R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[meipai] Fix according code review

Browse Source
This commit is contained in:
Philip Xu 2016-09-25 14:04:48 -04:00
parent f48bbd821a
commit 808bce4445
1 changed files with 12 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
youtube_dl/extractor/meipai.py
View File

@ -1,25 +1,9 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
from ..utils import parse_iso8601, unescapeHTML from ..utils import parse_iso8601
from .common import InfoExtractor from .common import InfoExtractor
# This is a sloppy fallback, except there is currently no other more reliable
# ways to get the title if the page does not contain OpenGraph data, which
# might be the case for some of the videos, the HTML output of the server is
# not consistent.
RE_TITLE = r'<title[^>]*>(.+)</title>'
# This pattern will only showed up when this video is a playback of previous
# live streaming
RE_M3U8_URL = r'file:\s*encodeURIComponent\(["\'](.+)["\']\)'
# This is the word in Simplified Chinese meaning 'Live Streaming Playback', it
# will showed up in the keyword meta tag if the video is a recorded playback,
# we use it to avoid false positives in the future as the RE_M3U8_URL pattern
# is not specific enough.
KEYWORD_PLAYBACK = '直播回放'
class MeipaiIE(InfoExtractor): class MeipaiIE(InfoExtractor):
IE_DESC = '美拍' IE_DESC = '美拍'
@ -76,13 +60,12 @@ class MeipaiIE(InfoExtractor):
title = self._og_search_title(webpage, default=None) title = self._og_search_title(webpage, default=None)
if title is None: if title is None:
# fall back to text used in title # fall back to text used in title
title = unescapeHTML( title = self._html_search_regex(
self._html_search_regex(RE_TITLE, webpage, 'title')) r'<title[^>]*>(.+)</title>', webpage, 'title')
release_date = self._og_search_property( release_date = self._og_search_property(
'video:release_date', webpage, 'release date', default=None) 'video:release_date', webpage, 'release date', fatal=False)
if release_date: release_date = parse_iso8601(release_date)
release_date = parse_iso8601(release_date)
tags = self._og_search_property( tags = self._og_search_property(
'video:tag', webpage, 'tags', default='').split(',') 'video:tag', webpage, 'tags', default='').split(',')
@ -90,21 +73,23 @@ class MeipaiIE(InfoExtractor):
info = { info = {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'thumbnail': self._og_search_thumbnail(webpage, default=None), 'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage, default=None), 'description': self._og_search_description(webpage),
'release_date': release_date, 'release_date': release_date,
'creator': self._og_search_property( 'creator': self._og_search_property(
'video:director', webpage, 'creator', default=None), 'video:director', webpage, 'creator', fatal=False),
'tags': tags, 'tags': tags,
} }
keywords = self._html_search_meta( keywords = self._html_search_meta(
'keywords', webpage, 'keywords', default=[]) 'keywords', webpage, 'keywords', default=[])
if KEYWORD_PLAYBACK in keywords: if '直播回放' in keywords:
# recorded playback of live streaming # recorded playback of live streaming
m3u8_url = self._html_search_regex( m3u8_url = self._html_search_regex(
RE_M3U8_URL, webpage, 'm3u8_url') r'file:\s*encodeURIComponent\(["\'](.+)["\']\)',
webpage,
'm3u8_url')
info['formats'] = self._extract_m3u8_formats( info['formats'] = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native') m3u8_url, video_id, 'mp4', 'm3u8_native')
else: else: