369 lines
13 KiB
Python
369 lines
13 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import hashlib
|
|
import math
|
|
import os
|
|
import random
|
|
import time
|
|
import uuid
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_parse_qs,
|
|
compat_urllib_parse,
|
|
compat_urllib_parse_urlparse,
|
|
)
|
|
from ..utils import (
|
|
ExtractorError,
|
|
sanitized_Request,
|
|
urlencode_postdata,
|
|
url_basename,
|
|
)
|
|
|
|
|
|
class IqiyiIE(InfoExtractor):
|
|
IE_NAME = 'iqiyi'
|
|
IE_DESC = '爱奇艺'
|
|
|
|
_VALID_URL = r'http://(?:[^.]+\.)?iqiyi\.com/.+\.html'
|
|
|
|
_TESTS = [{
|
|
'url': 'http://www.iqiyi.com/v_19rrojlavg.html',
|
|
'md5': '2cb594dc2781e6c941a110d8f358118b',
|
|
'info_dict': {
|
|
'id': '9c1fb1b99d192b21c559e5a1a2cb3c73',
|
|
'title': '美国德州空中惊现奇异云团 酷似UFO',
|
|
'ext': 'f4v',
|
|
}
|
|
}, {
|
|
'url': 'http://www.iqiyi.com/v_19rrhnnclk.html',
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
'playlist': [{
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part1',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part2',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part3',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part4',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part5',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part6',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part7',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'e3f585b550a280af23c98b6cb2be19fb_part8',
|
|
'ext': 'f4v',
|
|
'title': '名侦探柯南第752集',
|
|
},
|
|
}],
|
|
'params': {
|
|
'skip_download': True,
|
|
},
|
|
}, {
|
|
'url': 'http://www.iqiyi.com/w_19rt6o8t9p.html',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'http://www.iqiyi.com/a_19rrhbc6kt.html',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'http://yule.iqiyi.com/pcb.html',
|
|
'only_matching': True,
|
|
}, {
|
|
# VIP-only video. The first 2 parts (6 minutes) are available without login
|
|
# MD5 sums omitted as values are different on Travis CI and my machine
|
|
'url': 'http://www.iqiyi.com/v_19rrny4w8w.html',
|
|
'info_dict': {
|
|
'id': 'f3cf468b39dddb30d676f89a91200dc1',
|
|
'title': '泰坦尼克号',
|
|
},
|
|
'playlist': [{
|
|
'info_dict': {
|
|
'id': 'f3cf468b39dddb30d676f89a91200dc1_part1',
|
|
'ext': 'f4v',
|
|
'title': '泰坦尼克号',
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': 'f3cf468b39dddb30d676f89a91200dc1_part2',
|
|
'ext': 'f4v',
|
|
'title': '泰坦尼克号',
|
|
},
|
|
}],
|
|
'expected_warnings': ['Needs a VIP account for full video'],
|
|
}]
|
|
|
|
_FORMATS_MAP = [
|
|
('1', 'h6'),
|
|
('2', 'h5'),
|
|
('3', 'h4'),
|
|
('4', 'h3'),
|
|
('5', 'h2'),
|
|
('10', 'h1'),
|
|
]
|
|
|
|
@staticmethod
|
|
def md5_text(text):
|
|
return hashlib.md5(text.encode('utf-8')).hexdigest()
|
|
|
|
def _authenticate_vip_video(self, api_video_url, video_id, tvid, _uuid, do_report_warning):
|
|
auth_params = {
|
|
# version and platform hard-coded in com/qiyi/player/core/model/remote/AuthenticationRemote.as
|
|
'version': '2.0',
|
|
'platform': 'b6c13e26323c537d',
|
|
'aid': tvid,
|
|
'tvid': tvid,
|
|
'uid': '',
|
|
'deviceId': _uuid,
|
|
'playType': 'main', # XXX: always main?
|
|
'filename': os.path.splitext(url_basename(api_video_url))[0],
|
|
}
|
|
|
|
qd_items = compat_parse_qs(compat_urllib_parse_urlparse(api_video_url).query)
|
|
for key, val in qd_items.items():
|
|
auth_params[key] = val[0]
|
|
|
|
auth_req = sanitized_Request(
|
|
'http://api.vip.iqiyi.com/services/ckn.action',
|
|
urlencode_postdata(auth_params))
|
|
# iQiyi server throws HTTP 405 error without the following header
|
|
auth_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
|
auth_result = self._download_json(
|
|
auth_req, video_id,
|
|
note='Downloading video authentication JSON',
|
|
errnote='Unable to download video authentication JSON')
|
|
if auth_result['code'] == 'Q00506': # requires a VIP account
|
|
if do_report_warning:
|
|
self.report_warning('Needs a VIP account for full video')
|
|
return False
|
|
|
|
return auth_result
|
|
|
|
def construct_video_urls(self, data, video_id, _uuid, tvid):
|
|
def do_xor(x, y):
|
|
a = y % 3
|
|
if a == 1:
|
|
return x ^ 121
|
|
if a == 2:
|
|
return x ^ 72
|
|
return x ^ 103
|
|
|
|
def get_encode_code(l):
|
|
a = 0
|
|
b = l.split('-')
|
|
c = len(b)
|
|
s = ''
|
|
for i in range(c - 1, -1, -1):
|
|
a = do_xor(int(b[c - i - 1], 16), i)
|
|
s += chr(a)
|
|
return s[::-1]
|
|
|
|
def get_path_key(x, format_id, segment_index):
|
|
mg = ')(*&^flash@#$%a'
|
|
tm = self._download_json(
|
|
'http://data.video.qiyi.com/t?tn=' + str(random.random()), video_id,
|
|
note='Download path key of segment %d for format %s' % (segment_index + 1, format_id)
|
|
)['t']
|
|
t = str(int(math.floor(int(tm) / (600.0))))
|
|
return self.md5_text(t + mg + x)
|
|
|
|
video_urls_dict = {}
|
|
need_vip_warning_report = True
|
|
for format_item in data['vp']['tkl'][0]['vs']:
|
|
if 0 < int(format_item['bid']) <= 10:
|
|
format_id = self.get_format(format_item['bid'])
|
|
else:
|
|
continue
|
|
|
|
video_urls = []
|
|
|
|
video_urls_info = format_item['fs']
|
|
if not format_item['fs'][0]['l'].startswith('/'):
|
|
t = get_encode_code(format_item['fs'][0]['l'])
|
|
if t.endswith('mp4'):
|
|
video_urls_info = format_item['flvs']
|
|
|
|
for segment_index, segment in enumerate(video_urls_info):
|
|
vl = segment['l']
|
|
if not vl.startswith('/'):
|
|
vl = get_encode_code(vl)
|
|
is_vip_video = '/vip/' in vl
|
|
filesize = segment['b']
|
|
base_url = data['vp']['du'].split('/')
|
|
if not is_vip_video:
|
|
key = get_path_key(
|
|
vl.split('/')[-1].split('.')[0], format_id, segment_index)
|
|
base_url.insert(-1, key)
|
|
base_url = '/'.join(base_url)
|
|
param = {
|
|
'su': _uuid,
|
|
'qyid': uuid.uuid4().hex,
|
|
'client': '',
|
|
'z': '',
|
|
'bt': '',
|
|
'ct': '',
|
|
'tn': str(int(time.time()))
|
|
}
|
|
api_video_url = base_url + vl
|
|
if is_vip_video:
|
|
api_video_url = api_video_url.replace('.f4v', '.hml')
|
|
auth_result = self._authenticate_vip_video(
|
|
api_video_url, video_id, tvid, _uuid, need_vip_warning_report)
|
|
if auth_result is False:
|
|
need_vip_warning_report = False
|
|
break
|
|
param.update({
|
|
't': auth_result['data']['t'],
|
|
# cid is hard-coded in com/qiyi/player/core/player/RuntimeData.as
|
|
'cid': 'afbe8fd3d73448c9',
|
|
'vid': video_id,
|
|
'QY00001': auth_result['data']['u'],
|
|
})
|
|
api_video_url += '?' if '?' not in api_video_url else '&'
|
|
api_video_url += compat_urllib_parse.urlencode(param)
|
|
js = self._download_json(
|
|
api_video_url, video_id,
|
|
note='Download video info of segment %d for format %s' % (segment_index + 1, format_id))
|
|
video_url = js['l']
|
|
video_urls.append(
|
|
(video_url, filesize))
|
|
|
|
video_urls_dict[format_id] = video_urls
|
|
return video_urls_dict
|
|
|
|
def get_format(self, bid):
|
|
matched_format_ids = [_format_id for _bid, _format_id in self._FORMATS_MAP if _bid == str(bid)]
|
|
return matched_format_ids[0] if len(matched_format_ids) else None
|
|
|
|
def get_bid(self, format_id):
|
|
matched_bids = [_bid for _bid, _format_id in self._FORMATS_MAP if _format_id == format_id]
|
|
return matched_bids[0] if len(matched_bids) else None
|
|
|
|
def get_raw_data(self, tvid, video_id, enc_key, _uuid):
|
|
tm = str(int(time.time()))
|
|
tail = tm + tvid
|
|
param = {
|
|
'key': 'fvip',
|
|
'src': self.md5_text('youtube-dl'),
|
|
'tvId': tvid,
|
|
'vid': video_id,
|
|
'vinfo': 1,
|
|
'tm': tm,
|
|
'enc': self.md5_text(enc_key + tail),
|
|
'qyid': _uuid,
|
|
'tn': random.random(),
|
|
'um': 0,
|
|
'authkey': self.md5_text(self.md5_text('') + tail),
|
|
'k_tag': 1,
|
|
}
|
|
|
|
api_url = 'http://cache.video.qiyi.com/vms' + '?' + \
|
|
compat_urllib_parse.urlencode(param)
|
|
raw_data = self._download_json(api_url, video_id)
|
|
return raw_data
|
|
|
|
def get_enc_key(self, swf_url, video_id):
|
|
# TODO: automatic key extraction
|
|
# last update at 2016-01-22 for Zombie::bite
|
|
enc_key = '6ab6d0280511493ba85594779759d4ed'
|
|
return enc_key
|
|
|
|
def _real_extract(self, url):
|
|
webpage = self._download_webpage(
|
|
url, 'temp_id', note='download video page')
|
|
tvid = self._search_regex(
|
|
r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
|
|
video_id = self._search_regex(
|
|
r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
|
|
swf_url = self._search_regex(
|
|
r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL')
|
|
_uuid = uuid.uuid4().hex
|
|
|
|
enc_key = self.get_enc_key(swf_url, video_id)
|
|
|
|
raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid)
|
|
|
|
if raw_data['code'] != 'A000000':
|
|
raise ExtractorError('Unable to load data. Error code: ' + raw_data['code'])
|
|
|
|
data = raw_data['data']
|
|
|
|
title = data['vi']['vn']
|
|
|
|
# generate video_urls_dict
|
|
video_urls_dict = self.construct_video_urls(
|
|
data, video_id, _uuid, tvid)
|
|
|
|
# construct info
|
|
entries = []
|
|
for format_id in video_urls_dict:
|
|
video_urls = video_urls_dict[format_id]
|
|
for i, video_url_info in enumerate(video_urls):
|
|
if len(entries) < i + 1:
|
|
entries.append({'formats': []})
|
|
entries[i]['formats'].append(
|
|
{
|
|
'url': video_url_info[0],
|
|
'filesize': video_url_info[-1],
|
|
'format_id': format_id,
|
|
'preference': int(self.get_bid(format_id))
|
|
}
|
|
)
|
|
|
|
for i in range(len(entries)):
|
|
self._sort_formats(entries[i]['formats'])
|
|
entries[i].update(
|
|
{
|
|
'id': '%s_part%d' % (video_id, i + 1),
|
|
'title': title,
|
|
}
|
|
)
|
|
|
|
if len(entries) > 1:
|
|
info = {
|
|
'_type': 'multi_video',
|
|
'id': video_id,
|
|
'title': title,
|
|
'entries': entries,
|
|
}
|
|
else:
|
|
info = entries[0]
|
|
info['id'] = video_id
|
|
info['title'] = title
|
|
|
|
return info
|