fix youtube find

This commit is contained in:
j 2008-09-30 15:58:21 +02:00
parent c54bcc0738
commit 9e33245ee1
1 changed files with 33 additions and 3 deletions

View File

@ -2,10 +2,11 @@
# vi:si:et:sw=4:sts=4:ts=4
from urllib import quote
import xml.etree.ElementTree as ET
import re
import feedparser
from oxlib.cache import getUrl
from oxlib import findString
from oxlib.cache import getUrl, getUrlUnicode
from oxlib import findString, findRe
def getVideoUrl(youtubeId, format='mp4'):
@ -26,6 +27,7 @@ def getMovieInfo(youtubeId):
fd = feedparser.parse(data)
return getInfoFromAtom(fd.entries[0])
'''
def getInfoFromAtom(entry):
info = dict()
info['title'] = entry['title']
@ -38,7 +40,7 @@ def getInfoFromAtom(entry):
info['thumbnail'] = "http://img.youtube.com/vi/%s/0.jpg" % info['id']
info['flv'] = getVideoUrl(info['id'], 'flv')
info['mp4'] = getVideoUrl(info['id'], 'mp4')
info['embed'] = '''<object width="425" height="355"><param name="movie" value="http://www.youtube.com/v/%s&hl=en"></param><param name="wmode" value="transparent"></param><embed src="http://www.youtube.com/v/%s&hl=en" type="application/x-shockwave-flash" wmode="transparent" width="425" height="355"></embed></object>''' % (info['id'], info['id'])
info['embed'] = '<object width="425" height="355"><param name="movie" value="http://www.youtube.com/v/%s&hl=en"></param><param name="wmode" value="transparent"></param><embed src="http://www.youtube.com/v/%s&hl=en" type="application/x-shockwave-flash" wmode="transparent" width="425" height="355"></embed></object>' % (info['id'], info['id'])
return info
def find(query, max_results=10, offset=1, orderBy='relevance'):
@ -53,4 +55,32 @@ def find(query, max_results=10, offset=1, orderBy='relevance'):
if len(videos) >= max_results:
return videos
return videos
'''
def find(query, max_results=10, offset=1, orderBy='relevance', video_url_base=None):
url = "http://youtube.com/results?search_query=%s&search=Search" % quote(query)
data = getUrlUnicode(url)
regx = re.compile(''' <a href="/watch.v=(.*?)" title="(.*?)" ''')
regx = re.compile('''<a href="/watch\?v=(\w*?)" ><img src="(.*?)" class="vimg120" title="(.*?)" alt="video">''')
id_title = regx.findall(data)
data_flat = data.replace('\n', ' ')
videos = {}
for video in id_title:
vid = video[0]
if vid not in videos:
v = dict()
v['id'] = vid
v['link'] = "http//youtube.com/watch.v=%s" % v['id']
v['title'] = video[2].strip()
if video_url_base:
v['video_link'] = "%s/%s" % (video_url_base, v['id'])
else:
v['video_url'] = get_video_url(v['id'])
v['description'] = findRe(data, 'BeginvidDesc%s">(.*?)</span>' % v['id']).strip().replace('<b>', ' ').replace('</b>', '')
v['thumbnail'] = video[1]
videos[vid] = v
if len(videos) >= max_results:
return videos.values()
return videos.values()