Compare commits

..

44 Commits

Author SHA1 Message Date
Philipp Hagemeister
2891932bf0 release 2013.08.28.1 2013-08-28 19:00:17 +02:00
Philipp Hagemeister
9868c781a1 Merge remote-tracking branch 'origin/master' 2013-08-28 18:22:33 +02:00
Philipp Hagemeister
c257baff85 Merge remote-tracking branch 'rzhxeo/youporn-hd'
Conflicts:
	youtube_dl/utils.py
2013-08-28 18:22:28 +02:00
rzhxeo
878e83c5a4 YoupornIE: Clean up extraction of hd video 2013-08-28 16:04:48 +02:00
rzhxeo
0012690aae Let aes_decrypt_text return bytes instead of unicode 2013-08-28 16:03:35 +02:00
rzhxeo
6e74bc41ca Fix division bug in aes.py 2013-08-28 16:01:43 +02:00
rzhxeo
cba892fa1f Add intlist_to_bytes to utils.py 2013-08-28 15:59:07 +02:00
rzhxeo
550bfd4cbd Merge pull request #1 from phihag/youporn-hd-pr
Allow changes to run under Python 3
2013-08-28 06:23:33 -07:00
Jaime Marquínez Ferrándiz
920ef0779b Hide the password and username in verbose mode (closes #1089) 2013-08-28 15:14:02 +02:00
Philipp Hagemeister
48ea9cea77 Allow changes to run under Python 3 2013-08-28 14:34:49 +02:00
Philipp Hagemeister
ccf4b799df Merge remote-tracking branch 'origin/master' 2013-08-28 14:02:40 +02:00
Philipp Hagemeister
f143d86ad2 [sohu] Handle encoding, and fix tests 2013-08-28 14:00:05 +02:00
Jaime Marquínez Ferrándiz
8ae97d76ee PostProcessingError holds the message in the 'msg' property, not in 'message' (fixes #1323)
Causes DeprecationWarning: http://www.python.org/dev/peps/pep-0352/
2013-08-28 13:37:31 +02:00
Philipp Hagemeister
f8b362739e Merge remote-tracking branch 'Huarong/master' 2013-08-28 13:10:59 +02:00
Philipp Hagemeister
6d69d03bac Merge remote-tracking branch 'origin/reuse_ies' 2013-08-28 13:05:21 +02:00
Philipp Hagemeister
204da0d3e3 Merge remote-tracking branch 'origin/master' 2013-08-28 12:57:44 +02:00
Philipp Hagemeister
c496ca96e7 Fix platform name in Python 2 with --verbose (Closes #1228) 2013-08-28 12:57:10 +02:00
Jaime Marquínez Ferrándiz
67b22dd036 Add extractors for video.mit.edu and techtv.mit.edu (closes #1327)
video.mit.edu just embeds the videos from techtv.mit.edu
2013-08-28 12:55:42 +02:00
Philipp Hagemeister
ce6a696e4d Remove unused imports 2013-08-28 12:47:38 +02:00
Philipp Hagemeister
a5caba1eb0 [generic] simply use urljoin 2013-08-28 12:47:27 +02:00
Philipp Hagemeister
edde6c56ac Print playpath with --get-url (Fixes #1334) 2013-08-28 12:14:45 +02:00
Philipp Hagemeister
ae3531adf9 [generic] Fix URL concatenation
When the url is something like http://example.org/foo/bar?x=y  and the added is file/video.mp4 , we want http://example.org/foo/file/video.mp4
Fixes #1268.
2013-08-28 12:08:17 +02:00
Philipp Hagemeister
8cf5ee7831 Merge branch 'master' of github.com:rg3/youtube-dl 2013-08-28 11:57:18 +02:00
Philipp Hagemeister
aa3e950764 Tolerate junk at the end of gzip-compressed content (#1268) 2013-08-28 11:57:13 +02:00
Jaime Marquínez Ferrándiz
af8bd6a82d Show the time taken to download in the same format as the ETA 2013-08-28 10:56:11 +02:00
Jaime Marquínez Ferrándiz
6d38616e67 Merge pull request #1181 from h3xx/master
Add some verbosity when reporting finished downloads

Remove the mixed use of tabs and spaces for indentation.
2013-08-28 10:54:07 +02:00
Philipp Hagemeister
4f5f18acb9 [addanime] add file 2013-08-28 10:28:16 +02:00
Jaime Marquínez Ferrándiz
3e223834d9 [youtube] update algo for length 88, thanks to @Ramhack (fixes #1328) 2013-08-28 10:26:44 +02:00
Jaime Marquínez Ferrándiz
a1bb0f8773 [cnn] remove debug print call. 2013-08-28 10:20:37 +02:00
Jaime Marquínez Ferrándiz
0e283428f7 HTTPError is in urllib.error in Python 3, not in http.error 2013-08-28 10:18:39 +02:00
Philipp Hagemeister
2eabb80254 [addanime] improve 2013-08-28 04:25:38 +02:00
Philipp Hagemeister
44586389e4 [appletrailers] Add support 2013-08-28 02:18:44 +02:00
Philipp Hagemeister
273f603efb [cnn] Allow more URLs 2013-08-28 00:14:19 +02:00
kkalpakloglou
5a27ecdd2e Update AddAnime.py 2013-08-16 23:54:09 +03:00
rzhxeo
97b3656c2e YoupornIE: Add support for hd videos and update Test 2013-08-09 18:37:33 +02:00
rzhxeo
f3bcebb1d2 add an aes implementation 2013-08-09 18:36:01 +02:00
huohuarong
d5b00ee6e0 improve sohu extractor 2013-08-06 10:26:57 +08:00
tsantala
461cead4f7 changes 2013-08-06 04:34:24 +03:00
huohuarong
b5a6d40818 fix parse title bug 2013-08-05 22:51:54 +08:00
Dan Church
968b5e0112 Add some verbosity when reporting finished downloads
For example:

    [download] Resuming download at byte 1868140
    [download] Destination: Entry #1-Bn59FJ4HrmU.flv
    [download] 100% of 3.27MiB in 4s

This format is meant to somewhat mirror the behavior of wget(1) when reporting finished downloads:

    100%[==================>] 54,836,682   788KB/s   in 74s

    2013-08-04 12:32:05 (728 KB/s) - 'google-chrome-stable_current_x86_64.rpm' saved [54836682/54836682]
2013-08-04 12:45:24 -05:00
huohuarong
4ec929dc9b use ..utils/clean_html() 2013-08-03 10:29:58 +08:00
huohuarong
6624a2b07d add an extractor for tv.sohu.com 2013-08-02 17:58:46 +08:00
huohuarong
6d3a7d03e1 fix bug: kankan extractor not support http://vod.kankan.com/v/70/70309.shtml 2013-08-02 15:26:11 +08:00
Jaime Marquínez Ferrándiz
56c7366547 YoutubeIE: reuse instances of InfoExtractors (closes #998)
When a IE is added to the list, it's also added to a dictionary. When a IE is requested it first looks in the dictionary and if there's no instance it will create a new one.

That way _real_initialize is only called once for each IE, saving time if it needs to login for example.
2013-07-08 15:14:27 +02:00
21 changed files with 774 additions and 55 deletions

View File

@@ -14,9 +14,9 @@ tests = [
# 89
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'",
"/?;:|}<[{=+-_)(*&^%$#@!MqBVCXZASDFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuyt"),
# 88
# 88 - vflapUV9V 2013/08/28
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
"J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"),
"ioplkjhgfdsazxcvbnm12<4567890QWERTYUIOZLKJHGFDSAeXCVBNM!@#$%^&*()_-+={[]}|:;?/>.3"),
# 87
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
"uioplkjhgfdsazxcvbnm1t34567890QWE2TYUIOPLKJHGFDSAZXCVeNM!@#$^&*()_-+={[]}|:;?/>.<"),

View File

@@ -63,6 +63,17 @@ class FileDownloader(object):
converted = float(bytes) / float(1024 ** exponent)
return '%.2f%s' % (converted, suffix)
@staticmethod
def format_seconds(seconds):
(mins, secs) = divmod(seconds, 60)
(hours, eta_mins) = divmod(mins, 60)
if hours > 99:
return '--:--:--'
if hours == 0:
return '%02d:%02d' % (mins, secs)
else:
return '%02d:%02d:%02d' % (hours, mins, secs)
@staticmethod
def calc_percent(byte_counter, data_len):
if data_len is None:
@@ -78,14 +89,7 @@ class FileDownloader(object):
return '--:--'
rate = float(current) / dif
eta = int((float(total) - float(current)) / rate)
(eta_mins, eta_secs) = divmod(eta, 60)
(eta_hours, eta_mins) = divmod(eta_mins, 60)
if eta_hours > 99:
return '--:--:--'
if eta_hours == 0:
return '%02d:%02d' % (eta_mins, eta_secs)
else:
return '%02d:%02d:%02d' % (eta_hours, eta_mins, eta_secs)
return FileDownloader.format_seconds(eta)
@staticmethod
def calc_speed(start, now, bytes):
@@ -234,12 +238,14 @@ class FileDownloader(object):
"""Report it was impossible to resume download."""
self.to_screen(u'[download] Unable to resume')
def report_finish(self):
def report_finish(self, data_len_str, tot_time):
"""Report download finished."""
if self.params.get('noprogress', False):
self.to_screen(u'[download] Download completed')
else:
self.to_screen(u'')
clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
self.to_screen(u'\r%s[download] 100%% of %s in %s' %
(clear_line, data_len_str, self.format_seconds(tot_time)))
def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
self.report_destination(filename)
@@ -542,7 +548,7 @@ class FileDownloader(object):
self.report_error(u'Did not get any data blocks')
return False
stream.close()
self.report_finish()
self.report_finish(data_len_str, (time.time() - start))
if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, int(data_len))
self.try_rename(tmpfilename, filename)

View File

@@ -137,7 +137,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
try:
FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
except FFmpegPostProcessorError as err:
raise AudioConversionError(err.message)
raise AudioConversionError(err.msg)
def run(self, information):
path = information['filepath']
@@ -207,7 +207,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
except:
etype,e,tb = sys.exc_info()
if isinstance(e, AudioConversionError):
msg = u'audio conversion failed: ' + e.message
msg = u'audio conversion failed: ' + e.msg
else:
msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
raise PostProcessingError(msg)

View File

@@ -97,6 +97,7 @@ class YoutubeDL(object):
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
self._ies_instances = {}
self._pps = []
self._progress_hooks = []
self._download_retcode = 0
@@ -111,8 +112,21 @@ class YoutubeDL(object):
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
self._ies_instances[ie.ie_key()] = ie
ie.set_downloader(self)
def get_info_extractor(self, ie_key):
"""
Get an instance of an IE with name ie_key, it will try to get one from
the _ies list, if there's no instance it will create a new one and add
it to the extractor list.
"""
ie = self._ies_instances.get(ie_key)
if ie is None:
ie = get_info_extractor(ie_key)()
self.add_info_extractor(ie)
return ie
def add_default_info_extractors(self):
"""
Add the InfoExtractors returned by gen_extractors to the end of the list
@@ -294,9 +308,7 @@ class YoutubeDL(object):
'''
if ie_key:
ie = get_info_extractor(ie_key)()
ie.set_downloader(self)
ies = [ie]
ies = [self.get_info_extractor(ie_key)]
else:
ies = self._ies
@@ -448,7 +460,8 @@ class YoutubeDL(object):
if self.params.get('forceid', False):
compat_print(info_dict['id'])
if self.params.get('forceurl', False):
compat_print(info_dict['url'])
# For RTMP URLs, also include the playpath
compat_print(info_dict['url'] + info_dict.get('play_path', u''))
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
compat_print(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and 'description' in info_dict:

View File

@@ -45,6 +45,7 @@ import sys
import warnings
import platform
from .utils import *
from .update import update_self
from .version import __version__
@@ -99,6 +100,16 @@ def parseOpts(overrideArguments=None):
pass
return None
def _hide_login_info(opts):
opts = list(opts)
for private_opt in ['-p', '--password', '-u', '--username']:
try:
i = opts.index(private_opt)
opts[i+1] = '<PRIVATE>'
except ValueError:
pass
return opts
max_width = 80
max_help_position = 80
@@ -357,9 +368,9 @@ def parseOpts(overrideArguments=None):
argv = systemConf + userConf + commandLineConf
opts, args = parser.parse_args(argv)
if opts.verbose:
sys.stderr.write(u'[debug] System config: ' + repr(systemConf) + '\n')
sys.stderr.write(u'[debug] User config: ' + repr(userConf) + '\n')
sys.stderr.write(u'[debug] Command-line args: ' + repr(commandLineConf) + '\n')
sys.stderr.write(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
sys.stderr.write(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
sys.stderr.write(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
return parser, opts, args
@@ -611,7 +622,7 @@ def _real_main(argv=None):
sys.exc_clear()
except:
pass
sys.stderr.write(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform()) + u'\n')
sys.stderr.write(u'[debug] Python version %s - %s' %(platform.python_version(), platform_name()) + u'\n')
sys.stderr.write(u'[debug] Proxy map: ' + str(proxy_handler.proxies) + u'\n')
ydl.add_default_info_extractors()

202
youtube_dl/aes.py Normal file
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

View File

@@ -1,3 +1,5 @@
from .appletrailers import AppleTrailersIE
from .addanime import AddAnimeIE
from .archiveorg import ArchiveOrgIE
from .ard import ARDIE
from .arte import ArteTvIE
@@ -48,6 +50,7 @@ from .keek import KeekIE
from .liveleak import LiveLeakIE
from .livestream import LivestreamIE
from .metacafe import MetacafeIE
from .mit import TechTVMITIE, MITIE
from .mixcloud import MixcloudIE
from .mtv import MTVIE
from .muzu import MuzuTVIE
@@ -67,6 +70,7 @@ from .roxwel import RoxwelIE
from .rtlnow import RTLnowIE
from .sina import SinaIE
from .slashdot import SlashdotIE
from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE

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
}

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,
}

View File

@@ -4,10 +4,12 @@ import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import determine_ext
class CNNIE(InfoExtractor):
_VALID_URL = r'https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/(?P<path>.+?/(?P<title>[^/]+?)\.cnn)'
_TEST = {
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',
@@ -15,14 +17,23 @@ class CNNIE(InfoExtractor):
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_xml = self._download_webpage(
'http://cnn.com/video/data/3.0/%s/index.xml' % path, page_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 = []

View File

@@ -114,6 +114,11 @@ class InfoExtractor(object):
"""Real extraction process. Redefine in subclasses."""
pass
@classmethod
def ie_key(cls):
"""A string for getting the InfoExtractor with get_info_extractor"""
return cls.__name__[:-2]
@property
def IE_NAME(self):
return type(self).__name__[:-2]
@@ -129,7 +134,7 @@ class InfoExtractor(object):
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
if errnote is None:
errnote = u'Unable to download webpage'
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
""" Returns a tuple (page content as string, URL handle) """
@@ -140,12 +145,17 @@ class InfoExtractor(object):
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read()
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
if m:
encoding = m.group(1)
else:
encoding = 'utf-8'
webpage_bytes = urlh.read()
m = re.search(br'<meta[^>]+charset="?([^"]+)[ /">]',
webpage_bytes[:1024])
if m:
encoding = m.group(1).decode('ascii')
else:
encoding = 'utf-8'
if self._downloader.params.get('dump_intermediate_pages', False):
try:
url = url_or_request.get_full_url()

View File

@@ -7,8 +7,8 @@ from .common import InfoExtractor
from ..utils import (
compat_urllib_error,
compat_urllib_parse,
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urlparse,
ExtractorError,
)
@@ -163,10 +163,7 @@ class GenericIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url)
video_url = compat_urllib_parse.unquote(mobj.group(1))
if video_url.startswith('//'):
video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url
if '://' not in video_url:
video_url = url + ('' if url.endswith('/') else '/') + video_url
video_url = compat_urlparse.urljoin(url, video_url)
video_id = os.path.basename(video_url)
# here's a fun little line of code for you:

View File

@@ -21,8 +21,10 @@ class KankanIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'G_TITLE=[\'"](.+?)[\'"]', webpage, u'video title')
gcid = self._search_regex(r'lurl:[\'"]http://.+?/.+?/(.+?)/', webpage, u'gcid')
title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, u'video title')
surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
gcid = gcids[-1]
video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
video_id, u'Downloading video url info')

View File

@@ -0,0 +1,76 @@
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')
webpage = self._download_webpage(
'http://techtv.mit.edu/videos/%s' % video_id, video_id)
embed_page = self._download_webpage(
'http://techtv.mit.edu/embeds/%s/' % video_id, video_id,
note=u'Downloading embed page')
base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
embed_page, u'base url')
formats_json = self._search_regex(r'bitrates: (\[.+?\])', embed_page,
u'video formats')
formats = json.loads(formats_json)
formats = sorted(formats, key=lambda f: f['bitrate'])
title = get_element_by_id('edit-title', webpage)
description = clean_html(get_element_by_id('edit-description', webpage))
thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
embed_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')

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'MVFar 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

View File

@@ -3,9 +3,6 @@ import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class TriluliluIE(InfoExtractor):

View File

@@ -6,7 +6,6 @@ import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
unified_strdate,
)

View File

@@ -12,14 +12,16 @@ from ..utils import (
unescapeHTML,
unified_strdate,
)
from ..aes import (
aes_decrypt_text
)
class YouPornIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
_TEST = {
u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
u'file': u'505835.mp4',
u'md5': u'c37ddbaaa39058c76a7e86c6813423c1',
u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
u'info_dict': {
u"upload_date": u"20101221",
u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
@@ -75,7 +77,15 @@ class YouPornIE(InfoExtractor):
# Get all of the links from the page
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
links = re.findall(LINK_RE, download_list_html)
if(len(links) == 0):
# Get link of hd video if available
mobj = re.search(r'var encryptedQuality720URL = \'(?P<encrypted_video_url>[a-zA-Z0-9+/]+={0,2})\';', webpage)
if mobj != None:
encrypted_video_url = mobj.group(u'encrypted_video_url')
video_url = aes_decrypt_text(encrypted_video_url, video_title, 32).decode('utf-8')
links = [video_url] + links
if not links:
raise ExtractorError(u'ERROR: no known formats available for video')
self.to_screen(u'Links found: %d' % len(links))
@@ -112,7 +122,7 @@ class YouPornIE(InfoExtractor):
self._print_formats(formats)
return
req_format = self._downloader.params.get('format', None)
req_format = self._downloader.params.get('format', 'best')
self.to_screen(u'Format: %s' % req_format)
if req_format is None or req_format == 'best':

View File

@@ -419,7 +419,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
elif len(s) == 89:
return s[84:78:-1] + s[87] + s[77:60:-1] + s[0] + s[59:3:-1]
elif len(s) == 88:
return s[48] + s[81:67:-1] + s[82] + s[66:62:-1] + s[85] + s[61:48:-1] + s[67] + s[47:12:-1] + s[3] + s[11:3:-1] + s[2] + s[12]
return s[7:28] + s[87] + s[29:45] + s[55] + s[46:55] + s[2] + s[56:87] + s[28]
elif len(s) == 87:
return s[6:27] + s[4] + s[28:39] + s[27] + s[40:59] + s[2] + s[60:]
elif len(s) == 86:

View File

@@ -1,19 +1,20 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import datetime
import email.utils
import errno
import gzip
import io
import json
import locale
import os
import platform
import re
import socket
import sys
import traceback
import zlib
import email.utils
import socket
import datetime
try:
import urllib.request as compat_urllib_request
@@ -60,6 +61,11 @@ try:
except ImportError: # Python 2
import httplib as compat_http_client
try:
from urllib.error import HTTPError as compat_HTTPError
except ImportError: # Python 2
from urllib2 import HTTPError as compat_HTTPError
try:
from subprocess import DEVNULL
compat_subprocess_get_DEVNULL = lambda: DEVNULL
@@ -489,7 +495,7 @@ def make_HTTPS_handler(opts):
class ExtractorError(Exception):
"""Error during info extraction."""
def __init__(self, msg, tb=None, expected=False):
def __init__(self, msg, tb=None, expected=False, cause=None):
""" tb, if given, is the original traceback (so that it can be printed out).
If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
"""
@@ -502,6 +508,7 @@ class ExtractorError(Exception):
self.traceback = tb
self.exc_info = sys.exc_info() # preserve original exception
self.cause = cause
def format_traceback(self):
if self.traceback is None:
@@ -622,8 +629,23 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
content = resp.read()
gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
try:
uncompressed = io.BytesIO(gz.read())
except IOError as original_ioerror:
# There may be junk add the end of the file
# See http://stackoverflow.com/q/4928560/35070 for details
for i in range(1, 1024):
try:
gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
uncompressed = io.BytesIO(gz.read())
except IOError:
continue
break
else:
raise original_ioerror
resp = self.addinfourl_wrapper(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
@@ -711,3 +733,31 @@ class DateRange(object):
return self.start <= date <= self.end
def __str__(self):
return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())
def platform_name():
""" Returns the platform name as a compat_str """
res = platform.platform()
if isinstance(res, bytes):
res = res.decode(preferredencoding())
assert isinstance(res, compat_str)
return res
def bytes_to_intlist(bs):
if not bs:
return []
if isinstance(bs[0], int): # Python 3
return list(bs)
else:
return [ord(c) for c in bs]
def intlist_to_bytes(xs):
if not xs:
return b''
if isinstance(chr(0), bytes): # Python 2
return ''.join([chr(x) for x in xs])
else:
return bytes(xs)

View File

@@ -1,2 +1,2 @@
__version__ = '2013.08.28'
__version__ = '2013.08.28.1'