1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import compat_urlparse
class GolemIE(InfoExtractor):
_VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
_TEST = {
'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
'info_dict': {
'id': '14095',
'format_id': 'high',
'ext': 'mp4',
'title': 'iPhone 6 und 6 Plus - Test',
'duration': 300,
'filesize': 65309548,
}
}
_CONFIG = 'https://video.golem.de/xml/{}.xml'
_PREFIX = 'http://video.golem.de'
def _warn(self, fmt, *args):
self.report_warning(fmt.format(*args), self._id)
def _extract_format(self, elem):
format_id = elem.tag
url = elem.findtext('./url')
if url == '':
self._warn("{}: url: empty, skipping", format_id)
return None
fmt = {
'format_id': format_id,
'url': compat_urlparse.urljoin(self._PREFIX, url)
}
try:
_, ext = elem.findtext('./filename', '').rsplit('.', 1)
except ValueError:
self._warn('{}: ext: missing extension', format_id)
else:
fmt['ext'] = ext
filesize = elem.findtext('./filesize')
if filesize is not None:
try:
fmt['filesize'] = int(filesize)
except ValueError as e:
self._warn('{}: filesize: {}', format_id, e)
width = elem.get('width')
if width is not None:
try:
fmt['width'] = int(width)
except ValueError as e:
self._warn('{}: width: {}', format_id, e)
height = elem.get('height')
if height is not None:
try:
fmt['height'] = int(height)
except ValueError as e:
self._warn('{}: height: {}', format_id, e)
return fmt
def _extract_thumbnail(self, elem):
url = elem.findtext('./url')
if url == '':
return None
thumb = {
'url': compat_urlparse.urljoin(self._PREFIX, url)
}
width = elem.get('width')
if width is not None:
try:
thumb['width'] = int(width)
except ValueError as e:
self._warn('thumbnail: width: {}', e)
height = elem.get('height')
if height is not None:
try:
thumb['height'] = int(height)
except ValueError as e:
self._warn('thumbnail: height: {}', e)
return thumb
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
self._id = mobj.group('id')
config = self._download_xml(self._CONFIG.format(self._id), self._id)
info = {
'id': self._id,
'title': config.findtext('./title', 'golem')
}
formats = []
for e in config.findall('./*[url]'):
fmt = self._extract_format(e)
if fmt is not None:
formats.append(fmt)
self._sort_formats(formats)
info['formats'] = formats
thumbnails = []
for e in config.findall('.//teaser[url]'):
thumb = self._extract_thumbnail(e)
if thumb is not None:
thumbnails.append(thumb)
info['thumbnails'] = thumbnails
playtime = config.findtext('./playtime')
if playtime is not None:
try:
info['duration'] = round(float(playtime))
except ValueError as e:
self._warn('duration: {}', e)
return info
|
