support qq video soap opera album list download
This commit is contained in:
huangtiande
parent
bc3e66a671
commit
d0cdefae3a
@ -4,7 +4,9 @@ from __future__ import unicode_literals
|
|||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
ExtractorError,
|
||||||
|
)
|
||||||
|
|
||||||
class QqVideoIE(InfoExtractor):
|
class QqVideoIE(InfoExtractor):
|
||||||
""" qq viedo extractor """
|
""" qq viedo extractor """
|
||||||
@ -47,61 +49,77 @@ class QqVideoIE(InfoExtractor):
|
|||||||
|
|
||||||
]
|
]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _soap_extract(self, url, video_id):
|
||||||
""" extract qq video url """
|
""" extract soap opera url of qq video,"""
|
||||||
mobj = re.match(self._VALID_URL, url)
|
webpage = self._download_webpage(url, video_id, 'download web page: {0}'.format(url))
|
||||||
pid = mobj.group('pid')
|
album_list = [album.group('vid') for album in re.finditer(r'(?is)<a[^>]+class="album_link"\s+id="(?P<vid>[\w\d\-_]+)"[^>]+>.*?</a>', webpage)]
|
||||||
video_id = mobj.group('id') or mobj.group('vid') or pid
|
if len(album_list) == 0:
|
||||||
|
raise ExtractorError('invalid video id: {0}'.format(video_id))
|
||||||
|
elif video_id in album_list:
|
||||||
|
album_list.clear()
|
||||||
|
album_list.append(video_id)
|
||||||
|
|
||||||
info_doc = self._download_xml(
|
entries = []
|
||||||
'http://vv.video.qq.com/getinfo?vid={0}&otype=xml&defaultfmt=shd'.format(video_id),
|
for album_index in range(len(album_list)):
|
||||||
video_id, 'fetch video metadata')
|
vid = album_list[album_index]
|
||||||
|
info_doc = self._download_xml(
|
||||||
title = info_doc.find('./vl/vi/ti').text
|
'http://vv.video.qq.com/getinfo?vid={0}&otype=xml&defaultfmt=shd'.format(vid),
|
||||||
|
vid, 'fetch video metadata: {0}'.format(vid))
|
||||||
if (pid is not None):
|
|
||||||
fclip = info_doc.find('./vl/vi/cl/fc').text
|
fclip = info_doc.find('./vl/vi/cl/fc').text
|
||||||
fn = info_doc.find('./vl/vi/fn').text
|
fn = info_doc.find('./vl/vi/fn').text
|
||||||
vtypes = {v.find('./name').text:v.find('./id').text for v in info_doc.findall('./fl/fi')}
|
vtypes = {v.find('./name').text:v.find('./id').text for v in info_doc.findall('./fl/fi')}
|
||||||
url = info_doc.findall('./vl/vi/ul/ui/url')[-1].text
|
base_url = info_doc.findall('./vl/vi/ul/ui/url')[-1].text
|
||||||
entries = [{
|
title = info_doc.find('./vl/vi/ti').text
|
||||||
'id': '{0}_part{1}'.format(video_id, i + 1),
|
|
||||||
'title': title,
|
|
||||||
'formats': [],
|
|
||||||
} for i in range(int(fclip))]
|
|
||||||
for i in range(int(fclip)):
|
for i in range(int(fclip)):
|
||||||
newfn = '{0}.{1}.{2}'.format(fn[:-4], i + 1, 'mp4')
|
newfn = '{0}.{1}.{2}'.format(fn[:-4], i + 1, 'mp4')
|
||||||
qid = vtypes['sd']
|
qid = vtypes['sd']
|
||||||
if 'fhd' in vtypes:
|
if 'fhd' in vtypes:
|
||||||
qid = vtypes['fhd']
|
qid = vtypes['fhd']
|
||||||
elif 'shd' in vtypes:
|
elif 'shd' in vtypes:
|
||||||
qid = vtypes['shd']
|
qid = vtypes['shd']
|
||||||
elif 'hd' in vtypes:
|
elif 'hd' in vtypes:
|
||||||
qid = vtypes['hd']
|
qid = vtypes['hd']
|
||||||
key_doc = self._download_xml(
|
key_doc = self._download_xml(
|
||||||
'http://vv.video.qq.com/getkey?format=10{0}&otype=xml&vid={1}&filename={2}'.format(int(qid) % 10000, video_id, newfn),
|
'http://vv.video.qq.com/getkey?format=10{0}&otype=xml&vid={1}&filename={2}'.format(int(qid) % 10000, vid, newfn),
|
||||||
video_id, 'get {0}{1} vkey'.format('clip', i + 1))
|
vid, 'get {0} {1}{2} vkey with vid: {3}'.format(title, 'clip', i + 1, vid))
|
||||||
vkey = key_doc.find('./key').text
|
vkey = key_doc.find('./key').text
|
||||||
video_url = '{0}{1}?vkey={2}&type={3}'.format(url, newfn, vkey, 'mp4')
|
video_url = '{0}{1}?vkey={2}&type={3}'.format(base_url, newfn, vkey, 'mp4')
|
||||||
entries[i]['formats'].append({
|
entries.append({
|
||||||
'url': video_url,
|
'id': '{0}_part{1}'.format(vid, i + 1),
|
||||||
'ext': 'mp4',
|
'title': title,
|
||||||
|
'formats': [{
|
||||||
|
'url': video_url,
|
||||||
|
'ext': 'mp4'
|
||||||
|
}],
|
||||||
})
|
})
|
||||||
return {
|
return {
|
||||||
'_type': 'multi_video',
|
'_type': 'multi_video',
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'entries': entries,
|
'entries': entries,
|
||||||
}
|
}
|
||||||
else:
|
|
||||||
url_doc = self._download_xml(
|
def _video_extract(self, url, video_id):
|
||||||
|
""" extract normal qq video url """
|
||||||
|
video_url = self._download_xml(
|
||||||
'http://vv.video.qq.com/geturl?vid={0}&otype=xml'.format(video_id),
|
'http://vv.video.qq.com/geturl?vid={0}&otype=xml'.format(video_id),
|
||||||
video_id, 'fetch video url')
|
video_id, 'fetch video url').find('./vd/vi/url').text
|
||||||
url = url_doc.find('./vd/vi/url').text
|
ext = self._search_regex('\.([\d\w]+)\?', video_url, '', '')
|
||||||
ext = self._search_regex('\.([\d\w]+)\?', url, '', '')
|
title = self._download_xml(
|
||||||
return {
|
'http://vv.video.qq.com/getinfo?vid={0}&otype=xml&defaultfmt=shd'.format(video_id),
|
||||||
'id': video_id,
|
video_id, 'fetch video metadata').find('./vl/vi/ti').text
|
||||||
'title': title,
|
return {
|
||||||
'url': url,
|
'id': video_id,
|
||||||
'ext': ext,
|
'title': title,
|
||||||
}
|
'url': video_url,
|
||||||
|
'ext': ext,
|
||||||
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
""" extract qq video url """
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
video_id = mobj.group('id') or mobj.group('vid') or mobj.group('pid')
|
||||||
|
if (mobj.group('pid') is not None):
|
||||||
|
return self._soap_extract(url, video_id)
|
||||||
|
else:
|
||||||
|
return self._video_extract(url, video_id)
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user