO_COUNTRIES = ['CA']
|
||||
_VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
|
||||
@ -36,7 +38,9 @@ class TFOIE(InfoExtractor):
|
||||
'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
|
||||
})
|
||||
if infos.get('success') == 0:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, infos['msg']), expected=True)
|
||||
if infos.get('code') == 'ErrGeoBlocked':
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True)
|
||||
video_data = infos['data']
|
||||
|
||||
return {
|
||||
|
@ -3,7 +3,10 @@ from __future__ import unicode_literals
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import qualities
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
qualities,
|
||||
)
|
||||
|
||||
|
||||
class TheSceneIE(InfoExtractor):
|
||||
@ -16,6 +19,11 @@ class TheSceneIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear',
|
||||
'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear',
|
||||
'duration': 127,
|
||||
'series': 'Style.com Fashion Shows',
|
||||
'season': 'Ready To Wear Spring 2013',
|
||||
'tags': list,
|
||||
'categories': list,
|
||||
},
|
||||
}
|
||||
|
||||
@ -32,21 +40,29 @@ class TheSceneIE(InfoExtractor):
|
||||
player = self._download_webpage(player_url, display_id)
|
||||
info = self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'),
|
||||
r'(?m)video\s*:\s*({.+?}),$', player, 'info json'),
|
||||
display_id)
|
||||
|
||||
video_id = info['id']
|
||||
title = info['title']
|
||||
|
||||
qualities_order = qualities(('low', 'high'))
|
||||
formats = [{
|
||||
'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
|
||||
'url': f['src'],
|
||||
'quality': qualities_order(f['quality']),
|
||||
} for f in info['sources'][0]]
|
||||
} for f in info['sources']]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': info['id'],
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': info['title'],
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': info.get('poster_frame'),
|
||||
'duration': int_or_none(info.get('duration')),
|
||||
'series': info.get('series_title'),
|
||||
'season': info.get('season_title'),
|
||||
'tags': info.get('tags'),
|
||||
'categories': info.get('categories'),
|
||||
}
|
||||
|
@ -10,6 +10,7 @@ from ..utils import remove_end
|
||||
class ThisAVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
|
||||
_TESTS = [{
|
||||
# jwplayer
|
||||
'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
|
||||
'md5': '0480f1ef3932d901f0e0e719f188f19b',
|
||||
'info_dict': {
|
||||
@ -20,6 +21,7 @@ class ThisAVIE(InfoExtractor):
|
||||
'uploader_id': 'dj7970'
|
||||
}
|
||||
}, {
|
||||
# html5 media
|
||||
'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
|
||||
'md5': 'ba90c076bd0f80203679e5b60bf523ee',
|
||||
'info_dict': {
|
||||
@ -48,8 +50,12 @@ class ThisAVIE(InfoExtractor):
|
||||
}],
|
||||
}
|
||||
else:
|
||||
info_dict = self._extract_jwplayer_data(
|
||||
webpage, video_id, require_title=False)
|
||||
entries = self._parse_html5_media_entries(url, webpage, video_id)
|
||||
if entries:
|
||||
info_dict = entries[0]
|
||||
else:
|
||||
info_dict = self._extract_jwplayer_data(
|
||||
webpage, video_id, require_title=False)
|
||||
uploader = self._html_search_regex(
|
||||
r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
|
||||
webpage, 'uploader name', fatal=False)
|
||||
|
@ -16,6 +16,7 @@ class TubiTvIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/video/(?P<id>[0-9]+)'
|
||||
_LOGIN_URL = 'http://tubitv.com/login'
|
||||
_NETRC_MACHINE = 'tubitv'
|
||||
_GEO_COUNTRIES = ['US']
|
||||
_TEST = {
|
||||
'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
|
||||
'md5': '43ac06be9326f41912dc64ccf7a80320',
|
||||
|
@ -24,6 +24,7 @@ class TV4IE(InfoExtractor):
|
||||
sport/|
|
||||
)
|
||||
)(?P<id>[0-9]+)'''
|
||||
_GEO_COUNTRIES = ['SE']
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650',
|
||||
@ -71,16 +72,12 @@ class TV4IE(InfoExtractor):
|
||||
'http://www.tv4play.se/player/assets/%s.json' % video_id,
|
||||
video_id, 'Downloading video info JSON')
|
||||
|
||||
# If is_geo_restricted is true, it doesn't necessarily mean we can't download it
|
||||
if info.get('is_geo_restricted'):
|
||||
self.report_warning('This content might not be available in your country due to licensing restrictions.')
|
||||
|
||||
title = info['title']
|
||||
|
||||
subtitles = {}
|
||||
formats = []
|
||||
# http formats are linked with unresolvable host
|
||||
for kind in ('hls', ''):
|
||||
for kind in ('hls3', ''):
|
||||
data = self._download_json(
|
||||
'https://prima.tv4play.se/api/web/asset/%s/play.json' % video_id,
|
||||
video_id, 'Downloading sources JSON', query={
|
||||
@ -113,6 +110,10 @@ class TV4IE(InfoExtractor):
|
||||
'url': manifest_url,
|
||||
'ext': 'vtt',
|
||||
}]})
|
||||
|
||||
if not formats and info.get('is_geo_restricted'):
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
|
76
youtube_dl/extractor/tvn24.py
Normal file
76
youtube_dl/extractor/tvn24.py
Normal file
@ -0,0 +1,76 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unescapeHTML,
|
||||
)
|
||||
|
||||
|
||||
class TVN24IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:[^/]+)\.)?tvn24(?:bis)?\.pl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tvn24.pl/wiadomosci-z-kraju,3/oredzie-artura-andrusa,702428.html',
|
||||
'md5': 'fbdec753d7bc29d96036808275f2130c',
|
||||
'info_dict': {
|
||||
'id': '1584444',
|
||||
'ext': 'mp4',
|
||||
'title': '"Święta mają być wesołe, dlatego, ludziska, wszyscy pod jemiołę"',
|
||||
'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości "Szkła kontaktowego".',
|
||||
'thumbnail': 're:http://.*[.]jpeg',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://sport.tvn24.pl/pilka-nozna,105/ligue-1-kamil-glik-rozcial-glowe-monaco-tylko-remisuje-z-bastia,716522.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://tvn24bis.pl/poranek,146,m/gen-koziej-w-tvn24-bis-wracamy-do-czasow-zimnej-wojny,715660.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
|
||||
def extract_json(attr, name, fatal=True):
|
||||
return self._parse_json(
|
||||
self._search_regex(
|
||||
r'\b%s=(["\'])(?P<json>(?!\1).+?)\1' % attr, webpage,
|
||||
name, group='json', fatal=fatal) or '{}',
|
||||
video_id, transform_source=unescapeHTML, fatal=fatal)
|
||||
|
||||
quality_data = extract_json('data-quality', 'formats')
|
||||
|
||||
formats = []
|
||||
for format_id, url in quality_data.items():
|
||||
formats.append({
|
||||
'url': url,
|
||||
'format_id': format_id,
|
||||
'height': int_or_none(format_id.rstrip('p')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._og_search_thumbnail(
|
||||
webpage, default=None) or self._html_search_regex(
|
||||
r'\bdata-poster=(["\'])(?P<url>(?!\1).+?)\1', webpage,
|
||||
'thumbnail', group='url')
|
||||
|
||||
share_params = extract_json(
|
||||
'data-share-params', 'share params', fatal=False)
|
||||
if isinstance(share_params, dict):
|
||||
video_id = share_params.get('id') or video_id
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
}
|
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
class TwentyFourVideoIE(InfoExtractor):
|
||||
IE_NAME = '24video'
|
||||
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex|tube)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.24video.net/video/view/1044982',
|
||||
@ -37,6 +37,9 @@ class TwentyFourVideoIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.24video.me/video/view/1044982',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.24video.tube/video/view/2363750',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -20,6 +20,7 @@ class Vbox7IE(InfoExtractor):
|
||||
)
|
||||
(?P<id>[\da-fA-F]+)
|
||||
'''
|
||||
_GEO_COUNTRIES = ['BG']
|
||||
_TESTS = [{
|
||||
'url': 'http://vbox7.com/play:0946fff23c',
|
||||
'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
|
||||
@ -78,7 +79,7 @@ class Vbox7IE(InfoExtractor):
|
||||
video_url = video['src']
|
||||
|
||||
if '/na.mp4' in video_url:
|
||||
self.raise_geo_restricted()
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
|
||||
uploader = video.get('uploader')
|
||||
|
||||
|
@ -14,6 +14,7 @@ from ..utils import (
|
||||
|
||||
class VGTVIE(XstreamIE):
|
||||
IE_DESC = 'VGTV, BTTV, FTV, Aftenposten and Aftonbladet'
|
||||
_GEO_BYPASS = False
|
||||
|
||||
_HOST_TO_APPNAME = {
|
||||
'vgtv.no': 'vgtv',
|
||||
@ -217,7 +218,8 @@ class VGTVIE(XstreamIE):
|
||||
properties = try_get(
|
||||
data, lambda x: x['streamConfiguration']['properties'], list)
|
||||
if properties and 'geoblocked' in properties:
|
||||
raise self.raise_geo_restricted()
|
||||
raise self.raise_geo_restricted(
|
||||
countries=[host.rpartition('.')[-1].partition('/')[0].upper()])
|
||||
|
||||
self._sort_formats(info['formats'])
|
||||
|
||||
|
@ -70,10 +70,10 @@ class ViceBaseIE(AdobePassIE):
|
||||
'url': uplynk_preplay_url,
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': base.get('body'),
|
||||
'description': base.get('body') or base.get('display_body'),
|
||||
'thumbnail': watch_hub_data.get('cover-image') or watch_hub_data.get('thumbnail'),
|
||||
'duration': parse_duration(video_data.get('video_duration') or watch_hub_data.get('video-duration')),
|
||||
'timestamp': int_or_none(video_data.get('created_at')),
|
||||
'duration': int_or_none(video_data.get('video_duration')) or parse_duration(watch_hub_data.get('video-duration')),
|
||||
'timestamp': int_or_none(video_data.get('created_at'), 1000),
|
||||
'age_limit': parse_age_limit(video_data.get('video_rating')),
|
||||
'series': video_data.get('show_title') or watch_hub_data.get('show-title'),
|
||||
'episode_number': int_or_none(episode.get('episode_number') or watch_hub_data.get('episode')),
|
||||
|
@ -7,16 +7,16 @@ from .vice import ViceBaseIE
|
||||
class VicelandIE(ViceBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?viceland\.com/[^/]+/video/[^/]+/(?P<id>[a-f0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.viceland.com/en_us/video/cyberwar-trailer/57608447973ee7705f6fbd4e',
|
||||
'url': 'https://www.viceland.com/en_us/video/trapped/588a70d0dba8a16007de7316',
|
||||
'info_dict': {
|
||||
'id': '57608447973ee7705f6fbd4e',
|
||||
'id': '588a70d0dba8a16007de7316',
|
||||
'ext': 'mp4',
|
||||
'title': 'CYBERWAR (Trailer)',
|
||||
'description': 'Tapping into the geopolitics of hacking and surveillance, Ben Makuch travels the world to meet with hackers, government officials, and dissidents to investigate the ecosystem of cyberwarfare.',
|
||||
'title': 'TRAPPED (Series Trailer)',
|
||||
'description': 'md5:7a8e95c2b6cd86461502a2845e581ccf',
|
||||
'age_limit': 14,
|
||||
'timestamp': 1466008539,
|
||||
'upload_date': '20160615',
|
||||
'uploader_id': '11',
|
||||
'timestamp': 1485474122,
|
||||
'upload_date': '20170126',
|
||||
'uploader_id': '57a204098cb727dec794c6a3',
|
||||
'uploader': 'Viceland',
|
||||
},
|
||||
'params': {
|
||||
|
@ -13,7 +13,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class VidziIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://vidzi.tv/cghql9yq6emu.html',
|
||||
'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
|
||||
@ -29,6 +29,9 @@ class VidziIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
|
||||
'skip_download': True,
|
||||
}, {
|
||||
'url': 'http://vidzi.cc/cghql9yq6emu.html',
|
||||
'skip_download': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@ -86,7 +86,9 @@ class ViewsterIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
# Get 'api_token' cookie
|
||||
self._request_webpage(HEADRequest('http://www.viewster.com/'), video_id)
|
||||
self._request_webpage(
|
||||
HEADRequest('http://www.viewster.com/'),
|
||||
video_id, headers=self.geo_verification_headers())
|
||||
cookies = self._get_cookies('http://www.viewster.com/')
|
||||
self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value)
|
||||
|
||||
|
@ -27,6 +27,7 @@ class VikiBaseIE(InfoExtractor):
|
||||
_APP_VERSION = '2.2.5.1428709186'
|
||||
_APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)'
|
||||
|
||||
_GEO_BYPASS = False
|
||||
_NETRC_MACHINE = 'viki'
|
||||
|
||||
_token = None
|
||||
@ -77,8 +78,11 @@ class VikiBaseIE(InfoExtractor):
|
||||
def _check_errors(self, data):
|
||||
for reason, status in data.get('blocking', {}).items():
|
||||
if status and reason in self._ERRORS:
|
||||
message = self._ERRORS[reason]
|
||||
if reason == 'geo':
|
||||
self.raise_geo_restricted(msg=message)
|
||||
raise ExtractorError('%s said: %s' % (
|
||||
self.IE_NAME, self._ERRORS[reason]), expected=True)
|
||||
self.IE_NAME, message), expected=True)
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
@ -228,17 +228,29 @@ def parseOpts(overrideArguments=None):
|
||||
action='store_const', const='::', dest='source_address',
|
||||
help='Make all connections via IPv6',
|
||||
)
|
||||
network.add_option(
|
||||
|
||||
geo = optparse.OptionGroup(parser, 'Geo Restriction')
|
||||
geo.add_option(
|
||||
'--geo-verification-proxy',
|
||||
dest='geo_verification_proxy', default=None, metavar='URL',
|
||||
help='Use this proxy to verify the IP address for some geo-restricted sites. '
|
||||
'The default proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading.'
|
||||
)
|
||||
network.add_option(
|
||||
'The default proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading.')
|
||||
geo.add_option(
|
||||
'--cn-verification-proxy',
|
||||
dest='cn_verification_proxy', default=None, metavar='URL',
|
||||
help=optparse.SUPPRESS_HELP,
|
||||
)
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
geo.add_option(
|
||||
'--geo-bypass',
|
||||
action='store_true', dest='geo_bypass', default=True,
|
||||
help='Bypass geographic restriction via faking X-Forwarded-For HTTP header (experimental)')
|
||||
geo.add_option(
|
||||
'--no-geo-bypass',
|
||||
action='store_false', dest='geo_bypass', default=True,
|
||||
help='Do not bypass geographic restriction via faking X-Forwarded-For HTTP header (experimental)')
|
||||
geo.add_option(
|
||||
'--geo-bypass-country', metavar='CODE',
|
||||
dest='geo_bypass_country', default=None,
|
||||
help='Force bypass geographic restriction with explicitly provided two-letter ISO 3166-2 country code (experimental)')
|
||||
|
||||
selection = optparse.OptionGroup(parser, 'Video Selection')
|
||||
selection.add_option(
|
||||
@ -302,8 +314,10 @@ def parseOpts(overrideArguments=None):
|
||||
'match if the key is present, '
|
||||
'!key to check if the key is not present, '
|
||||
'key > NUMBER (like "comment_count > 12", also works with '
|
||||
'>=, <, <=, !=, =) to compare against a number, and '
|
||||
'& to require multiple matches. '
|
||||
'>=, <, <=, !=, =) to compare against a number, '
|
||||
'key = \'LITERAL\' (like "uploader = \'Mike Smith\'", also works with !=) '
|
||||
'to match against a string literal '
|
||||
'and & to require multiple matches. '
|
||||
'Values which are not known are excluded unless you '
|
||||
'put a question mark (?) after the operator. '
|
||||
'For example, to only match videos that have been liked more than '
|
||||
@ -665,8 +679,8 @@ def parseOpts(overrideArguments=None):
|
||||
help=('Output filename template, see the "OUTPUT TEMPLATE" for all the info'))
|
||||
filesystem.add_option(
|
||||
'--autonumber-size',
|
||||
dest='autonumber_size', metavar='NUMBER', default=5, type=int,
|
||||
help='Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given (default is %default)')
|
||||
dest='autonumber_size', metavar='NUMBER', type=int,
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'--autonumber-start',
|
||||
dest='autonumber_start', metavar='NUMBER', default=1, type=int,
|
||||
@ -678,15 +692,15 @@ def parseOpts(overrideArguments=None):
|
||||
filesystem.add_option(
|
||||
'-A', '--auto-number',
|
||||
action='store_true', dest='autonumber', default=False,
|
||||
help='[deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000')
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'-t', '--title',
|
||||
action='store_true', dest='usetitle', default=False,
|
||||
help='[deprecated] Use title in file name (default)')
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'-l', '--literal', default=False,
|
||||
action='store_true', dest='usetitle',
|
||||
help='[deprecated] Alias of --title')
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'-w', '--no-overwrites',
|
||||
action='store_true', dest='nooverwrites', default=False,
|
||||
@ -834,6 +848,7 @@ def parseOpts(overrideArguments=None):
|
||||
|
||||
parser.add_option_group(general)
|
||||
parser.add_option_group(network)
|
||||
parser.add_option_group(geo)
|
||||
parser.add_option_group(selection)
|
||||
parser.add_option_group(downloader)
|
||||
parser.add_option_group(filesystem)
|
||||
|
@ -536,8 +536,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
|
||||
ext = sub['ext']
|
||||
if ext == new_ext:
|
||||
self._downloader.to_screen(
|
||||
'[ffmpeg] Subtitle file for %s is already in the requested'
|
||||
'format' % new_ext)
|
||||
'[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext)
|
||||
continue
|
||||
old_file = subtitles_filename(filename, lang, ext)
|
||||
sub_filenames.append(old_file)
|
||||
|
@ -23,6 +23,7 @@ import operator
|
||||
import os
|
||||
import pipes
|
||||
import platform
|
||||
import random
|
||||
import re
|
||||
import socket
|
||||
import ssl
|
||||
@ -701,7 +702,12 @@ def bug_reports_message():
|
||||
return msg
|
||||
|
||||
|
||||
class ExtractorError(Exception):
|
||||
class YoutubeDLError(Exception):
|
||||
"""Base exception for YoutubeDL errors."""
|
||||
pass
|
||||
|
||||
|
||||
class ExtractorError(YoutubeDLError):
|
||||
"""Error during info extraction."""
|
||||
|
||||
def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
|
||||
@ -742,7 +748,19 @@ class RegexNotFoundError(ExtractorError):
|
||||
pass
|
||||
|
||||
|
||||
class DownloadError(Exception):
|
||||
class GeoRestrictedError(ExtractorError):
|
||||
"""Geographic restriction Error exception.
|
||||
|
||||
This exception may be thrown when a video is not available from your
|
||||
geographic location due to geographic restrictions imposed by a website.
|
||||
"""
|
||||
def __init__(self, msg, countries=None):
|
||||
super(GeoRestrictedError, self).__init__(msg, expected=True)
|
||||
self.msg = msg
|
||||
self.countries = countries
|
||||
|
||||
|
||||
class DownloadError(YoutubeDLError):
|
||||
"""Download Error exception.
|
||||
|
||||
This exception may be thrown by FileDownloader objects if they are not
|
||||
@ -756,7 +774,7 @@ class DownloadError(Exception):
|
||||
self.exc_info = exc_info
|
||||
|
||||
|
||||
class SameFileError(Exception):
|
||||
class SameFileError(YoutubeDLError):
|
||||
"""Same File exception.
|
||||
|
||||
This exception will be thrown by FileDownloader objects if they detect
|
||||
@ -765,7 +783,7 @@ class SameFileError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class PostProcessingError(Exception):
|
||||
class PostProcessingError(YoutubeDLError):
|
||||
"""Post Processing exception.
|
||||
|
||||
This exception may be raised by PostProcessor's .run() method to
|
||||
@ -773,15 +791,16 @@ class PostProcessingError(Exception):
|
||||
"""
|
||||
|
||||
def __init__(self, msg):
|
||||
super(PostProcessingError, self).__init__(msg)
|
||||
self.msg = msg
|
||||
|
||||
|
||||
class MaxDownloadsReached(Exception):
|
||||
class MaxDownloadsReached(YoutubeDLError):
|
||||
""" --max-downloads limit has been reached. """
|
||||
pass
|
||||
|
||||
|
||||
class UnavailableVideoError(Exception):
|
||||
class UnavailableVideoError(YoutubeDLError):
|
||||
"""Unavailable Format exception.
|
||||
|
||||
This exception will be thrown when a video is requested
|
||||
@ -790,7 +809,7 @@ class UnavailableVideoError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class ContentTooShortError(Exception):
|
||||
class ContentTooShortError(YoutubeDLError):
|
||||
"""Content Too Short exception.
|
||||
|
||||
This exception may be raised by FileDownloader objects when a file they
|
||||
@ -799,12 +818,15 @@ class ContentTooShortError(Exception):
|
||||
"""
|
||||
|
||||
def __init__(self, downloaded, expected):
|
||||
super(ContentTooShortError, self).__init__(
|
||||
'Downloaded {0} bytes, expected {1} bytes'.format(downloaded, expected)
|
||||
)
|
||||
# Both in bytes
|
||||
self.downloaded = downloaded
|
||||
self.expected = expected
|
||||
|
||||
|
||||
class XAttrMetadataError(Exception):
|
||||
class XAttrMetadataError(YoutubeDLError):
|
||||
def __init__(self, code=None, msg='Unknown error'):
|
||||
super(XAttrMetadataError, self).__init__(msg)
|
||||
self.code = code
|
||||
@ -820,7 +842,7 @@ class XAttrMetadataError(Exception):
|
||||
self.reason = 'NOT_SUPPORTED'
|
||||
|
||||
|
||||
class XAttrUnavailableError(Exception):
|
||||
class XAttrUnavailableError(YoutubeDLError):
|
||||
pass
|
||||
|
||||
|
||||
@ -3018,6 +3040,260 @@ class ISO3166Utils(object):
|
||||
return cls._country_map.get(code.upper())
|
||||
|
||||
|
||||
class GeoUtils(object):
|
||||
# Major IPv4 address blocks per country
|
||||
_country_ip_map = {
|
||||
'AD': '85.94.160.0/19',
|
||||
'AE': '94.200.0.0/13',
|
||||
'AF': '149.54.0.0/17',
|
||||
'AG': '209.59.64.0/18',
|
||||
'AI': '204.14.248.0/21',
|
||||
'AL': '46.99.0.0/16',
|
||||
'AM': '46.70.0.0/15',
|
||||
'AO': '105.168.0.0/13',
|
||||
'AP': '159.117.192.0/21',
|
||||
'AR': '181.0.0.0/12',
|
||||
'AS': '202.70.112.0/20',
|
||||
'AT': '84.112.0.0/13',
|
||||
'AU': '1.128.0.0/11',
|
||||
'AW': '181.41.0.0/18',
|
||||
'AZ': '5.191.0.0/16',
|
||||
'BA': '31.176.128.0/17',
|
||||
'BB': '65.48.128.0/17',
|
||||
'BD': '114.130.0.0/16',
|
||||
'BE': '57.0.0.0/8',
|
||||
'BF': '129.45.128.0/17',
|
||||
'BG': '95.42.0.0/15',
|
||||
'BH': '37.131.0.0/17',
|
||||
'BI': '154.117.192.0/18',
|
||||
'BJ': '137.255.0.0/16',
|
||||
'BL': '192.131.134.0/24',
|
||||
'BM': '196.12.64.0/18',
|
||||
'BN': '156.31.0.0/16',
|
||||
'BO': '161.56.0.0/16',
|
||||
'BQ': '161.0.80.0/20',
|
||||
'BR': '152.240.0.0/12',
|
||||
'BS': '24.51.64.0/18',
|
||||
'BT': '119.2.96.0/19',
|
||||
'BW': '168.167.0.0/16',
|
||||
'BY': '178.120.0.0/13',
|
||||
'BZ': '179.42.192.0/18',
|
||||
'CA': '99.224.0.0/11',
|
||||
'CD': '41.243.0.0/16',
|
||||
'CF': '196.32.200.0/21',
|
||||
'CG': '197.214.128.0/17',
|
||||
'CH': '85.0.0.0/13',
|
||||
'CI': '154.232.0.0/14',
|
||||
'CK': '202.65.32.0/19',
|
||||
'CL': '152.172.0.0/14',
|
||||
'CM': '165.210.0.0/15',
|
||||
'CN': '36.128.0.0/10',
|
||||
'CO': '181.240.0.0/12',
|
||||
'CR': '201.192.0.0/12',
|
||||
'CU': '152.206.0.0/15',
|
||||
'CV': '165.90.96.0/19',
|
||||
'CW': '190.88.128.0/17',
|
||||
'CY': '46.198.0.0/15',
|
||||
'CZ': '88.100.0.0/14',
|
||||
'DE': '53.0.0.0/8',
|
||||
'DJ': '197.241.0.0/17',
|
||||
'DK': '87.48.0.0/12',
|
||||
'DM': '192.243.48.0/20',
|
||||
'DO': '152.166.0.0/15',
|
||||
'DZ': '41.96.0.0/12',
|
||||
'EC': '186.68.0.0/15',
|
||||
'EE': '90.190.0.0/15',
|
||||
'EG': '156.160.0.0/11',
|
||||
'ER': '196.200.96.0/20',
|
||||
'ES': '88.0.0.0/11',
|
||||
'ET': '196.188.0.0/14',
|
||||
'EU': '2.16.0.0/13',
|
||||
'FI': '91.152.0.0/13',
|
||||
'FJ': '144.120.0.0/16',
|
||||
'FM': '119.252.112.0/20',
|
||||
'FO': '88.85.32.0/19',
|
||||
'FR': '90.0.0.0/9',
|
||||
'GA': '41.158.0.0/15',
|
||||
'GB': '25.0.0.0/8',
|
||||
'GD': '74.122.88.0/21',
|
||||
'GE': '31.146.0.0/16',
|
||||
'GF': '161.22.64.0/18',
|
||||
'GG': '62.68.160.0/19',
|
||||
'GH': '45.208.0.0/14',
|
||||
'GI': '85.115.128.0/19',
|
||||
'GL': '88.83.0.0/19',
|
||||
'GM': '160.182.0.0/15',
|
||||
'GN': '197.149.192.0/18',
|
||||
'GP': '104.250.0.0/19',
|
||||
'GQ': '105.235.224.0/20',
|
||||
'GR': '94.64.0.0/13',
|
||||
'GT': '168.234.0.0/16',
|
||||
'GU': '168.123.0.0/16',
|
||||
'GW': '197.214.80.0/20',
|
||||
'GY': '181.41.64.0/18',
|
||||
'HK': '113.252.0.0/14',
|
||||
'HN': '181.210.0.0/16',
|
||||
'HR': '93.136.0.0/13',
|
||||
'HT': '148.102.128.0/17',
|
||||
'HU': '84.0.0.0/14',
|
||||
'ID': '39.192.0.0/10',
|
||||
'IE': '87.32.0.0/12',
|
||||
'IL': '79.176.0.0/13',
|
||||
'IM': '5.62.80.0/20',
|
||||
'IN': '117.192.0.0/10',
|
||||
'IO': '203.83.48.0/21',
|
||||
'IQ': '37.236.0.0/14',
|
||||
'IR': '2.176.0.0/12',
|
||||
'IS': '82.221.0.0/16',
|
||||
'IT': '79.0.0.0/10',
|
||||
'JE': '87.244.64.0/18',
|
||||
'JM': '72.27.0.0/17',
|
||||
'JO': '176.29.0.0/16',
|
||||
'JP': '126.0.0.0/8',
|
||||
'KE': '105.48.0.0/12',
|
||||
'KG': '158.181.128.0/17',
|
||||
'KH': '36.37.128.0/17',
|
||||
'KI': '103.25.140.0/22',
|
||||
'KM': '197.255.224.0/20',
|
||||
'KN': '198.32.32.0/19',
|
||||
'KP': '175.45.176.0/22',
|
||||
'KR': '175.192.0.0/10',
|
||||
'KW': '37.36.0.0/14',
|
||||
'KY': '64.96.0.0/15',
|
||||
'KZ': '2.72.0.0/13',
|
||||
'LA': '115.84.64.0/18',
|
||||
'LB': '178.135.0.0/16',
|
||||
'LC': '192.147.231.0/24',
|
||||
'LI': '82.117.0.0/19',
|
||||
'LK': '112.134.0.0/15',
|
||||
'LR': '41.86.0.0/19',
|
||||
'LS': '129.232.0.0/17',
|
||||
'LT': '78.56.0.0/13',
|
||||
'LU': '188.42.0.0/16',
|
||||
'LV': '46.109.0.0/16',
|
||||
'LY': '41.252.0.0/14',
|
||||
'MA': '105.128.0.0/11',
|
||||
'MC': '88.209.64.0/18',
|
||||
'MD': '37.246.0.0/16',
|
||||
'ME': '178.175.0.0/17',
|
||||
'MF': '74.112.232.0/21',
|
||||
'MG': '154.126.0.0/17',
|
||||
'MH': '117.103.88.0/21',
|
||||
'MK': '77.28.0.0/15',
|
||||
'ML': '154.118.128.0/18',
|
||||
'MM': '37.111.0.0/17',
|
||||
'MN': '49.0.128.0/17',
|
||||
'MO': '60.246.0.0/16',
|
||||
'MP': '202.88.64.0/20',
|
||||
'MQ': '109.203.224.0/19',
|
||||
'MR': '41.188.64.0/18',
|
||||
'MS': '208.90.112.0/22',
|
||||
'MT': '46.11.0.0/16',
|
||||
'MU': '105.16.0.0/12',
|
||||
'MV': '27.114.128.0/18',
|
||||
'MW': '105.234.0.0/16',
|
||||
'MX': '187.192.0.0/11',
|
||||
'MY': '175.136.0.0/13',
|
||||
'MZ': '197.218.0.0/15',
|
||||
'NA': '41.182.0.0/16',
|
||||
'NC': '101.101.0.0/18',
|
||||
'NE': '197.214.0.0/18',
|
||||
'NF': '203.17.240.0/22',
|
||||
'NG': '105.112.0.0/12',
|
||||
'NI': '186.76.0.0/15',
|
||||
'NL': '145.96.0.0/11',
|
||||
'NO': '84.208.0.0/13',
|
||||
'NP': '36.252.0.0/15',
|
||||
'NR': '203.98.224.0/19',
|
||||
'NU': '49.156.48.0/22',
|
||||
'NZ': '49.224.0.0/14',
|
||||
'OM': '5.36.0.0/15',
|
||||
'PA': '186.72.0.0/15',
|
||||
'PE': '186.160.0.0/14',
|
||||
'PF': '123.50.64.0/18',
|
||||
'PG': '124.240.192.0/19',
|
||||
'PH': '49.144.0.0/13',
|
||||
'PK': '39.32.0.0/11',
|
||||
'PL': '83.0.0.0/11',
|
||||
'PM': '70.36.0.0/20',
|
||||
'PR': '66.50.0.0/16',
|
||||
'PS': '188.161.0.0/16',
|
||||
'PT': '85.240.0.0/13',
|
||||
'PW': '202.124.224.0/20',
|
||||
'PY': '181.120.0.0/14',
|
||||
'QA': '37.210.0.0/15',
|
||||
'RE': '139.26.0.0/16',
|
||||
'RO': '79.112.0.0/13',
|
||||
'RS': '178.220.0.0/14',
|
||||
'RU': '5.136.0.0/13',
|
||||
'RW': '105.178.0.0/15',
|
||||
'SA': '188.48.0.0/13',
|
||||
'SB': '202.1.160.0/19',
|
||||
'SC': '154.192.0.0/11',
|
||||
'SD': '154.96.0.0/13',
|
||||
'SE': '78.64.0.0/12',
|
||||
'SG': '152.56.0.0/14',
|
||||
'SI': '188.196.0.0/14',
|
||||
'SK': '78.98.0.0/15',
|
||||
'SL': '197.215.0.0/17',
|
||||
'SM': '89.186.32.0/19',
|
||||
'SN': '41.82.0.0/15',
|
||||
'SO': '197.220.64.0/19',
|
||||
'SR': '186.179.128.0/17',
|
||||
'SS': '105.235.208.0/21',
|
||||
'ST': '197.159.160.0/19',
|
||||
'SV': '168.243.0.0/16',
|
||||
'SX': '190.102.0.0/20',
|
||||
'SY': '5.0.0.0/16',
|
||||
'SZ': '41.84.224.0/19',
|
||||
'TC': '65.255.48.0/20',
|
||||
'TD': '154.68.128.0/19',
|
||||
'TG': '196.168.0.0/14',
|
||||
'TH': '171.96.0.0/13',
|
||||
'TJ': '85.9.128.0/18',
|
||||
'TK': '27.96.24.0/21',
|
||||
'TL': '180.189.160.0/20',
|
||||
'TM': '95.85.96.0/19',
|
||||
'TN': '197.0.0.0/11',
|
||||
'TO': '175.176.144.0/21',
|
||||
'TR': '78.160.0.0/11',
|
||||
'TT': '186.44.0.0/15',
|
||||
'TV': '202.2.96.0/19',
|
||||
'TW': '120.96.0.0/11',
|
||||
'TZ': '156.156.0.0/14',
|
||||
'UA': '93.72.0.0/13',
|
||||
'UG': '154.224.0.0/13',
|
||||
'US': '3.0.0.0/8',
|
||||
'UY': '167.56.0.0/13',
|
||||
'UZ': '82.215.64.0/18',
|
||||
'VA': '212.77.0.0/19',
|
||||
'VC': '24.92.144.0/20',
|
||||
'VE': '186.88.0.0/13',
|
||||
'VG': '172.103.64.0/18',
|
||||
'VI': '146.226.0.0/16',
|
||||
'VN': '14.160.0.0/11',
|
||||
'VU': '202.80.32.0/20',
|
||||
'WF': '117.20.32.0/21',
|
||||
'WS': '202.4.32.0/19',
|
||||
'YE': '134.35.0.0/16',
|
||||
'YT': '41.242.116.0/22',
|
||||
'ZA': '41.0.0.0/11',
|
||||
'ZM': '165.56.0.0/13',
|
||||
'ZW': '41.85.192.0/19',
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def random_ipv4(cls, code):
|
||||
block = cls._country_ip_map.get(code.upper())
|
||||
if not block:
|
||||
return None
|
||||
addr, preflen = block.split('/')
|
||||
addr_min = compat_struct_unpack('!L', socket.inet_aton(addr))[0]
|
||||
addr_max = addr_min | (0xffffffff >> int(preflen))
|
||||
return compat_str(socket.inet_ntoa(
|
||||
compat_struct_pack('!L', random.randint(addr_min, addr_max))))
|
||||
|
||||
|
||||
class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
|
||||
def __init__(self, proxies=None):
|
||||
# Set default handlers
|
||||
|
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2017.02.17'
|
||||
__version__ = '2017.02.24.1'
|
||||
|
Reference in New Issue
Block a user