Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-23 00:54:31 +01:00
Code Issues Releases Wiki Activity

Fail if mandatory fields absent. Add test.

Browse Source
This commit is contained in:
FA 2019-05-07 17:17:43 -07:00
parent e7e8e4b445
commit c06ca8dcc9
1 changed files with 32 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
youtube_dl/extractor/earthcam.py
View File

@ -3,16 +3,18 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
urljoin, urljoin,
int_or_none, int_or_none,
url_or_none, url_or_none,
try_get, try_get,
js_to_json,
) )
class EarthCamIE(InfoExtractor): class EarthCamIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?earthcam\.com/.*\?.*cam=(?P<id>\w+)' _VALID_URL = r'https?://(?:www\.)?earthcam\.com/.*\?.*cam=(?P<id>\w+)'
_TEST = { _TESTS = [{
'url': 'https://www.earthcam.com/usa/newyork/timessquare/?cam=tsrobo1', 'url': 'https://www.earthcam.com/usa/newyork/timessquare/?cam=tsrobo1',
'info_dict': { 'info_dict': {
'id': 'tsrobo1', 'id': 'tsrobo1',
@ -22,29 +24,43 @@ class EarthCamIE(InfoExtractor):
'view_count': int, 'view_count': int,
'is_live': True, 'is_live': True,
'thumbnail': r're:^https?://.*\.(jpg|png)$', 'thumbnail': r're:^https?://.*\.(jpg|png)$',
}, },
} }, {
'url': 'https://www.earthcam.com/usa/louisiana/neworleans/bourbonstreet/?cam=catsmeowkaraoke',
'info_dict': {
'id': 'catsmeowkaraoke',
'ext': 'mp4',
'title': 'New Orleans, LA',
'description': 'Get a front row seat to all the wild and crazy stage performances happening at the Cat\'s Meow Karaoke Bar! Over the years, thousands of guests have enjoyed their moment singing in the spotlight at this popular local spot!',
'view_count': int,
'is_live': True,
'thumbnail': r're:^https?://.*\.(jpg|png)$',
}
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
json_str = self._html_search_regex(r'var\s+json_base\s*=\s*(?P<jstr>{\s*"cam"\s*:\s*{.*}.*});', webpage, 'json', group='jstr') json_str = self._html_search_regex(r'var\s+json_base\s*=\s*(?P<json_str>{\s*"cam"\s*:\s*{.*}.*});', webpage, 'json', group='json_str', default='{}')
json_base = self._parse_json(json_str, video_id) json_base = self._parse_json(js_to_json(json_str), video_id)
video_info = try_get(json_base, lambda x: x['cam'][video_id], dict) or {}
title = video_info.get("long_title") video_info = jsonn_base['cam'][video_id]
description = video_info.get("description") domain = video_info['html5_streamingdomain']
thumbnail = video_info.get("thumbimage") path = video_info['html5_streampath']
view_count = int_or_none(video_info.get("streamviews"))
domain = video_info.get("html5_streamingdomain")
path = video_info.get("html5_streampath")
m3u8_url = urljoin(domain, path) m3u8_url = urljoin(domain, path)
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native')
title = video_info.get('long_title') or self._og_search_title(webpage)
description = video_info.get('description') or self._og_search_description(webpage)
thumbnail = url_or_none(video_info.get('thumbimage')) or self._og_search_thumbnail(webpage)
view_count = int_or_none(video_info.get("streamviews"))
return { return {
'id': video_id, 'id': video_id,
'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native'), 'formats': formats,
'title': title or self._og_search_title(webpage), 'title': title,
'description': description or self._og_search_description(webpage), 'description': description,
'view_count': view_count, 'view_count': view_count,
'is_live': True, 'is_live': True,
'thumbnail': url_or_none(thumbnail), 'thumbnail': thumbnail,
} }