Ismael Mejia
11 years ago
49 changed files with 1682 additions and 159 deletions
Split View
Diff Options
-
+12 -7README.md
-
+5 -1devscripts/bash-completion.in
-
+18 -11devscripts/gh-pages/add-version.py
-
+1 -2devscripts/gh-pages/update-feed.py
-
+33 -0devscripts/gh-pages/update-sites.py
-
+2 -1devscripts/release.sh
-
+6 -6devscripts/youtube_genalgo.py
-
+42 -20test/test_all_urls.py
-
+3 -4test/test_download.py
-
+17 -11youtube_dl/FileDownloader.py
-
+3 -2youtube_dl/PostProcessor.py
-
+18 -5youtube_dl/YoutubeDL.py
-
+21 -5youtube_dl/__init__.py
-
+202 -0youtube_dl/aes.py
-
+20 -2youtube_dl/extractor/__init__.py
-
+75 -0youtube_dl/extractor/addanime.py
-
+166 -0youtube_dl/extractor/appletrailers.py
-
+2 -2youtube_dl/extractor/c56.py
-
+35 -0youtube_dl/extractor/canalc2.py
-
+1 -1youtube_dl/extractor/canalplus.py
-
+58 -0youtube_dl/extractor/cnn.py
-
+13 -3youtube_dl/extractor/common.py
-
+5 -3youtube_dl/extractor/dailymotion.py
-
+74 -0youtube_dl/extractor/daum.py
-
+39 -0youtube_dl/extractor/defense.py
-
+13 -5youtube_dl/extractor/generic.py
-
+2 -2youtube_dl/extractor/googleplus.py
-
+37 -0youtube_dl/extractor/hark.py
-
+6 -2youtube_dl/extractor/ign.py
-
+4 -2youtube_dl/extractor/kankan.py
-
+1 -1youtube_dl/extractor/metacafe.py
-
+55 -0youtube_dl/extractor/metacritic.py
-
+74 -0youtube_dl/extractor/mit.py
-
+73 -0youtube_dl/extractor/naver.py
-
+33 -0youtube_dl/extractor/nbc.py
-
+54 -0youtube_dl/extractor/orf.py
-
+42 -0youtube_dl/extractor/ro220.py
-
+15 -2youtube_dl/extractor/rtlnow.py
-
+90 -0youtube_dl/extractor/sohu.py
-
+73 -0youtube_dl/extractor/trilulilu.py
-
+1 -1youtube_dl/extractor/unistra.py
-
+56 -0youtube_dl/extractor/veehd.py
-
+37 -11youtube_dl/extractor/vimeo.py
-
+0 -1youtube_dl/extractor/wat.py
-
+10 -8youtube_dl/extractor/xhamster.py
-
+14 -4youtube_dl/extractor/youporn.py
-
+63 -26youtube_dl/extractor/youtube.py
-
+57 -7youtube_dl/utils.py
-
+1 -1youtube_dl/version.py
+ 12
- 7
README.md
View File
+ 5
- 1
devscripts/bash-completion.in
View File
+ 18
- 11
devscripts/gh-pages/add-version.py
View File
+ 1
- 2
devscripts/gh-pages/update-feed.py
View File
+ 33
- 0
devscripts/gh-pages/update-sites.py
View File
| @ -0,0 +1,33 @@ | |||
| #!/usr/bin/env python3 | |||
| import sys | |||
| import os | |||
| import textwrap | |||
| # We must be able to import youtube_dl | |||
| sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))) | |||
| import youtube_dl | |||
| def main(): | |||
| with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf: | |||
| template = tmplf.read() | |||
| ie_htmls = [] | |||
| for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME): | |||
| ie_html = '<b>{}</b>'.format(ie.IE_NAME) | |||
| try: | |||
| ie_html += ': {}'.format(ie.IE_DESC) | |||
| except AttributeError: | |||
| pass | |||
| if ie.working() == False: | |||
| ie_html += ' (Currently broken)' | |||
| ie_htmls.append('<li>{}</li>'.format(ie_html)) | |||
| template = template.replace('@SITES@', textwrap.indent('\n'.join(ie_htmls), '\t')) | |||
| with open('supportedsites.html', 'w', encoding='utf-8') as sitesf: | |||
| sitesf.write(template) | |||
| if __name__ == '__main__': | |||
| main() | |||
+ 2
- 1
devscripts/release.sh
View File
+ 6
- 6
devscripts/youtube_genalgo.py
View File
+ 42
- 20
test/test_all_urls.py
View File
+ 3
- 4
test/test_download.py
View File
+ 17
- 11
youtube_dl/FileDownloader.py
View File
+ 3
- 2
youtube_dl/PostProcessor.py
View File
+ 18
- 5
youtube_dl/YoutubeDL.py
View File
+ 21
- 5
youtube_dl/__init__.py
View File
+ 202
- 0
youtube_dl/aes.py
View File
| @ -0,0 +1,202 @@ | |||
| __all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text'] | |||
| import base64 | |||
| from math import ceil | |||
| from .utils import bytes_to_intlist, intlist_to_bytes | |||
| BLOCK_SIZE_BYTES = 16 | |||
| def aes_ctr_decrypt(data, key, counter): | |||
| """ | |||
| Decrypt with aes in counter mode | |||
| @param {int[]} data cipher | |||
| @param {int[]} key 16/24/32-Byte cipher key | |||
| @param {instance} counter Instance whose next_value function (@returns {int[]} 16-Byte block) | |||
| returns the next counter block | |||
| @returns {int[]} decrypted data | |||
| """ | |||
| expanded_key = key_expansion(key) | |||
| block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) | |||
| decrypted_data=[] | |||
| for i in range(block_count): | |||
| counter_block = counter.next_value() | |||
| block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] | |||
| block += [0]*(BLOCK_SIZE_BYTES - len(block)) | |||
| cipher_counter_block = aes_encrypt(counter_block, expanded_key) | |||
| decrypted_data += xor(block, cipher_counter_block) | |||
| decrypted_data = decrypted_data[:len(data)] | |||
| return decrypted_data | |||
| def key_expansion(data): | |||
| """ | |||
| Generate key schedule | |||
| @param {int[]} data 16/24/32-Byte cipher key | |||
| @returns {int[]} 176/208/240-Byte expanded key | |||
| """ | |||
| data = data[:] # copy | |||
| rcon_iteration = 1 | |||
| key_size_bytes = len(data) | |||
| expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES | |||
| while len(data) < expanded_key_size_bytes: | |||
| temp = data[-4:] | |||
| temp = key_schedule_core(temp, rcon_iteration) | |||
| rcon_iteration += 1 | |||
| data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) | |||
| for _ in range(3): | |||
| temp = data[-4:] | |||
| data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) | |||
| if key_size_bytes == 32: | |||
| temp = data[-4:] | |||
| temp = sub_bytes(temp) | |||
| data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) | |||
| for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0): | |||
| temp = data[-4:] | |||
| data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) | |||
| data = data[:expanded_key_size_bytes] | |||
| return data | |||
| def aes_encrypt(data, expanded_key): | |||
| """ | |||
| Encrypt one block with aes | |||
| @param {int[]} data 16-Byte state | |||
| @param {int[]} expanded_key 176/208/240-Byte expanded key | |||
| @returns {int[]} 16-Byte cipher | |||
| """ | |||
| rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 | |||
| data = xor(data, expanded_key[:BLOCK_SIZE_BYTES]) | |||
| for i in range(1, rounds+1): | |||
| data = sub_bytes(data) | |||
| data = shift_rows(data) | |||
| if i != rounds: | |||
| data = mix_columns(data) | |||
| data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]) | |||
| return data | |||
| def aes_decrypt_text(data, password, key_size_bytes): | |||
| """ | |||
| Decrypt text | |||
| - The first 8 Bytes of decoded 'data' are the 8 high Bytes of the counter | |||
| - The cipher key is retrieved by encrypting the first 16 Byte of 'password' | |||
| with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's) | |||
| - Mode of operation is 'counter' | |||
| @param {str} data Base64 encoded string | |||
| @param {str,unicode} password Password (will be encoded with utf-8) | |||
| @param {int} key_size_bytes Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit | |||
| @returns {str} Decrypted data | |||
| """ | |||
| NONCE_LENGTH_BYTES = 8 | |||
| data = bytes_to_intlist(base64.b64decode(data)) | |||
| password = bytes_to_intlist(password.encode('utf-8')) | |||
| key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password)) | |||
| key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES) | |||
| nonce = data[:NONCE_LENGTH_BYTES] | |||
| cipher = data[NONCE_LENGTH_BYTES:] | |||
| class Counter: | |||
| __value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES) | |||
| def next_value(self): | |||
| temp = self.__value | |||
| self.__value = inc(self.__value) | |||
| return temp | |||
| decrypted_data = aes_ctr_decrypt(cipher, key, Counter()) | |||
| plaintext = intlist_to_bytes(decrypted_data) | |||
| return plaintext | |||
| RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36) | |||
| SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76, | |||
| 0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0, | |||
| 0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15, | |||
| 0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75, | |||
| 0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84, | |||
| 0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF, | |||
| 0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8, | |||
| 0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2, | |||
| 0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73, | |||
| 0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB, | |||
| 0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79, | |||
| 0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08, | |||
| 0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A, | |||
| 0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E, | |||
| 0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF, | |||
| 0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16) | |||
| MIX_COLUMN_MATRIX = ((2,3,1,1), | |||
| (1,2,3,1), | |||
| (1,1,2,3), | |||
| (3,1,1,2)) | |||
| def sub_bytes(data): | |||
| return [SBOX[x] for x in data] | |||
| def rotate(data): | |||
| return data[1:] + [data[0]] | |||
| def key_schedule_core(data, rcon_iteration): | |||
| data = rotate(data) | |||
| data = sub_bytes(data) | |||
| data[0] = data[0] ^ RCON[rcon_iteration] | |||
| return data | |||
| def xor(data1, data2): | |||
| return [x^y for x, y in zip(data1, data2)] | |||
| def mix_column(data): | |||
| data_mixed = [] | |||
| for row in range(4): | |||
| mixed = 0 | |||
| for column in range(4): | |||
| addend = data[column] | |||
| if MIX_COLUMN_MATRIX[row][column] in (2,3): | |||
| addend <<= 1 | |||
| if addend > 0xff: | |||
| addend &= 0xff | |||
| addend ^= 0x1b | |||
| if MIX_COLUMN_MATRIX[row][column] == 3: | |||
| addend ^= data[column] | |||
| mixed ^= addend & 0xff | |||
| data_mixed.append(mixed) | |||
| return data_mixed | |||
| def mix_columns(data): | |||
| data_mixed = [] | |||
| for i in range(4): | |||
| column = data[i*4 : (i+1)*4] | |||
| data_mixed += mix_column(column) | |||
| return data_mixed | |||
| def shift_rows(data): | |||
| data_shifted = [] | |||
| for column in range(4): | |||
| for row in range(4): | |||
| data_shifted.append( data[((column + row) & 0b11) * 4 + row] ) | |||
| return data_shifted | |||
| def inc(data): | |||
| data = data[:] # copy | |||
| for i in range(len(data)-1,-1,-1): | |||
| if data[i] == 255: | |||
| data[i] = 0 | |||
| else: | |||
| data[i] = data[i] + 1 | |||
| break | |||
| return data | |||
+ 20
- 2
youtube_dl/extractor/__init__.py
View File
+ 75
- 0
youtube_dl/extractor/addanime.py
View File
| @ -0,0 +1,75 @@ | |||
| import re | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| compat_HTTPError, | |||
| compat_str, | |||
| compat_urllib_parse, | |||
| compat_urllib_parse_urlparse, | |||
| ExtractorError, | |||
| ) | |||
| class AddAnimeIE(InfoExtractor): | |||
| _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)' | |||
| IE_NAME = u'AddAnime' | |||
| _TEST = { | |||
| u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', | |||
| u'file': u'24MR3YO5SAS9.flv', | |||
| u'md5': u'1036a0e0cd307b95bd8a8c3a5c8cfaf1', | |||
| u'info_dict': { | |||
| u"description": u"One Piece 606", | |||
| u"title": u"One Piece 606" | |||
| } | |||
| } | |||
| def _real_extract(self, url): | |||
| try: | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('video_id') | |||
| webpage = self._download_webpage(url, video_id) | |||
| except ExtractorError as ee: | |||
| if not isinstance(ee.cause, compat_HTTPError): | |||
| raise | |||
| redir_webpage = ee.cause.read().decode('utf-8') | |||
| action = self._search_regex( | |||
| r'<form id="challenge-form" action="([^"]+)"', | |||
| redir_webpage, u'Redirect form') | |||
| vc = self._search_regex( | |||
| r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>', | |||
| redir_webpage, u'redirect vc value') | |||
| av = re.search( | |||
| r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);', | |||
| redir_webpage) | |||
| if av is None: | |||
| raise ExtractorError(u'Cannot find redirect math task') | |||
| av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3)) | |||
| parsed_url = compat_urllib_parse_urlparse(url) | |||
| av_val = av_res + len(parsed_url.netloc) | |||
| confirm_url = ( | |||
| parsed_url.scheme + u'://' + parsed_url.netloc + | |||
| action + '?' + | |||
| compat_urllib_parse.urlencode({ | |||
| 'jschl_vc': vc, 'jschl_answer': compat_str(av_val)})) | |||
| self._download_webpage( | |||
| confirm_url, video_id, | |||
| note=u'Confirming after redirect') | |||
| webpage = self._download_webpage(url, video_id) | |||
| video_url = self._search_regex(r"var normal_video_file = '(.*?)';", | |||
| webpage, u'video file URL') | |||
| video_title = self._og_search_title(webpage) | |||
| video_description = self._og_search_description(webpage) | |||
| return { | |||
| '_type': 'video', | |||
| 'id': video_id, | |||
| 'url': video_url, | |||
| 'ext': 'flv', | |||
| 'title': video_title, | |||
| 'description': video_description | |||
| } | |||
+ 166
- 0
youtube_dl/extractor/appletrailers.py
View File
| @ -0,0 +1,166 @@ | |||
| import re | |||
| import xml.etree.ElementTree | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| determine_ext, | |||
| ) | |||
| class AppleTrailersIE(InfoExtractor): | |||
| _VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)' | |||
| _TEST = { | |||
| u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/", | |||
| u"playlist": [ | |||
| { | |||
| u"file": u"manofsteel-trailer4.mov", | |||
| u"md5": u"11874af099d480cc09e103b189805d5f", | |||
| u"info_dict": { | |||
| u"duration": 111, | |||
| u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg", | |||
| u"title": u"Trailer 4", | |||
| u"upload_date": u"20130523", | |||
| u"uploader_id": u"wb", | |||
| }, | |||
| }, | |||
| { | |||
| u"file": u"manofsteel-trailer3.mov", | |||
| u"md5": u"07a0a262aae5afe68120eed61137ab34", | |||
| u"info_dict": { | |||
| u"duration": 182, | |||
| u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg", | |||
| u"title": u"Trailer 3", | |||
| u"upload_date": u"20130417", | |||
| u"uploader_id": u"wb", | |||
| }, | |||
| }, | |||
| { | |||
| u"file": u"manofsteel-trailer.mov", | |||
| u"md5": u"e401fde0813008e3307e54b6f384cff1", | |||
| u"info_dict": { | |||
| u"duration": 148, | |||
| u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg", | |||
| u"title": u"Trailer", | |||
| u"upload_date": u"20121212", | |||
| u"uploader_id": u"wb", | |||
| }, | |||
| }, | |||
| { | |||
| u"file": u"manofsteel-teaser.mov", | |||
| u"md5": u"76b392f2ae9e7c98b22913c10a639c97", | |||
| u"info_dict": { | |||
| u"duration": 93, | |||
| u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg", | |||
| u"title": u"Teaser", | |||
| u"upload_date": u"20120721", | |||
| u"uploader_id": u"wb", | |||
| }, | |||
| } | |||
| ] | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| movie = mobj.group('movie') | |||
| uploader_id = mobj.group('company') | |||
| playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc' | |||
| playlist_snippet = self._download_webpage(playlist_url, movie) | |||
| playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet) | |||
| playlist_html = u'<html>' + playlist_cleaned + u'</html>' | |||
| size_cache = {} | |||
| doc = xml.etree.ElementTree.fromstring(playlist_html) | |||
| playlist = [] | |||
| for li in doc.findall('./div/ul/li'): | |||
| title = li.find('.//h3').text | |||
| video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() | |||
| thumbnail = li.find('.//img').attrib['src'] | |||
| date_el = li.find('.//p') | |||
| upload_date = None | |||
| m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text) | |||
| if m: | |||
| upload_date = u'20' + m.group('year') + m.group('month') + m.group('day') | |||
| runtime_el = date_el.find('./br') | |||
| m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail) | |||
| duration = None | |||
| if m: | |||
| duration = 60 * int(m.group('minutes')) + int(m.group('seconds')) | |||
| formats = [] | |||
| for formats_el in li.findall('.//a'): | |||
| if formats_el.attrib['class'] != 'OverlayPanel': | |||
| continue | |||
| target = formats_el.attrib['target'] | |||
| format_code = formats_el.text | |||
| if 'Automatic' in format_code: | |||
| continue | |||
| size_q = formats_el.attrib['href'] | |||
| size_id = size_q.rpartition('#videos-')[2] | |||
| if size_id not in size_cache: | |||
| size_url = url + size_q | |||
| sizepage_html = self._download_webpage( | |||
| size_url, movie, | |||
| note=u'Downloading size info %s' % size_id, | |||
| errnote=u'Error while downloading size info %s' % size_id, | |||
| ) | |||
| _doc = xml.etree.ElementTree.fromstring(sizepage_html) | |||
| size_cache[size_id] = _doc | |||
| sizepage_doc = size_cache[size_id] | |||
| links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a') | |||
| for vid_a in links: | |||
| href = vid_a.get('href') | |||
| if not href.endswith(target): | |||
| continue | |||
| detail_q = href.partition('#')[0] | |||
| detail_url = url + '/' + detail_q | |||
| m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q) | |||
| detail_id = m.group('detail_id') | |||
| detail_html = self._download_webpage( | |||
| detail_url, movie, | |||
| note=u'Downloading detail %s %s' % (detail_id, size_id), | |||
| errnote=u'Error while downloading detail %s %s' % (detail_id, size_id) | |||
| ) | |||
| detail_doc = xml.etree.ElementTree.fromstring(detail_html) | |||
| movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a') | |||
| assert movie_link_el.get('class') == 'movieLink' | |||
| movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h') | |||
| ext = determine_ext(movie_link) | |||
| assert ext == 'mov' | |||
| formats.append({ | |||
| 'format': format_code, | |||
| 'ext': ext, | |||
| 'url': movie_link, | |||
| }) | |||
| info = { | |||
| '_type': 'video', | |||
| 'id': video_id, | |||
| 'title': title, | |||
| 'formats': formats, | |||
| 'title': title, | |||
| 'duration': duration, | |||
| 'thumbnail': thumbnail, | |||
| 'upload_date': upload_date, | |||
| 'uploader_id': uploader_id, | |||
| 'user_agent': 'QuickTime compatible (youtube-dl)', | |||
| } | |||
| # TODO: Remove when #980 has been merged | |||
| info['url'] = formats[-1]['url'] | |||
| info['ext'] = formats[-1]['ext'] | |||
| playlist.append(info) | |||
| return { | |||
| '_type': 'playlist', | |||
| 'id': movie, | |||
| 'entries': playlist, | |||
| } | |||
+ 2
- 2
youtube_dl/extractor/c56.py
View File
+ 35
- 0
youtube_dl/extractor/canalc2.py
View File
| @ -0,0 +1,35 @@ | |||
| # coding: utf-8 | |||
| import re | |||
| from .common import InfoExtractor | |||
| class Canalc2IE(InfoExtractor): | |||
| _IE_NAME = 'canalc2.tv' | |||
| _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui' | |||
| _TEST = { | |||
| u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui', | |||
| u'file': u'12163.mp4', | |||
| u'md5': u'060158428b650f896c542dfbb3d6487f', | |||
| u'info_dict': { | |||
| u'title': u'Terrasses du Numérique' | |||
| } | |||
| } | |||
| def _real_extract(self, url): | |||
| video_id = re.match(self._VALID_URL, url).group(1) | |||
| webpage = self._download_webpage(url, video_id) | |||
| file_name = self._search_regex( | |||
| r"so\.addVariable\('file','(.*?)'\);", | |||
| webpage, 'file name') | |||
| video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name | |||
| title = self._html_search_regex( | |||
| r'class="evenement8">(.*?)</a>', webpage, u'title') | |||
| return {'id': video_id, | |||
| 'ext': 'mp4', | |||
| 'url': video_url, | |||
| 'title': title, | |||
| } | |||
+ 1
- 1
youtube_dl/extractor/canalplus.py
View File
+ 58
- 0
youtube_dl/extractor/cnn.py
View File
| @ -0,0 +1,58 @@ | |||
| import re | |||
| import xml.etree.ElementTree | |||
| from .common import InfoExtractor | |||
| from ..utils import determine_ext | |||
| class CNNIE(InfoExtractor): | |||
| _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/ | |||
| (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))''' | |||
| _TESTS = [{ | |||
| u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', | |||
| u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4', | |||
| u'md5': u'3e6121ea48df7e2259fe73a0628605c4', | |||
| u'info_dict': { | |||
| u'title': u'Nadal wins 8th French Open title', | |||
| u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', | |||
| }, | |||
| }, | |||
| { | |||
| u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", | |||
| u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4", | |||
| u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e", | |||
| u"info_dict": { | |||
| u"title": "Student's epic speech stuns new freshmen", | |||
| u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"" | |||
| } | |||
| }] | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| path = mobj.group('path') | |||
| page_title = mobj.group('title') | |||
| info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path | |||
| info_xml = self._download_webpage(info_url, page_title) | |||
| info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) | |||
| formats = [] | |||
| for f in info.findall('files/file'): | |||
| mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate']) | |||
| if mf is not None: | |||
| formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text)) | |||
| formats = sorted(formats) | |||
| (_,_,_, video_path) = formats[-1] | |||
| video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path | |||
| thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')]) | |||
| thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails] | |||
| return {'id': info.attrib['id'], | |||
| 'title': info.find('headline').text, | |||
| 'url': video_url, | |||
| 'ext': determine_ext(video_url), | |||
| 'thumbnail': thumbnails[-1][1], | |||
| 'thumbnails': thumbs_dict, | |||
| 'description': info.find('description').text, | |||
| } | |||
+ 13
- 3
youtube_dl/extractor/common.py
View File
+ 5
- 3
youtube_dl/extractor/dailymotion.py
View File
+ 74
- 0
youtube_dl/extractor/daum.py
View File
| @ -0,0 +1,74 @@ | |||
| # encoding: utf-8 | |||
| import re | |||
| import xml.etree.ElementTree | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| compat_urllib_parse, | |||
| determine_ext, | |||
| ) | |||
| class DaumIE(InfoExtractor): | |||
| _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P<id>\d+)' | |||
| IE_NAME = u'daum.net' | |||
| _TEST = { | |||
| u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', | |||
| u'file': u'52554690.mp4', | |||
| u'info_dict': { | |||
| u'title': u'DOTA 2GETHER 시즌2 6회 - 2부', | |||
| u'description': u'DOTA 2GETHER 시즌2 6회 - 2부', | |||
| u'upload_date': u'20130831', | |||
| u'duration': 3868, | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group(1) | |||
| canonical_url = 'http://tvpot.daum.net/v/%s' % video_id | |||
| webpage = self._download_webpage(canonical_url, video_id) | |||
| full_id = self._search_regex(r'<link rel="video_src" href=".+?vid=(.+?)"', | |||
| webpage, u'full id') | |||
| query = compat_urllib_parse.urlencode({'vid': full_id}) | |||
| info_xml = self._download_webpage( | |||
| 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id, | |||
| u'Downloading video info') | |||
| urls_xml = self._download_webpage( | |||
| 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query, | |||
| video_id, u'Downloading video formats info') | |||
| info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) | |||
| urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8')) | |||
| self.to_screen(u'%s: Getting video urls' % video_id) | |||
| formats = [] | |||
| for format_el in urls.findall('result/output_list/output_list'): | |||
| profile = format_el.attrib['profile'] | |||
| format_query = compat_urllib_parse.urlencode({ | |||
| 'vid': full_id, | |||
| 'profile': profile, | |||
| }) | |||
| url_xml = self._download_webpage( | |||
| 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, | |||
| video_id, note=False) | |||
| url_doc = xml.etree.ElementTree.fromstring(url_xml.encode('utf-8')) | |||
| format_url = url_doc.find('result/url').text | |||
| formats.append({ | |||
| 'url': format_url, | |||
| 'ext': determine_ext(format_url), | |||
| 'format_id': profile, | |||
| }) | |||
| info = { | |||
| 'id': video_id, | |||
| 'title': info.find('TITLE').text, | |||
| 'formats': formats, | |||
| 'thumbnail': self._og_search_thumbnail(webpage), | |||
| 'description': info.find('CONTENTS').text, | |||
| 'duration': int(info.find('DURATION').text), | |||
| 'upload_date': info.find('REGDTTM').text[:8], | |||
| } | |||
| # TODO: Remove when #980 has been merged | |||
| info.update(formats[-1]) | |||
| return info | |||
+ 39
- 0
youtube_dl/extractor/defense.py
View File
| @ -0,0 +1,39 @@ | |||
| import re | |||
| import json | |||
| from .common import InfoExtractor | |||
| class DefenseGouvFrIE(InfoExtractor): | |||
| _IE_NAME = 'defense.gouv.fr' | |||
| _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/' | |||
| r'ligthboxvideo/base-de-medias/webtv/(.*)') | |||
| _TEST = { | |||
| u'url': (u'http://www.defense.gouv.fr/layout/set/ligthboxvideo/' | |||
| u'base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1'), | |||
| u'file': u'11213.mp4', | |||
| u'md5': u'75bba6124da7e63d2d60b5244ec9430c', | |||
| "info_dict": { | |||
| "title": "attaque-chimique-syrienne-du-21-aout-2013-1" | |||
| } | |||
| } | |||
| def _real_extract(self, url): | |||
| title = re.match(self._VALID_URL, url).group(1) | |||
| webpage = self._download_webpage(url, title) | |||
| video_id = self._search_regex( | |||
| r"flashvars.pvg_id=\"(\d+)\";", | |||
| webpage, 'ID') | |||
| json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/' | |||
| + video_id) | |||
| info = self._download_webpage(json_url, title, | |||
| 'Downloading JSON config') | |||
| video_url = json.loads(info)['renditions'][0]['url'] | |||
| return {'id': video_id, | |||
| 'ext': 'mp4', | |||
| 'url': video_url, | |||
| 'title': title, | |||
| } | |||
+ 13
- 5
youtube_dl/extractor/generic.py
View File
+ 2
- 2
youtube_dl/extractor/googleplus.py
View File
+ 37
- 0
youtube_dl/extractor/hark.py
View File
| @ -0,0 +1,37 @@ | |||
| # -*- coding: utf-8 -*- | |||
| import re | |||
| import json | |||
| from .common import InfoExtractor | |||
| from ..utils import determine_ext | |||
| class HarkIE(InfoExtractor): | |||
| _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+' | |||
| _TEST = { | |||
| u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', | |||
| u'file': u'mmbzyhkgny.mp3', | |||
| u'md5': u'6783a58491b47b92c7c1af5a77d4cbee', | |||
| u'info_dict': { | |||
| u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013", | |||
| u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', | |||
| u'duration': 11, | |||
| } | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group(1) | |||
| json_url = "http://www.hark.com/clips/%s.json" %(video_id) | |||
| info_json = self._download_webpage(json_url, video_id) | |||
| info = json.loads(info_json) | |||
| final_url = info['url'] | |||
| return {'id': video_id, | |||
| 'url' : final_url, | |||
| 'title': info['name'], | |||
| 'ext': determine_ext(final_url), | |||
| 'description': info['description'], | |||
| 'thumbnail': info['image_original'], | |||
| 'duration': info['duration'], | |||
| } | |||
+ 6
- 2
youtube_dl/extractor/ign.py
View File
+ 4
- 2
youtube_dl/extractor/kankan.py
View File
+ 1
- 1
youtube_dl/extractor/metacafe.py
View File
+ 55
- 0
youtube_dl/extractor/metacritic.py
View File
| @ -0,0 +1,55 @@ | |||
| import re | |||
| import xml.etree.ElementTree | |||
| import operator | |||
| from .common import InfoExtractor | |||
| class MetacriticIE(InfoExtractor): | |||
| _VALID_URL = r'https?://www\.metacritic\.com/.+?/trailers/(?P<id>\d+)' | |||
| _TEST = { | |||
| u'url': u'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222', | |||
| u'file': u'3698222.mp4', | |||
| u'info_dict': { | |||
| u'title': u'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors', | |||
| u'description': u'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.', | |||
| u'duration': 221, | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('id') | |||
| webpage = self._download_webpage(url, video_id) | |||
| # The xml is not well formatted, there are raw '&' | |||
| info_xml = self._download_webpage('http://www.metacritic.com/video_data?video=' + video_id, | |||
| video_id, u'Downloading info xml').replace('&', '&') | |||
| info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) | |||
| clip = next(c for c in info.findall('playList/clip') if c.find('id').text == video_id) | |||
| formats = [] | |||
| for videoFile in clip.findall('httpURI/videoFile'): | |||
| rate_str = videoFile.find('rate').text | |||
| video_url = videoFile.find('filePath').text | |||
| formats.append({ | |||
| 'url': video_url, | |||
| 'ext': 'mp4', | |||
| 'format_id': rate_str, | |||
| 'rate': int(rate_str), | |||
| }) | |||
| formats.sort(key=operator.itemgetter('rate')) | |||
| description = self._html_search_regex(r'<b>Description:</b>(.*?)</p>', | |||
| webpage, u'description', flags=re.DOTALL) | |||
| info = { | |||
| 'id': video_id, | |||
| 'title': clip.find('title').text, | |||
| 'formats': formats, | |||
| 'description': description, | |||
| 'duration': int(clip.find('duration').text), | |||
| } | |||
| # TODO: Remove when #980 has been merged | |||
| info.update(formats[-1]) | |||
| return info | |||
+ 74
- 0
youtube_dl/extractor/mit.py
View File
| @ -0,0 +1,74 @@ | |||
| import re | |||
| import json | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| clean_html, | |||
| get_element_by_id, | |||
| ) | |||
| class TechTVMITIE(InfoExtractor): | |||
| IE_NAME = u'techtv.mit.edu' | |||
| _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)' | |||
| _TEST = { | |||
| u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set', | |||
| u'file': u'25418.mp4', | |||
| u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f', | |||
| u'info_dict': { | |||
| u'title': u'MIT DNA Learning Center Set', | |||
| u'description': u'md5:82313335e8a8a3f243351ba55bc1b474', | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('id') | |||
| raw_page = self._download_webpage( | |||
| 'http://techtv.mit.edu/videos/%s' % video_id, video_id) | |||
| clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page) | |||
| base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)', | |||
| raw_page, u'base url') | |||
| formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page, | |||
| u'video formats') | |||
| formats = json.loads(formats_json) | |||
| formats = sorted(formats, key=lambda f: f['bitrate']) | |||
| title = get_element_by_id('edit-title', clean_page) | |||
| description = clean_html(get_element_by_id('edit-description', clean_page)) | |||
| thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'', | |||
| raw_page, u'thumbnail', flags=re.DOTALL) | |||
| return {'id': video_id, | |||
| 'title': title, | |||
| 'url': base_url + formats[-1]['url'].replace('mp4:', ''), | |||
| 'ext': 'mp4', | |||
| 'description': description, | |||
| 'thumbnail': thumbnail, | |||
| } | |||
| class MITIE(TechTVMITIE): | |||
| IE_NAME = u'video.mit.edu' | |||
| _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)' | |||
| _TEST = { | |||
| u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/', | |||
| u'file': u'21783.mp4', | |||
| u'md5': u'7db01d5ccc1895fc5010e9c9e13648da', | |||
| u'info_dict': { | |||
| u'title': u'The Government is Profiling You', | |||
| u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd', | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| page_title = mobj.group('title') | |||
| webpage = self._download_webpage(url, page_title) | |||
| self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME)) | |||
| embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage, | |||
| u'embed url') | |||
| return self.url_result(embed_url, ie='TechTVMIT') | |||
+ 73
- 0
youtube_dl/extractor/naver.py
View File
| @ -0,0 +1,73 @@ | |||
| # encoding: utf-8 | |||
| import re | |||
| import xml.etree.ElementTree | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| compat_urllib_parse, | |||
| ExtractorError, | |||
| ) | |||
| class NaverIE(InfoExtractor): | |||
| _VALID_URL = r'https?://tvcast\.naver\.com/v/(?P<id>\d+)' | |||
| _TEST = { | |||
| u'url': u'http://tvcast.naver.com/v/81652', | |||
| u'file': u'81652.mp4', | |||
| u'info_dict': { | |||
| u'title': u'[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번', | |||
| u'description': u'합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', | |||
| u'upload_date': u'20130903', | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group(1) | |||
| webpage = self._download_webpage(url, video_id) | |||
| m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"', | |||
| webpage) | |||
| if m_id is None: | |||
| raise ExtractorError(u'couldn\'t extract vid and key') | |||
| vid = m_id.group(1) | |||
| key = m_id.group(2) | |||
| query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,}) | |||
| query_urls = compat_urllib_parse.urlencode({ | |||
| 'masterVid': vid, | |||
| 'protocol': 'p2p', | |||
| 'inKey': key, | |||
| }) | |||
| info_xml = self._download_webpage( | |||
| 'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query, | |||
| video_id, u'Downloading video info') | |||
| urls_xml = self._download_webpage( | |||
| 'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls, | |||
| video_id, u'Downloading video formats info') | |||
| info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) | |||
| urls = xml.etree.ElementTree.fromstring(urls_xml.encode('utf-8')) | |||
| formats = [] | |||
| for format_el in urls.findall('EncodingOptions/EncodingOption'): | |||
| domain = format_el.find('Domain').text | |||
| if domain.startswith('rtmp'): | |||
| continue | |||
| formats.append({ | |||
| 'url': domain + format_el.find('uri').text, | |||
| 'ext': 'mp4', | |||
| 'width': int(format_el.find('width').text), | |||
| 'height': int(format_el.find('height').text), | |||
| }) | |||
| info = { | |||
| 'id': video_id, | |||
| 'title': info.find('Subject').text, | |||
| 'formats': formats, | |||
| 'description': self._og_search_description(webpage), | |||
| 'thumbnail': self._og_search_thumbnail(webpage), | |||
| 'upload_date': info.find('WriteDate').text.replace('.', ''), | |||
| 'view_count': int(info.find('PlayCount').text), | |||
| } | |||
| # TODO: Remove when #980 has been merged | |||
| info.update(formats[-1]) | |||
| return info | |||
+ 33
- 0
youtube_dl/extractor/nbc.py
View File
| @ -0,0 +1,33 @@ | |||
| import re | |||
| import xml.etree.ElementTree | |||
| from .common import InfoExtractor | |||
| from ..utils import find_xpath_attr, compat_str | |||
| class NBCNewsIE(InfoExtractor): | |||
| _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)' | |||
| _TEST = { | |||
| u'url': u'http://www.nbcnews.com/video/nbc-news/52753292', | |||
| u'file': u'52753292.flv', | |||
| u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179', | |||
| u'info_dict': { | |||
| u'title': u'Crew emerges after four-month Mars food study', | |||
| u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1', | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('id') | |||
| info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id) | |||
| info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video') | |||
| return {'id': video_id, | |||
| 'title': info.find('headline').text, | |||
| 'ext': 'flv', | |||
| 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, | |||
| 'description': compat_str(info.find('caption').text), | |||
| 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, | |||
| } | |||
+ 54
- 0
youtube_dl/extractor/orf.py
View File
| @ -0,0 +1,54 @@ | |||
| # coding: utf-8 | |||
| import re | |||
| import xml.etree.ElementTree | |||
| import json | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| compat_urlparse, | |||
| ExtractorError, | |||
| find_xpath_attr, | |||
| ) | |||
| class ORFIE(InfoExtractor): | |||
| _VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)' | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| playlist_id = mobj.group('id') | |||
| webpage = self._download_webpage(url, playlist_id) | |||
| flash_xml = self._search_regex('ORF.flashXML = \'(.+?)\'', webpage, u'flash xml') | |||
| flash_xml = compat_urlparse.parse_qs('xml='+flash_xml)['xml'][0] | |||
| flash_config = xml.etree.ElementTree.fromstring(flash_xml.encode('utf-8')) | |||
| playlist_json = self._search_regex(r'playlist\': \'(\[.*?\])\'', webpage, u'playlist').replace(r'\"','"') | |||
| playlist = json.loads(playlist_json) | |||
| videos = [] | |||
| ns = '{http://tempuri.org/XMLSchema.xsd}' | |||
| xpath = '%(ns)sPlaylist/%(ns)sItems/%(ns)sItem' % {'ns': ns} | |||
| webpage_description = self._og_search_description(webpage) | |||
| for (i, (item, info)) in enumerate(zip(flash_config.findall(xpath), playlist), 1): | |||
| # Get best quality url | |||
| rtmp_url = None | |||
| for q in ['Q6A', 'Q4A', 'Q1A']: | |||
| video_url = find_xpath_attr(item, '%sVideoUrl' % ns, 'quality', q) | |||
| if video_url is not None: | |||
| rtmp_url = video_url.text | |||
| break | |||
| if rtmp_url is None: | |||
| raise ExtractorError(u'Couldn\'t get video url: %s' % info['id']) | |||
| description = self._html_search_regex( | |||
| r'id="playlist_entry_%s".*?<p>(.*?)</p>' % i, webpage, | |||
| u'description', default=webpage_description, flags=re.DOTALL) | |||
| videos.append({ | |||
| '_type': 'video', | |||
| 'id': info['id'], | |||
| 'title': info['title'], | |||
| 'url': rtmp_url, | |||
| 'ext': 'flv', | |||
| 'description': description, | |||
| }) | |||
| return videos | |||
+ 42
- 0
youtube_dl/extractor/ro220.py
View File
| @ -0,0 +1,42 @@ | |||
| import re | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| clean_html, | |||
| compat_parse_qs, | |||
| ) | |||
| class Ro220IE(InfoExtractor): | |||
| IE_NAME = '220.ro' | |||
| _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)' | |||
| _TEST = { | |||
| u"url": u"http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/", | |||
| u'file': u'LYV6doKo7f.mp4', | |||
| u'md5': u'03af18b73a07b4088753930db7a34add', | |||
| u'info_dict': { | |||
| u"title": u"Luati-le Banii sez 4 ep 1", | |||
| u"description": u"Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.", | |||
| } | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('video_id') | |||
| webpage = self._download_webpage(url, video_id) | |||
| flashVars_str = self._search_regex( | |||
| r'<param name="flashVars" value="([^"]+)"', | |||
| webpage, u'flashVars') | |||
| flashVars = compat_parse_qs(flashVars_str) | |||
| info = { | |||
| '_type': 'video', | |||
| 'id': video_id, | |||
| 'ext': 'mp4', | |||
| 'url': flashVars['videoURL'][0], | |||
| 'title': flashVars['title'][0], | |||
| 'description': clean_html(flashVars['desc'][0]), | |||
| 'thumbnail': flashVars['preview'][0], | |||
| } | |||
| return info | |||
+ 15
- 2
youtube_dl/extractor/rtlnow.py
View File
+ 90
- 0
youtube_dl/extractor/sohu.py
View File
| @ -0,0 +1,90 @@ | |||
| # encoding: utf-8 | |||
| import json | |||
| import re | |||
| from .common import InfoExtractor | |||
| from ..utils import ExtractorError | |||
| class SohuIE(InfoExtractor): | |||
| _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?' | |||
| _TEST = { | |||
| u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super', | |||
| u'file': u'382479172.mp4', | |||
| u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7', | |||
| u'info_dict': { | |||
| u'title': u'MV：Far East Movement《The Illest》', | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| def _fetch_data(vid_id): | |||
| base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid=' | |||
| data_url = base_data_url + str(vid_id) | |||
| data_json = self._download_webpage( | |||
| data_url, video_id, | |||
| note=u'Downloading JSON data for ' + str(vid_id)) | |||
| return json.loads(data_json) | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('id') | |||
| webpage = self._download_webpage(url, video_id) | |||
| raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>', | |||
| webpage, u'video title') | |||
| title = raw_title.partition('-')[0].strip() | |||
| vid = self._html_search_regex(r'var vid="(\d+)"', webpage, | |||
| u'video path') | |||
| data = _fetch_data(vid) | |||
| QUALITIES = ('ori', 'super', 'high', 'nor') | |||
| vid_ids = [data['data'][q + 'Vid'] | |||
| for q in QUALITIES | |||
| if data['data'][q + 'Vid'] != 0] | |||
| if not vid_ids: | |||
| raise ExtractorError(u'No formats available for this video') | |||
| # For now, we just pick the highest available quality | |||
| vid_id = vid_ids[-1] | |||
| format_data = data if vid == vid_id else _fetch_data(vid_id) | |||
| part_count = format_data['data']['totalBlocks'] | |||
| allot = format_data['allot'] | |||
| prot = format_data['prot'] | |||
| clipsURL = format_data['data']['clipsURL'] | |||
| su = format_data['data']['su'] | |||
| playlist = [] | |||
| for i in range(part_count): | |||
| part_url = ('http://%s/?prot=%s&file=%s&new=%s' % | |||
| (allot, prot, clipsURL[i], su[i])) | |||
| part_str = self._download_webpage( | |||
| part_url, video_id, | |||
| note=u'Downloading part %d of %d' % (i+1, part_count)) | |||
| part_info = part_str.split('|') | |||
| video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) | |||
| video_info = { | |||
| 'id': '%s_part%02d' % (video_id, i + 1), | |||
| 'title': title, | |||
| 'url': video_url, | |||
| 'ext': 'mp4', | |||
| } | |||
| playlist.append(video_info) | |||
| if len(playlist) == 1: | |||
| info = playlist[0] | |||
| info['id'] = video_id | |||
| else: | |||
| info = { | |||
| '_type': 'playlist', | |||
| 'entries': playlist, | |||
| 'id': video_id, | |||
| } | |||
| return info | |||
+ 73
- 0
youtube_dl/extractor/trilulilu.py
View File
| @ -0,0 +1,73 @@ | |||
| import json | |||
| import re | |||
| import xml.etree.ElementTree | |||
| from .common import InfoExtractor | |||
| class TriluliluIE(InfoExtractor): | |||
| _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)' | |||
| _TEST = { | |||
| u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1", | |||
| u'file': u"big-buck-bunny-1.mp4", | |||
| u'info_dict': { | |||
| u"title": u"Big Buck Bunny", | |||
| u"description": u":) pentru copilul din noi", | |||
| }, | |||
| # Server ignores Range headers (--test) | |||
| u"params": { | |||
| u"skip_download": True | |||
| } | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('video_id') | |||
| webpage = self._download_webpage(url, video_id) | |||
| title = self._og_search_title(webpage) | |||
| thumbnail = self._og_search_thumbnail(webpage) | |||
| description = self._og_search_description(webpage) | |||
| log_str = self._search_regex( | |||
| r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info') | |||
| log = json.loads(log_str) | |||
| format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/' | |||
| u'video-formats2' % log) | |||
| format_str = self._download_webpage( | |||
| format_url, video_id, | |||
| note=u'Downloading formats', | |||
| errnote=u'Error while downloading formats') | |||
| format_doc = xml.etree.ElementTree.fromstring(format_str) | |||
| video_url_template = ( | |||
| u'http://fs%(server)s.trilulilu.ro/stream.php?type=video' | |||
| u'&source=site&hash=%(hash)s&username=%(userid)s&' | |||
| u'key=ministhebest&format=%%s&sig=&exp=' % | |||
| log) | |||
| formats = [ | |||
| { | |||
| 'format': fnode.text, | |||
| 'url': video_url_template % fnode.text, | |||
| } | |||
| for fnode in format_doc.findall('./formats/format') | |||
| ] | |||
| info = { | |||
| '_type': 'video', | |||
| 'id': video_id, | |||
| 'formats': formats, | |||
| 'title': title, | |||
| 'description': description, | |||
| 'thumbnail': thumbnail, | |||
| } | |||
| # TODO: Remove when #980 has been merged | |||
| info['url'] = formats[-1]['url'] | |||
| info['ext'] = formats[-1]['format'].partition('-')[0] | |||
| return info | |||
+ 1
- 1
youtube_dl/extractor/unistra.py
View File
+ 56
- 0
youtube_dl/extractor/veehd.py
View File
| @ -0,0 +1,56 @@ | |||
| import re | |||
| import json | |||
| from .common import InfoExtractor | |||
| from ..utils import ( | |||
| compat_urlparse, | |||
| get_element_by_id, | |||
| clean_html, | |||
| ) | |||
| class VeeHDIE(InfoExtractor): | |||
| _VALID_URL = r'https?://veehd.com/video/(?P<id>\d+)' | |||
| _TEST = { | |||
| u'url': u'http://veehd.com/video/4686958', | |||
| u'file': u'4686958.mp4', | |||
| u'info_dict': { | |||
| u'title': u'Time Lapse View from Space ( ISS)', | |||
| u'uploader_id': u'spotted', | |||
| u'description': u'md5:f0094c4cf3a72e22bc4e4239ef767ad7', | |||
| }, | |||
| } | |||
| def _real_extract(self, url): | |||
| mobj = re.match(self._VALID_URL, url) | |||
| video_id = mobj.group('id') | |||
| webpage = self._download_webpage(url, video_id) | |||
| player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"', | |||
| webpage, u'player path') | |||
| player_url = compat_urlparse.urljoin(url, player_path) | |||
| player_page = self._download_webpage(player_url, video_id, | |||
| u'Downloading player page') | |||
| config_json = self._search_regex(r'value=\'config=({.+?})\'', | |||
| player_page, u'config json') | |||
| config = json.loads(config_json) | |||
| video_url = compat_urlparse.unquote(config['clip']['url']) | |||
| title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) | |||
| uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>', | |||
| webpage, u'uploader') | |||
| thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"', | |||
| webpage, u'thumbnail') | |||
| description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul', | |||
| webpage, u'description', flags=re.DOTALL) | |||
| return { | |||
| '_type': 'video', | |||
| 'id': video_id, | |||
| 'title': title, | |||
| 'url': video_url, | |||
| 'ext': 'mp4', | |||
| 'uploader_id': uploader_id, | |||
| 'thumbnail': thumbnail, | |||
| 'description': description, | |||
| } | |||
+ 37
- 11
youtube_dl/extractor/vimeo.py
View File
+ 0
- 1
youtube_dl/extractor/wat.py
View File
+ 10
- 8
youtube_dl/extractor/xhamster.py
View File
+ 14
- 4
youtube_dl/extractor/youporn.py
View File
+ 63
- 26
youtube_dl/extractor/youtube.py
View File
+ 57
- 7
youtube_dl/utils.py
View File
+ 1
- 1
youtube_dl/version.py
View File
| @ -1,2 +1,2 @@ | |||
| __version__ = '2013.08.22' | |||
| __version__ = '2013.09.06.1' | |||