[Yam] Add new extractor

This commit is contained in:
Yen Chi Hsuan 2015-02-13 15:14:23 +08:00
parent c80b9cd280
commit 7105440cec
3 changed files with 87 additions and 4 deletions

View file

@ -578,6 +578,7 @@ from .yahoo import (
YahooIE, YahooIE,
YahooSearchIE, YahooSearchIE,
) )
from .yam import YamIE
from .yesjapan import YesJapanIE from .yesjapan import YesJapanIE
from .ynet import YnetIE from .ynet import YnetIE
from .youjizz import YouJizzIE from .youjizz import YouJizzIE

View file

@ -0,0 +1,70 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import month_by_abbreviation
import re
class YamIE(InfoExtractor):
_VALID_URL = r'http://mymedia.yam.com/m/(?P<id>\d+)'
_TESTS = [{
# An audio hosted on Yam
'url': 'http://mymedia.yam.com/m/2283921',
'md5': 'c011b8e262a52d5473d9c2e3c9963b9c',
'info_dict': {
'id': '2283921',
'ext': 'mp3',
'title': '發現 - 趙薇 京華煙雲主題曲',
'uploader_id': 'princekt',
'upload_date': '20080807',
'duration': 313.0,
}
}, {
# An external video hosted on YouTube
'url': 'http://mymedia.yam.com/m/3598173',
'md5': '0238ceec479c654e8c2f1223755bf3e9',
'info_dict': {
'id': 'pJ2Deys283c',
'ext': 'mp4',
'upload_date': '20150202',
'uploader': '新莊社大瑜伽社',
'description': 'md5:f5cc72f0baf259a70fb731654b0d2eff',
'uploader_id': '2323agoy',
'title': '外婆的澎湖灣KTV-潘安邦',
}
}]
def _real_extract(self, url):
media_id = self._match_id(url)
page = self._download_webpage(url, media_id)
# Is it hosted externally on YouTube?
youtube_url = self._html_search_regex(
r'<embed src="(http://www.youtube.com/[^"]+)"',
page, 'YouTube url', default=None)
if youtube_url:
return self.url_result(youtube_url, 'Youtube')
api_page = self._download_webpage(
'http://mymedia.yam.com/api/a/?pID=' + media_id, media_id)
api_result_obj = compat_urlparse.parse_qs(api_page)
author = self._html_search_regex(
r'<!-- 發表作者 -->[\n ]+<a href="/([a-z]+)"', page, 'author')
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)
upload_date = '%s%02d%02d' % (mobj.group('year'),
month_by_abbreviation(mobj.group('mon')),
int(mobj.group('day')))
return {
'id': media_id,
'url': api_result_obj['mp3file'][0],
'title': self._html_search_meta('description', page),
'duration': float(api_result_obj['totaltime'][0]) / 1000.0,
'uploader_id': author,
'upload_date': upload_date,
}

View file

@ -62,6 +62,11 @@ std_headers = {
} }
ENGLISH_MONTH_NAMES = [
'January', 'February', 'March', 'April', 'May', 'June',
'July', 'August', 'September', 'October', 'November', 'December']
def preferredencoding(): def preferredencoding():
"""Get preferred encoding. """Get preferred encoding.
@ -1185,11 +1190,18 @@ def get_term_width():
def month_by_name(name): def month_by_name(name):
""" Return the number of a month by (locale-independently) English name """ """ Return the number of a month by (locale-independently) English name """
ENGLISH_NAMES = [
'January', 'February', 'March', 'April', 'May', 'June',
'July', 'August', 'September', 'October', 'November', 'December']
try: try:
return ENGLISH_NAMES.index(name) + 1 return ENGLISH_MONTH_NAMES.index(name) + 1
except ValueError:
return None
def month_by_abbreviation(abbrev):
""" Return the number of a month by (locale-independently) English
abbreviations """
try:
return [s[:3] for s in ENGLISH_MONTH_NAMES].index(abbrev) + 1
except ValueError: except ValueError:
return None return None