X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/65cc51b0a1ddf217bc2026332532e0f8019c158a..c7b4d76a372777e3af76ecf9966a8ab9952e52f4:/youtube_dl/InfoExtractors.py?ds=inline
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
old mode 100644
new mode 100755
index 5ebe64b..4bcd8b9
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -3,7 +3,9 @@
from __future__ import absolute_import
+import base64
import datetime
+import itertools
import netrc
import os
import re
@@ -13,6 +15,7 @@ import email.utils
import xml.etree.ElementTree
import random
import math
+import operator
from .utils import *
@@ -23,7 +26,7 @@ class InfoExtractor(object):
Information extractors are the classes that, given a URL, extract
information about the video (or videos) the URL refers to. This
information includes the real video URL, the video title, author and
- others. The information is stored in a dictionary which is then
+ others. The information is stored in a dictionary which is then
passed to the FileDownloader. The FileDownloader processes this
information possibly downloading the video to the file system, among
other possible outcomes.
@@ -32,8 +35,6 @@ class InfoExtractor(object):
id: Video identifier.
url: Final video URL.
- uploader: Nickname of the video uploader, unescaped.
- upload_date: Video upload date (YYYYMMDD).
title: Video title, unescaped.
ext: Video filename extension.
@@ -42,8 +43,12 @@ class InfoExtractor(object):
format: The video format, defaults to ext (used for --get-format)
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
+ uploader: Full name of the video uploader.
+ upload_date: Video upload date (YYYYMMDD).
+ uploader_id: Nickname or id of the video uploader.
+ location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
- subtitles: The .srt file contents.
+ subtitles: The subtitle file contents.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
@@ -69,13 +74,15 @@ class InfoExtractor(object):
self._ready = False
self.set_downloader(downloader)
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url) is not None
+ return re.match(cls._VALID_URL, url) is not None
- def working(self):
+ @classmethod
+ def working(cls):
"""Getter method for _WORKING."""
- return self._WORKING
+ return cls._WORKING
def initialize(self):
"""Initializes an instance (authentication, etc)."""
@@ -100,6 +107,87 @@ class InfoExtractor(object):
"""Real extraction process. Redefine in subclasses."""
pass
+ @property
+ def IE_NAME(self):
+ return type(self).__name__[:-2]
+
+ def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the response handle """
+ if note is None:
+ self.report_download_webpage(video_id)
+ elif note is not False:
+ self.to_screen(u'%s: %s' % (video_id, note))
+ try:
+ return compat_urllib_request.urlopen(url_or_request)
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ if errnote is None:
+ errnote = u'Unable to download webpage'
+ raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+
+ def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns a tuple (page content as string, URL handle) """
+ urlh = self._request_webpage(url_or_request, video_id, note, errnote)
+ content_type = urlh.headers.get('Content-Type', '')
+ m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
+ if m:
+ encoding = m.group(1)
+ else:
+ encoding = 'utf-8'
+ webpage_bytes = urlh.read()
+ if self._downloader.params.get('dump_intermediate_pages', False):
+ try:
+ url = url_or_request.get_full_url()
+ except AttributeError:
+ url = url_or_request
+ self.to_screen(u'Dumping request to ' + url)
+ dump = base64.b64encode(webpage_bytes).decode('ascii')
+ self._downloader.to_screen(dump)
+ content = webpage_bytes.decode(encoding, 'replace')
+ return (content, urlh)
+
+ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
+ """ Returns the data of the page as a string """
+ return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0]
+
+ def to_screen(self, msg):
+ """Print msg to screen, prefixing it with '[ie_name]'"""
+ self._downloader.to_screen(u'[%s] %s' % (self.IE_NAME, msg))
+
+ def report_extraction(self, id_or_name):
+ """Report information extraction."""
+ self.to_screen(u'%s: Extracting information' % id_or_name)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self.to_screen(u'%s: Downloading webpage' % video_id)
+
+ def report_age_confirmation(self):
+ """Report attempt to confirm age."""
+ self.to_screen(u'Confirming age')
+
+ #Methods for following #608
+ #They set the correct value of the '_type' key
+ def video_result(self, video_info):
+ """Returns a video"""
+ video_info['_type'] = 'video'
+ return video_info
+ def url_result(self, url, ie=None):
+ """Returns a url that points to a page that should be processed"""
+ #TODO: ie should be the class used for getting the info
+ video_info = {'_type': 'url',
+ 'url': url,
+ 'ie_key': ie}
+ return video_info
+ def playlist_result(self, entries, playlist_id=None, playlist_title=None):
+ """Returns a playlist"""
+ video_info = {'_type': 'playlist',
+ 'entries': entries}
+ if playlist_id:
+ video_info['id'] = playlist_id
+ if playlist_title:
+ video_info['title'] = playlist_title
+ return video_info
+
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
@@ -110,13 +198,12 @@ class YoutubeIE(InfoExtractor):
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
- (?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?:watch(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
- (?:.+&)? # any other preceding param (like /?s=tuff&v=xxxx)
+ (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v=
)
)? # optional -> youtube.com/xxxx is OK
@@ -124,8 +211,8 @@ class YoutubeIE(InfoExtractor):
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
- _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
- _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
+ _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+ _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_NETRC_MACHINE = 'youtube'
@@ -159,65 +246,125 @@ class YoutubeIE(InfoExtractor):
'44': '480x854',
'45': '720x1280',
'46': '1080x1920',
- }
+ }
IE_NAME = u'youtube'
- def suitable(self, url):
+ @classmethod
+ def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+ if YoutubePlaylistIE.suitable(url): return False
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self):
"""Report attempt to set language."""
- self._downloader.to_screen(u'[youtube] Setting language')
+ self.to_screen(u'Setting language')
def report_login(self):
"""Report attempt to log in."""
- self._downloader.to_screen(u'[youtube] Logging in')
-
- def report_age_confirmation(self):
- """Report attempt to confirm age."""
- self._downloader.to_screen(u'[youtube] Confirming age')
+ self.to_screen(u'Logging in')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video webpage' % video_id)
+ 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._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
+ self.to_screen(u'%s: Downloading video info webpage' % video_id)
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
- self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
+ self.to_screen(u'%s: Checking available subtitles' % video_id)
+
+ def report_video_subtitles_request(self, video_id, sub_lang, format):
+ """Report attempt to download video info webpage."""
+ self.to_screen(u'%s: Downloading video subtitles for %s.%s' % (video_id, sub_lang, format))
+
+ def report_video_subtitles_available(self, video_id, sub_lang_list):
+ """Report available subtitles."""
+ sub_lang = ",".join(list(sub_lang_list.keys()))
+ self.to_screen(u'%s: Available subtitles for video: %s' % (video_id, sub_lang))
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
- self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
+ self.to_screen(u'%s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
- self._downloader.to_screen(u'[youtube] %s: Format %s not available' % (video_id, format))
+ self.to_screen(u'%s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
- self._downloader.to_screen(u'[youtube] RTMP download detected')
-
- def _closed_captions_xml_to_srt(self, xml_string):
- srt = ''
- texts = re.findall(r'([^<]+)', xml_string, re.MULTILINE)
- # TODO parse xml instead of regex
- for n, (start, dur_tag, dur, caption) in enumerate(texts):
- if not dur: dur = '4'
- start = float(start)
- end = start + float(dur)
- start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
- end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
- caption = unescapeHTML(caption)
- caption = unescapeHTML(caption) # double cycle, intentional
- srt += str(n+1) + '\n'
- srt += start + ' --> ' + end + '\n'
- srt += caption + '\n\n'
- return srt
+ self.to_screen(u'RTMP download detected')
+
+ def _get_available_subtitles(self, video_id):
+ self.report_video_subtitles_download(video_id)
+ request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
+ try:
+ sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ return (u'unable to download video subtitles: %s' % compat_str(err), None)
+ sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
+ sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
+ if not sub_lang_list:
+ return (u'video doesn\'t have subtitles', None)
+ return sub_lang_list
+
+ def _list_available_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ self.report_video_subtitles_available(video_id, sub_lang_list)
+
+ def _request_subtitle(self, sub_lang, sub_name, video_id, format):
+ """
+ Return tuple:
+ (error_message, sub_lang, sub)
+ """
+ self.report_video_subtitles_request(video_id, sub_lang, format)
+ params = compat_urllib_parse.urlencode({
+ 'lang': sub_lang,
+ 'name': sub_name,
+ 'v': video_id,
+ 'fmt': format,
+ })
+ url = 'http://www.youtube.com/api/timedtext?' + params
+ try:
+ sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
+ if not sub:
+ return (u'Did not fetch video subtitles', None, None)
+ return (None, sub_lang, sub)
+
+ def _extract_subtitle(self, video_id):
+ """
+ Return a list with a tuple:
+ [(error_message, sub_lang, sub)]
+ """
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+ return [(sub_lang_list[0], None, None)]
+ if self._downloader.params.get('subtitleslang', False):
+ sub_lang = self._downloader.params.get('subtitleslang')
+ elif 'en' in sub_lang_list:
+ sub_lang = 'en'
+ else:
+ sub_lang = list(sub_lang_list.keys())[0]
+ if not sub_lang in sub_lang_list:
+ return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
+
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ return [subtitle]
+
+ def _extract_all_subtitles(self, video_id):
+ sub_lang_list = self._get_available_subtitles(video_id)
+ sub_format = self._downloader.params.get('subtitlesformat')
+ if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
+ return [(sub_lang_list[0], None, None)]
+ subtitles = []
+ for sub_lang in sub_lang_list:
+ subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
+ subtitles.append(subtitle)
+ return subtitles
def _print_formats(self, formats):
print('Available formats:')
@@ -245,7 +392,7 @@ class YoutubeIE(InfoExtractor):
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
+ self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
return
# Set language
@@ -254,30 +401,65 @@ class YoutubeIE(InfoExtractor):
self.report_lang()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
+ self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
return
# No authentication to be performed
if username is None:
return
+ request = compat_urllib_request.Request(self._LOGIN_URL)
+ try:
+ login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
+ return
+
+ galx = None
+ dsh = None
+ match = re.search(re.compile(r']* name="loginForm"', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
+ login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
+ if re.search(r'(?i)