diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2014-12-13 12:24:42 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2014-12-13 12:35:45 +0100 |
| commit | 1cc79574fc5df21bf35dccf61eac0e9e75ed8d20 (patch) | |
| tree | 5cc2bd2a2faba0ac5e8371892e3ef09ab5338080 /youtube_dl/extractor/mitele.py | |
| parent | 20e35880bf7413c5085c1ade96af0fc6e56d84d1 (diff) | |
Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail.
· Use _match_id consistently whenever possible
· Fix some outdated tests
· Use consistent valid URL (always match the whole protocol, no ^ at start required)
· Use modern test definitions
Diffstat (limited to 'youtube_dl/extractor/mitele.py')
| -rw-r--r-- | youtube_dl/extractor/mitele.py | 13 |
1 files changed, 6 insertions, 7 deletions
diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 6691521e5..256758323 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,12 +1,13 @@ from __future__ import unicode_literals -import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, +) +from ..utils import ( get_element_by_attribute, parse_duration, strip_jsonp, @@ -15,7 +16,7 @@ from ..utils import ( class MiTeleIE(InfoExtractor): IE_NAME = 'mitele.es' - _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/' + _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/' _TEST = { 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', @@ -31,12 +32,10 @@ class MiTeleIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - episode = mobj.group('episode') + episode = self._match_id(url) webpage = self._download_webpage(url, episode) embed_data_json = self._search_regex( - r'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', - flags=re.DOTALL + r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data', ).replace('\'', '"') embed_data = json.loads(embed_data_json) |