[mgtv] fix extraction(closes #20650)

This commit is contained in:
Remita Amine 2019-04-12 09:19:09 +01:00
parent c912029480
commit dc27fd8bb8

View file

@ -1,22 +1,32 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import time
import uuid
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import int_or_none
from ..compat import (
compat_HTTPError,
compat_str,
)
from ..utils import (
ExtractorError,
int_or_none,
)
class MGTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
IE_DESC = '芒果TV'
_GEO_COUNTRIES = ['CN']
_TESTS = [{
'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
'md5': 'b1ffc0fc163152acf6beaa81832c9ee7',
'info_dict': {
'id': '3116640',
'ext': 'mp4',
'title': '我是歌手第四季双年巅峰会:韩红李玟“双王”领军对抗',
'title': '我是歌手 第四季',
'description': '我是歌手第四季双年巅峰会',
'duration': 7461,
'thumbnail': r're:^https?://.*\.jpg$',
@ -28,16 +38,30 @@ class MGTVIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
try:
api_data = self._download_json(
'http://pcweb.api.mgtv.com/player/video', video_id,
query={'video_id': video_id},
headers=self.geo_verification_headers())['data']
'https://pcweb.api.mgtv.com/player/video', video_id, query={
'tk2': base64.urlsafe_b64encode(b'did=%s|pno=1030|ver=0.3.0301|clit=%d' % (compat_str(uuid.uuid4()).encode(), time.time()))[::-1],
'video_id': video_id,
}, headers=self.geo_verification_headers())['data']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
error = self._parse_json(e.cause.read().decode(), None)
if error.get('code') == 40005:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
raise ExtractorError(error['msg'], expected=True)
raise
info = api_data['info']
title = info['title'].strip()
stream_domain = api_data['stream_domain'][0]
stream_data = self._download_json(
'https://pcweb.api.mgtv.com/player/getSource', video_id, query={
'pm2': api_data['atc']['pm2'],
'video_id': video_id,
}, headers=self.geo_verification_headers())['data']
stream_domain = stream_data['stream_domain'][0]
formats = []
for idx, stream in enumerate(api_data['stream']):
for idx, stream in enumerate(stream_data['stream']):
stream_path = stream.get('url')
if not stream_path:
continue
@ -47,7 +71,7 @@ def _real_extract(self, url):
format_url = format_data.get('info')
if not format_url:
continue
tbr = int_or_none(self._search_regex(
tbr = int_or_none(stream.get('filebitrate') or self._search_regex(
r'_(\d+)_mp4/', format_url, 'tbr', default=None))
formats.append({
'format_id': compat_str(tbr or idx),