Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-30 04:08:01 +01:00
Code Issues Releases Wiki Activity

Made changes

Browse Source
This commit is contained in:
john 2018-12-31 16:00:11 -08:00
parent d61d495d5e
commit ef212dc2fe
1 changed files with 16 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/niconico.py
View File

@ -483,7 +483,7 @@ class NicovideoIE(SearchInfoExtractor):
currDate = datetime.datetime.now().date() currDate = datetime.datetime.now().date()
while True: while True:
search_url = "http://www.nicovideo.jp/search/%s?sort=f&order=d" % (query) search_url = "http://www.nicovideo.jp/search/%s" % query
r = self._get_entries_for_date(search_url, query, currDate) r = self._get_entries_for_date(search_url, query, currDate)
# did we gather more entries in the last few pages than were asked for? If so, only add as many as are needed to reach the desired number. # did we gather more entries in the last few pages than were asked for? If so, only add as many as are needed to reach the desired number.
@ -504,17 +504,21 @@ class NicovideoIE(SearchInfoExtractor):
} }
def _get_entries_for_date(self, url, query, date, pageNumber=1): def _get_entries_for_date(self, url, query, date, pageNumber=1):
link = url + "&page=" + str(pageNumber) + "&start=" + str(date) + "&end=" + str(date) while True:
results = self._download_webpage(link, query, note='Extracting results from page %s for date %s' % (pageNumber, date)) link = url + "?page=" + str(pageNumber) + "&start=" + str(date) + "&end=" + str(date)
results = self._download_webpage(link, "None", note='Extracting results from page %s for date %s' % (pageNumber, date))
entries = [] entries = []
r = re.findall(r'''<li.*(?!</li>) data-video-id=['|"](..[0-9]{1,8})''', results) r = re.findall(r'(?<=data-video-id=)["\']?(?P<videoid>.*?)(?=["\'])', results)
for item in r: for item in r:
e = self.url_result("http://www.nicovideo.jp/watch/" + str(item), 'Niconico') e = self.url_result("http://www.nicovideo.jp/watch/" + item, 'Niconico')
entries.append(e) entries.append(e)
# each page holds a maximum of 32 entries. If we've seen 32 entries on the current page, # each page holds a maximum of 32 entries. If we've seen 32 entries on the current page,
# it's possible there may be another, so we can check. It's a little awkward, but it works. # it's possible there may be another, so we can check. It's a little awkward, but it works.
if(len(r) >= 32): if(len(r) < 32):
entries += self._get_entries_for_date(url, query, date, pageNumber + 1) break
pageNumber += 1
return entries return entries