Mirror
/
youtube-dl
mirror of https://github.com/ytdl-org/youtube-dl.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[yam] Allow faults in optional fields (#4943)

pull/4973/head
Philipp Hagemeister 2015-02-16 04:50:57 +01:00
parent bfa6bdcd8b
commit 85e80f71cd
1 changed files with 24 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
youtube_dl/extractor/yam.py
View File

@ -1,10 +1,14 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..utils import month_by_abbreviation from ..utils import (
import re float_or_none,
month_by_abbreviation,
)
class YamIE(InfoExtractor): class YamIE(InfoExtractor):
@ -38,8 +42,8 @@ class YamIE(InfoExtractor):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
media_id = self._match_id(url) video_id = self._match_id(url)
page = self._download_webpage(url, media_id) page = self._download_webpage(url, video_id)
# Is it hosted externally on YouTube? # Is it hosted externally on YouTube?
youtube_url = self._html_search_regex( youtube_url = self._html_search_regex(
@ -49,22 +53,29 @@ class YamIE(InfoExtractor):
return self.url_result(youtube_url, 'Youtube') return self.url_result(youtube_url, 'Youtube')
api_page = self._download_webpage( api_page = self._download_webpage(
'http://mymedia.yam.com/api/a/?pID=' + media_id, media_id) 'http://mymedia.yam.com/api/a/?pID=' + video_id, video_id,
note='Downloading API page')
api_result_obj = compat_urlparse.parse_qs(api_page) api_result_obj = compat_urlparse.parse_qs(api_page)
author = self._html_search_regex( uploader_id = self._html_search_regex(
r'<!-- 發表作者 -->：[\n ]+<a href="/([a-z]+)"', page, 'author') r'<!-- 發表作者 -->：[\n ]+<a href="/([a-z]+)"',
page, 'uploader id', fatal=False)
mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2}) ' + mobj = re.search(r'<!-- 發表於 -->(?P<mon>[A-Z][a-z]{2}) ' +
r'(?P<day>\d{1,2}), (?P<year>\d{4})', page) r'(?P<day>\d{1,2}), (?P<year>\d{4})', page)
upload_date = '%s%02d%02d' % (mobj.group('year'), if mobj:
month_by_abbreviation(mobj.group('mon')), upload_date = '%s%02d%02d' % (
int(mobj.group('day'))) mobj.group('year'),
month_by_abbreviation(mobj.group('mon')),
int(mobj.group('day')))
else:
upload_date = None
duration = float_or_none(api_result_obj['totaltime'][0], scale=1000)
return { return {
'id': media_id, 'id': video_id,
'url': api_result_obj['mp3file'][0], 'url': api_result_obj['mp3file'][0],
'title': self._html_search_meta('description', page), 'title': self._html_search_meta('description', page),
'duration': float(api_result_obj['totaltime'][0]) / 1000.0, 'duration': duration,
'uploader_id': author, 'uploader_id': uploader_id,
'upload_date': upload_date, 'upload_date': upload_date,
} }