depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-22 16:57:40 +00:00
Code Issues Releases Wiki Activity

[niconico] Simplify and make work with old Python versions

Browse source 
The website requires SSLv3, otherwise it just times out during SSL negotiation.
This commit is contained in:
Philipp Hagemeister 2013-11-24 06:37:14 +01:00
parent 4c9c57428f
commit 13ebea791f
2 changed files with 55 additions and 95 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

121
youtube_dl/extractor/niconico.py
View file

@ -17,6 +17,7 @@ from ..utils import (
unified_strdate, unified_strdate,
) )
class NiconicoIE(InfoExtractor): class NiconicoIE(InfoExtractor):
IE_NAME = u'niconico' IE_NAME = u'niconico'
IE_DESC = u'ニコニコ動画' IE_DESC = u'ニコニコ動画'
@ -38,8 +39,7 @@ class NiconicoIE(InfoExtractor):
}, },
} }
_VALID_URL = r'^(?:https?://)?(?:www\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$' _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$'
_LOGIN_URL = 'https://secure.nicovideo.jp/secure/login'
_NETRC_MACHINE = 'niconico' _NETRC_MACHINE = 'niconico'
# If True it will raise an error if no login info is provided # If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = True _LOGIN_REQUIRED = True
@ -57,99 +57,63 @@ class NiconicoIE(InfoExtractor):
# Log in # Log in
login_form_strs = { login_form_strs = {
u'mail': username, u'mail': username,
u'password': password, u'password': password,
} }
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode # chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) 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') login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
request = compat_urllib_request.Request(self._LOGIN_URL, login_data) request = compat_urllib_request.Request(
try: u'https://secure.nicovideo.jp/secure/login', login_data)
self.report_login() login_results = self._download_webpage(
login_results = compat_urllib_request.urlopen(request).read().decode('utf-8') request, u'', note=u'Logging in', errnote=u'Unable to log in')
if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None: if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
self._downloader.report_warning(u'unable to log in: bad username or password') 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))
return False return False
return True return True
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._extract_id(url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
# Get video webpage # Get video webpage
self.report_video_webpage_download(video_id) video_webpage = self._download_webpage(
url = 'http://www.nicovideo.jp/watch/' + video_id 'http://www.nicovideo.jp/watch/' + video_id, 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 video_info_webpage = self._download_webpage(
self.report_video_info_webpage_download(video_id) 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
url = 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id note=u'Downloading video info page')
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 # Get flv info
self.report_flv_info_webpage_download(video_id) flv_info_webpage = self._download_webpage(
url = 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id u'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
request = compat_urllib_request.Request(url) video_id, u'Downloading flv info')
try: video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
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 # Start extracting information
self.report_information_extraction(video_id)
video_info = xml.etree.ElementTree.fromstring(video_info_webpage) 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 video_title = video_info.find('.//title').text
# ext
video_extension = video_info.find('.//movie_type').text video_extension = video_info.find('.//movie_type').text
# format
video_format = video_extension.upper() video_format = video_extension.upper()
# thumbnail
video_thumbnail = video_info.find('.//thumbnail_url').text video_thumbnail = video_info.find('.//thumbnail_url').text
# description
video_description = video_info.find('.//description').text video_description = video_info.find('.//description').text
# uploader_id
video_uploader_id = video_info.find('.//user_id').text video_uploader_id = video_info.find('.//user_id').text
video_upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
video_view_count = video_info.find('.//view_counter').text
video_webpage_url = video_info.find('.//watch_url').text
# uploader # uploader
video_uploader = video_uploader_id
url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
request = compat_urllib_request.Request(url)
try: try:
user_info_webpage = compat_urllib_request.urlopen(request).read() user_info_webpage = self._download_webpage(
url, video_id, note=u'Downloading user information')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: 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)) self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err))
else:
user_info = xml.etree.ElementTree.fromstring(user_info_webpage) user_info = xml.etree.ElementTree.fromstring(user_info_webpage)
video_uploader = user_info.find('.//nickname').text video_uploader = user_info.find('.//nickname').text
# uploder_date
video_upload_date = unified_strdate(video_info.find('.//first_retrieve').text.split('+')[0])
# view_count
video_view_count = video_info.find('.//view_counter').text
# webpage_url
video_webpage_url = video_info.find('.//watch_url').text
return { return {
'id': video_id, 'id': video_id,
@ -165,26 +129,3 @@ class NiconicoIE(InfoExtractor):
'view_count': video_view_count, 'view_count': video_view_count,
'webpage_url': video_webpage_url, 'webpage_url': video_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)
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)
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 report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self.to_screen(u'%s: Extracting video information' % video_id)

29
youtube_dl/utils.py
View file

@ -12,6 +12,7 @@ import os
import pipes import pipes
import platform import platform
import re import re
import ssl
import socket import socket
import sys import sys
import traceback import traceback
@ -535,13 +536,31 @@ def formatSeconds(secs):
else: else:
return '%d' % secs return '%d' % secs
def make_HTTPS_handler(opts): def make_HTTPS_handler(opts):
if sys.version_info < (3,2): if sys.version_info < (3, 2):
# Python's 2.x handler is very simplistic import httplib
return compat_urllib_request.HTTPSHandler()
class HTTPSConnectionV3(httplib.HTTPSConnection):
def __init__(self, *args, **kwargs):
httplib.HTTPSConnection.__init__(self, *args, **kwargs)
def connect(self):
sock = socket.create_connection((self.host, self.port), self.timeout)
if self._tunnel_host:
self.sock = sock
self._tunnel()
try:
self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv3)
except ssl.SSLError as e:
self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)
class HTTPSHandlerV3(compat_urllib_request.HTTPSHandler):
def https_open(self, req):
return self.do_open(HTTPSConnectionV3, req)
return HTTPSHandlerV3()
else: else:
import ssl context = ssl.SSLContext(ssl.PROTOCOL_SSLv3)
context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
context.set_default_verify_paths() context.set_default_verify_paths()
context.verify_mode = (ssl.CERT_NONE context.verify_mode = (ssl.CERT_NONE