summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/phoenix.py
blob: 63c256019e984190a9773ba84292d4cf1c727226 (plain)
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
import re

from .youtube import YoutubeIE
from .zdf import ZDFBaseIE
from ..utils import (
    int_or_none,
    merge_dicts,
    try_get,
    unified_timestamp,
    urljoin,
)


class PhoenixIE(ZDFBaseIE):
    IE_NAME = 'phoenix.de'
    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
    _TESTS = [{
        # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
        'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
        'md5': '34ec321e7eb34231fd88616c65c92db0',
        'info_dict': {
            'id': '210222_phx_nachgehakt_corona_protest',
            'ext': 'mp4',
            'title': 'Wohin führt der Protest in der Pandemie?',
            'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
            'duration': 1691,
            'timestamp': 1613902500,
            'upload_date': '20210221',
            'uploader': 'Phoenix',
            'series': 'corona nachgehakt',
            'episode': 'Wohin führt der Protest in der Pandemie?',
        },
    }, {
        # Youtube embed
        'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
        'info_dict': {
            'id': 'hMQtqFYjomk',
            'ext': 'mp4',
            'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
            'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
            'duration': 3509,
            'upload_date': '20201219',
            'uploader': 'phoenix',
            'uploader_id': 'phoenix',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
        'only_matching': True,
    }, {
        # no media
        'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
        'only_matching': True,
    }, {
        # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
        'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        article_id = self._match_id(url)

        article = self._download_json(
            f'https://www.phoenix.de/response/id/{article_id}', article_id,
            'Downloading article JSON')

        video = article['absaetze'][0]
        title = video.get('titel') or article.get('subtitel')

        if video.get('typ') == 'video-youtube':
            video_id = video['id']
            return self.url_result(
                video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
                video_title=title)

        video_id = str(video.get('basename') or video.get('content'))

        details = self._download_json(
            'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
            video_id, 'Downloading details JSON', query={
                'ak': 'web',
                'ptmd': 'true',
                'id': video_id,
                'profile': 'player2',
            })

        title = title or details['title']
        content_id = details['tracking']['nielsen']['content']['assetid']

        info = self._extract_ptmd(
            f'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/{content_id}',
            content_id, None, url)

        duration = int_or_none(try_get(
            details, lambda x: x['tracking']['nielsen']['content']['length']))
        timestamp = unified_timestamp(details.get('editorialDate'))
        series = try_get(
            details, lambda x: x['tracking']['nielsen']['content']['program'],
            str)
        episode = title if details.get('contentType') == 'episode' else None

        thumbnails = []
        teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
        for thumbnail_key, thumbnail_url in teaser_images.items():
            thumbnail_url = urljoin(url, thumbnail_url)
            if not thumbnail_url:
                continue
            thumbnail = {
                'url': thumbnail_url,
            }
            m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
            if m:
                thumbnail['width'] = int(m.group(1))
                thumbnail['height'] = int(m.group(2))
            thumbnails.append(thumbnail)

        return merge_dicts(info, {
            'id': content_id,
            'title': title,
            'description': details.get('leadParagraph'),
            'duration': duration,
            'thumbnails': thumbnails,
            'timestamp': timestamp,
            'uploader': details.get('tvService'),
            'series': series,
            'episode': episode,
        })