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
132
133
134
135
136
|
import json
import math
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
traverse_obj,
)
class LeFigaroVideoEmbedIE(InfoExtractor):
_VALID_URL = r'https?://video\.lefigaro\.fr/embed/[^?#]+/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://video.lefigaro.fr/embed/figaro/video/les-francais-ne-veulent-ils-plus-travailler-suivez-en-direct-le-club-le-figaro-idees/',
'md5': 'a0c3069b7e4c4526abf0053a7713f56f',
'info_dict': {
'id': 'g9j7Eovo',
'title': 'Les Français ne veulent-ils plus travailler ? Retrouvez Le Club Le Figaro Idées',
'description': 'md5:862b8813148ba4bf10763a65a69dfe41',
'upload_date': '20230216',
'timestamp': 1676581615,
'duration': 3076,
'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
'ext': 'mp4',
},
}, {
'url': 'https://video.lefigaro.fr/embed/figaro/video/intelligence-artificielle-faut-il-sen-mefier/',
'md5': '319c662943dd777bab835cae1e2d73a5',
'info_dict': {
'id': 'LeAgybyc',
'title': 'Intelligence artificielle : faut-il s’en méfier ?',
'description': 'md5:249d136e3e5934a67c8cb704f8abf4d2',
'upload_date': '20230124',
'timestamp': 1674584477,
'duration': 860,
'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
'ext': 'mp4',
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://video.lefigaro.fr/figaro/video/suivez-en-direct-le-club-le-figaro-international-avec-philippe-gelie-9/',
'md5': '6289f9489efb969e38245f31721596fe',
'info_dict': {
'id': 'QChnbPYA',
'title': 'Où en est le couple franco-allemand ? Retrouvez Le Club Le Figaro International',
'description': 'md5:6f47235b7e7c93b366fd8ebfa10572ac',
'upload_date': '20230123',
'timestamp': 1674503575,
'duration': 3153,
'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
'age_limit': 0,
'ext': 'mp4',
},
}, {
'url': 'https://video.lefigaro.fr/figaro/video/la-philosophe-nathalie-sarthou-lajus-est-linvitee-du-figaro-live/',
'md5': 'f6df814cae53e85937621599d2967520',
'info_dict': {
'id': 'QJzqoNbf',
'title': 'La philosophe Nathalie Sarthou-Lajus est l’invitée du Figaro Live',
'description': 'md5:c586793bb72e726c83aa257f99a8c8c4',
'upload_date': '20230217',
'timestamp': 1676661986,
'duration': 1558,
'thumbnail': r're:^https?://[^?#]+\.(?:jpeg|jpg)',
'age_limit': 0,
'ext': 'mp4',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_data = self._search_nextjs_data(
webpage, display_id)['props']['pageProps']['initialProps']['pageData']['playerData']
return self.url_result(
f'jwplatform:{player_data["videoId"]}', title=player_data.get('title'),
description=player_data.get('description'), thumbnail=player_data.get('poster'))
class LeFigaroVideoSectionIE(InfoExtractor):
_VALID_URL = r'https?://video\.lefigaro\.fr/figaro/(?P<id>[\w-]+)/?(?:[#?]|$)'
_TESTS = [{
'url': 'https://video.lefigaro.fr/figaro/le-club-le-figaro-idees/',
'info_dict': {
'id': 'le-club-le-figaro-idees',
'title': 'Le Club Le Figaro Idées',
},
'playlist_mincount': 14,
}, {
'url': 'https://video.lefigaro.fr/figaro/factu/',
'info_dict': {
'id': 'factu',
'title': 'Factu',
},
'playlist_mincount': 519,
}]
_PAGE_SIZE = 20
def _get_api_response(self, display_id, page_num, note=None):
return self._download_json(
'https://api-graphql.lefigaro.fr/graphql', display_id, note=note,
query={
'id': 'flive-website_UpdateListPage_1fb260f996bca2d78960805ac382544186b3225f5bedb43ad08b9b8abef79af6',
'variables': json.dumps({
'slug': display_id,
'videosLimit': self._PAGE_SIZE,
'sort': 'DESC',
'order': 'PUBLISHED_AT',
'page': page_num,
}).encode(),
})
def _real_extract(self, url):
display_id = self._match_id(url)
initial_response = self._get_api_response(display_id, page_num=1)['data']['playlist']
def page_func(page_num):
api_response = self._get_api_response(display_id, page_num + 1, note=f'Downloading page {page_num + 1}')
return [self.url_result(
video['embedUrl'], LeFigaroVideoEmbedIE, **traverse_obj(video, {
'title': 'name',
'description': 'description',
'thumbnail': 'thumbnailUrl',
})) for video in api_response['data']['playlist']['jsonLd'][0]['itemListElement']]
entries = InAdvancePagedList(
page_func, math.ceil(initial_response['videoCount'] / self._PAGE_SIZE), self._PAGE_SIZE)
return self.playlist_result(entries, playlist_id=display_id, playlist_title=initial_response.get('title'))
|
