diff options
| author | huohuarong <huohuarong@gmail.com> | 2013-08-03 10:29:58 +0800 |
|---|---|---|
| committer | huohuarong <huohuarong@gmail.com> | 2013-08-03 10:29:58 +0800 |
| commit | 4ec929dc9b55a2588b4a27e64871c5bfa900bf37 (patch) | |
| tree | bdee9a28442f183a2a1c5c8c6ff561d536033afa | |
| parent | 6624a2b07dafad4de895b4e84f4595214817518d (diff) | |
use ..utils/clean_html()
| -rw-r--r-- | youtube_dl/extractor/sohu.py | 19 |
1 files changed, 6 insertions, 13 deletions
diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 830814221..cf0ab5478 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -7,7 +7,7 @@ import logging import urllib2 from .common import InfoExtractor -from ..utils import compat_urllib_request +from ..utils import compat_urllib_request, clean_html class SohuIE(InfoExtractor): @@ -22,16 +22,6 @@ class SohuIE(InfoExtractor): }, } - def _clearn_html(self, string): - tags = re.findall(r'<.+?>', string) - for t in tags: - string = string.replace(t, ' ') - for i in range(2): - spaces = re.findall(r'\s+', string) - for s in spaces: - string = string.replace(s, ' ') - string = string.strip() - return string def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -40,7 +30,7 @@ class SohuIE(InfoExtractor): pattern = r'<h1 id="video-title">\n*?(.+?)\n*?</h1>' compiled = re.compile(pattern, re.DOTALL) title = self._search_regex(compiled, webpage, u'video title').strip('\t\n') - title = self._clearn_html(title) + title = clean_html(title) pattern = re.compile(r'var vid="(\d+)"') result = re.search(pattern, webpage) if not result: @@ -93,5 +83,8 @@ class SohuIE(InfoExtractor): } files_info.append(info) time.sleep(1) - + if num_of_parts == 1: + info = files_info[0] + info['id'] = video_id + return info return files_info |