X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fniconico.py;h=62d5707fee87302b5f69544f768b1a56a5e3976b;hb=baa708036c64e2dce419b5f0648ee6b84ce2132e;hp=8638a8ee84fb2284d10ed7e526f2fb82a18b6642;hpb=52ad14aeb0178a187a861e7ce2259b7046702281;p=youtube-dl
diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py
index 8638a8ee8..62d5707fe 100644
--- a/youtube_dl/extractor/niconico.py
+++ b/youtube_dl/extractor/niconico.py
@@ -1,48 +1,47 @@
# encoding: utf-8
+from __future__ import unicode_literals
import re
-import socket
-import xml.etree.ElementTree
+import json
from .common import InfoExtractor
from ..utils import (
- compat_http_client,
- compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
- compat_str,
-
- ExtractorError,
unified_strdate,
+ parse_duration,
+ int_or_none,
)
+
class NiconicoIE(InfoExtractor):
- IE_NAME = u'niconico'
- IE_DESC = u'ãã³ãã³åç»'
+ IE_NAME = 'niconico'
+ IE_DESC = 'ãã³ãã³åç»'
_TEST = {
- u'url': u'http://www.nicovideo.jp/watch/sm22312215',
- u'file': u'sm22312215.mp4',
- u'md5': u'd1a75c0823e2f629128c43e1212760f9',
- u'info_dict': {
- u'title': u'Big Buck Bunny',
- u'uploader': u'takuya0301',
- u'uploader_id': u'2698420',
- u'upload_date': u'20131123',
- u'description': u'(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
+ 'url': 'http://www.nicovideo.jp/watch/sm22312215',
+ 'md5': 'd1a75c0823e2f629128c43e1212760f9',
+ 'info_dict': {
+ 'id': 'sm22312215',
+ 'ext': 'mp4',
+ 'title': 'Big Buck Bunny',
+ 'uploader': 'takuya0301',
+ 'uploader_id': '2698420',
+ 'upload_date': '20131123',
+ 'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
+ 'duration': 33,
},
- u'params': {
- u'username': u'ydl.niconico@gmail.com',
- u'password': u'youtube-dl',
+ 'params': {
+ 'username': 'ydl.niconico@gmail.com',
+ 'password': 'youtube-dl',
},
}
- _VALID_URL = r'^(?:https?://)?(?:www\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$'
- _LOGIN_URL = 'https://secure.nicovideo.jp/secure/login'
+ _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)'
_NETRC_MACHINE = 'niconico'
- # If True it will raise an error if no login info is provided
- _LOGIN_REQUIRED = True
+ # Determine whether the downloader used authentication to download video
+ _AUTHENTICATED = False
def _real_initialize(self):
self._login()
@@ -50,141 +49,134 @@ class NiconicoIE(InfoExtractor):
def _login(self):
(username, password) = self._get_login_info()
# No authentication to be performed
- if username is None:
- if self._LOGIN_REQUIRED:
- raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
- return False
+ if not username:
+ return True
# Log in
login_form_strs = {
- u'mail': username,
- u'password': password,
+ 'mail': username,
+ 'password': password,
}
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode
- login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
- login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
- request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
- try:
- self.report_login()
- login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
- if re.search(r'(?i)
Log in error
', login_results) is not None:
- self._downloader.report_warning(u'unable to log in: bad username or password')
- return False
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
+ login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
+ login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
+ request = compat_urllib_request.Request(
+ 'https://secure.nicovideo.jp/secure/login', login_data)
+ login_results = self._download_webpage(
+ request, None, note='Logging in', errnote='Unable to log in')
+ if re.search(r'(?i)Log in error
', login_results) is not None:
+ self._downloader.report_warning('unable to log in: bad username or password')
return False
+ # Successful login
+ self._AUTHENTICATED = True
return True
def _real_extract(self, url):
- video_id = self._extract_id(url)
-
- # Get video webpage
- self.report_video_webpage_download(video_id)
- url = 'http://www.nicovideo.jp/watch/' + video_id
- request = compat_urllib_request.Request(url)
- try:
- video_webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download video webpage: %s' % compat_str(err))
-
- # Get video info
- self.report_video_info_webpage_download(video_id)
- url = 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id
- request = compat_urllib_request.Request(url)
- try:
- video_info_webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download video info webpage: %s' % compat_str(err))
-
- # Get flv info
- self.report_flv_info_webpage_download(video_id)
- url = 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id
- request = compat_urllib_request.Request(url)
- try:
- flv_info_webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to download flv info webpage: %s' % compat_str(err))
-
- # Start extracting information
- self.report_information_extraction(video_id)
- video_info = xml.etree.ElementTree.fromstring(video_info_webpage)
-
- # url
- video_real_url = compat_urlparse.parse_qs(flv_info_webpage.decode('utf-8'))['url'][0]
-
- # title
- video_title = video_info.find('.//title').text
-
- # ext
- video_extension = video_info.find('.//movie_type').text
-
- # format
- video_format = video_extension.upper()
-
- # thumbnail
- video_thumbnail = video_info.find('.//thumbnail_url').text
-
- # description
- video_description = video_info.find('.//description').text
-
- # uploader_id
- video_uploader_id = video_info.find('.//user_id').text
-
- # uploader
- url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
- request = compat_urllib_request.Request(url)
- try:
- user_info_webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err))
-
- user_info = xml.etree.ElementTree.fromstring(user_info_webpage)
- video_uploader = user_info.find('.//nickname').text
-
- # uploder_date
- video_upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group(1)
- # view_count
- video_view_count = video_info.find('.//view_counter').text
+ # Get video webpage. We are not actually interested in it, but need
+ # the cookies in order to be able to download the info webpage
+ self._download_webpage('http://www.nicovideo.jp/watch/' + video_id, video_id)
+
+ video_info = self._download_xml(
+ 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
+ note='Downloading video info page')
+
+ if self._AUTHENTICATED:
+ # Get flv info
+ flv_info_webpage = self._download_webpage(
+ 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
+ video_id, 'Downloading flv info')
+ else:
+ # Get external player info
+ ext_player_info = self._download_webpage(
+ 'http://ext.nicovideo.jp/thumb_watch/' + video_id, video_id)
+ thumb_play_key = self._search_regex(
+ r'\'thumbPlayKey\'\s*:\s*\'(.*?)\'', ext_player_info, 'thumbPlayKey')
+
+ # Get flv info
+ flv_info_data = compat_urllib_parse.urlencode({
+ 'k': thumb_play_key,
+ 'v': video_id
+ })
+ flv_info_request = compat_urllib_request.Request(
+ 'http://ext.nicovideo.jp/thumb_watch', flv_info_data,
+ {'Content-Type': 'application/x-www-form-urlencoded'})
+ flv_info_webpage = self._download_webpage(
+ flv_info_request, video_id,
+ note='Downloading flv info', errnote='Unable to download flv info')
+
+ video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
- # webpage_url
- video_webpage_url = video_info.find('.//watch_url').text
+ # Start extracting information
+ title = video_info.find('.//title').text
+ extension = video_info.find('.//movie_type').text
+ video_format = extension.upper()
+ thumbnail = video_info.find('.//thumbnail_url').text
+ description = video_info.find('.//description').text
+ upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
+ view_count = int_or_none(video_info.find('.//view_counter').text)
+ comment_count = int_or_none(video_info.find('.//comment_num').text)
+ duration = parse_duration(video_info.find('.//length').text)
+ webpage_url = video_info.find('.//watch_url').text
+
+ if video_info.find('.//ch_id') is not None:
+ uploader_id = video_info.find('.//ch_id').text
+ uploader = video_info.find('.//ch_name').text
+ elif video_info.find('.//user_id') is not None:
+ uploader_id = video_info.find('.//user_id').text
+ uploader = video_info.find('.//user_nickname').text
+ else:
+ uploader_id = uploader = None
return {
- 'id': video_id,
- 'url': video_real_url,
- 'title': video_title,
- 'ext': video_extension,
- 'format': video_format,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- 'uploader': video_uploader,
- 'upload_date': video_upload_date,
- 'uploader_id': video_uploader_id,
- 'view_count': video_view_count,
- 'webpage_url': video_webpage_url,
+ 'id': video_id,
+ 'url': video_real_url,
+ 'title': title,
+ 'ext': extension,
+ 'format': video_format,
+ 'thumbnail': thumbnail,
+ 'description': description,
+ 'uploader': uploader,
+ 'upload_date': upload_date,
+ 'uploader_id': uploader_id,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ 'duration': duration,
+ 'webpage_url': webpage_url,
}
- def _extract_id(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
- video_id = mobj.group(1)
- return video_id
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self.to_screen(u'%s: Downloading video webpage' % video_id)
+class NiconicoPlaylistIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P\d+)'
- def report_video_info_webpage_download(self, video_id):
- """Report attempt to download video info webpage."""
- self.to_screen(u'%s: Downloading video info webpage' % video_id)
+ _TEST = {
+ 'url': 'http://www.nicovideo.jp/mylist/27411728',
+ 'info_dict': {
+ 'id': '27411728',
+ 'title': 'AKB48ã®ãªã¼ã«ãã¤ããããã³',
+ },
+ 'playlist_mincount': 225,
+ }
- def report_flv_info_webpage_download(self, video_id):
- """Report attempt to download flv info webpage."""
- self.to_screen(u'%s: Downloading flv info webpage' % video_id)
+ def _real_extract(self, url):
+ list_id = self._match_id(url)
+ webpage = self._download_webpage(url, list_id)
+
+ entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);',
+ webpage, 'entries')
+ entries = json.loads(entries_json)
+ entries = [{
+ '_type': 'url',
+ 'ie_key': NiconicoIE.ie_key(),
+ 'url': 'http://www.nicovideo.jp/watch/%s' % entry['item_id'],
+ } for entry in entries]
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self.to_screen(u'%s: Extracting video information' % video_id)
+ return {
+ '_type': 'playlist',
+ 'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
+ 'id': list_id,
+ 'entries': entries,
+ }