Roxedus/ytdl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[dailymotion:playlist] Use an iterator for the entries

Browse Source 
So that using '--playlist-end' only downloads the required pages (reported in #2175).
This commit is contained in:
Jaime Marquínez Ferrándiz 2015-08-02 15:19:57 +02:00
parent 5c45bbe57b
commit 25a4c5a9ed
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
youtube_dl/extractor/dailymotion.py
View File

@ -15,7 +15,6 @@ from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
int_or_none, int_or_none,
orderedSet,
parse_iso8601, parse_iso8601,
str_to_int, str_to_int,
unescapeHTML, unescapeHTML,
@ -278,7 +277,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
}] }]
def _extract_entries(self, id): def _extract_entries(self, id):
video_ids = [] video_ids = set()
processed_urls = set() processed_urls = set()
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
page_url = self._PAGE_TEMPLATE % (id, pagenum) page_url = self._PAGE_TEMPLATE % (id, pagenum)
@ -291,12 +290,13 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
processed_urls.add(urlh.geturl()) processed_urls.add(urlh.geturl())
video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage)) for video_id in re.findall(r'data-xid="(.+?)"', webpage):
if video_id not in video_ids:
yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
video_ids.add(video_id)
if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
break break
return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
for video_id in orderedSet(video_ids)]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)