diff options
Diffstat (limited to 'youtube_dl')
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 129 | ||||
| -rw-r--r-- | youtube_dl/extractor/metacafe.py | 110 | ||||
| -rw-r--r-- | youtube_dl/extractor/statigram.py | 33 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 1 |
4 files changed, 145 insertions, 128 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index d950880ad..fcc5d02cf 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -24,106 +24,12 @@ from .utils import * from .extractor.common import InfoExtractor, SearchInfoExtractor +from .extractor.metacafe import MetacafeIE +from .extractor.statigram import StatigramIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeUserIE, YoutubeChannelIE -class MetacafeIE(InfoExtractor): - """Information Extractor for metacafe.com.""" - - _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' - _DISCLAIMER = 'http://www.metacafe.com/family_filter/' - _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' - IE_NAME = u'metacafe' - - def report_disclaimer(self): - """Report disclaimer retrieval.""" - self.to_screen(u'Retrieving disclaimer') - - def _real_initialize(self): - # Retrieve disclaimer - request = compat_urllib_request.Request(self._DISCLAIMER) - try: - self.report_disclaimer() - disclaimer = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err)) - - # Confirm age - disclaimer_form = { - 'filters': '0', - 'submit': "Continue - I'm over 18", - } - request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) - try: - self.report_age_confirmation() - disclaimer = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) - - def _real_extract(self, url): - # Extract id and simplified title from URL - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - video_id = mobj.group(1) - - # Check if video comes from YouTube - mobj2 = re.match(r'^yt-(.*)$', video_id) - if mobj2 is not None: - return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] - - # Retrieve video webpage to extract further information - webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id) - - # Extract URL, uploader and title from webpage - self.report_extraction(video_id) - mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) - if mobj is not None: - mediaURL = compat_urllib_parse.unquote(mobj.group(1)) - video_extension = mediaURL[-3:] - - # Extract gdaKey if available - mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) - if mobj is None: - video_url = mediaURL - else: - gdaKey = mobj.group(1) - video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) - else: - mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - vardict = compat_parse_qs(mobj.group(1)) - if 'mediaData' not in vardict: - raise ExtractorError(u'Unable to extract media URL') - mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0]) - if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - mediaURL = mobj.group('mediaURL').replace('\\/', '/') - video_extension = mediaURL[-3:] - video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) - - mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract title') - video_title = mobj.group(1).decode('utf-8') - - mobj = re.search(r'submitter=(.*?);', webpage) - if mobj is None: - raise ExtractorError(u'Unable to extract uploader nickname') - video_uploader = mobj.group(1) - - return [{ - 'id': video_id.decode('utf-8'), - 'url': video_url.decode('utf-8'), - 'uploader': video_uploader.decode('utf-8'), - 'upload_date': None, - 'title': video_title, - 'ext': video_extension.decode('utf-8'), - }] - class DailymotionIE(InfoExtractor): """Information Extractor for Dailymotion""" @@ -3621,37 +3527,6 @@ class GametrailersIE(InfoExtractor): 'description': video_description, } -class StatigramIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group(1) - webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'<meta property="og:video:secure_url" content="(.+?)">', - webpage, u'video URL') - thumbnail_url = self._html_search_regex( - r'<meta property="og:image" content="(.+?)" />', - webpage, u'thumbnail URL', fatal=False) - html_title = self._html_search_regex( - r'<title>(.+?)</title>', - webpage, u'title') - title = html_title.rpartition(u' | Statigram')[0] - uploader_id = self._html_search_regex( - r'@([^ ]+)', title, u'uploader name', fatal=False) - ext = 'mp4' - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - 'uploader_id' : uploader_id - }] - def gen_extractors(): """ Return a list of an instance of every supported extractor. The order does matter; the first extractor matched is the one handling the URL. diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py new file mode 100644 index 000000000..66d6554fe --- /dev/null +++ b/youtube_dl/extractor/metacafe.py @@ -0,0 +1,110 @@ +import re +import socket + +from .common import InfoExtractor +from ..utils import ( + compat_http_client, + compat_parse_qs, + compat_urllib_error, + compat_urllib_parse, + compat_urllib_request, + compat_str, + + ExtractorError, +) + +class MetacafeIE(InfoExtractor): + """Information Extractor for metacafe.com.""" + + _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' + _DISCLAIMER = 'http://www.metacafe.com/family_filter/' + _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' + IE_NAME = u'metacafe' + + def report_disclaimer(self): + """Report disclaimer retrieval.""" + self.to_screen(u'Retrieving disclaimer') + + def _real_initialize(self): + # Retrieve disclaimer + request = compat_urllib_request.Request(self._DISCLAIMER) + try: + self.report_disclaimer() + compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err)) + + # Confirm age + disclaimer_form = { + 'filters': '0', + 'submit': "Continue - I'm over 18", + } + request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form)) + try: + self.report_age_confirmation() + compat_urllib_request.urlopen(request).read() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err)) + + def _real_extract(self, url): + # Extract id and simplified title from URL + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + + video_id = mobj.group(1) + + # Check if video comes from YouTube + mobj2 = re.match(r'^yt-(.*)$', video_id) + if mobj2 is not None: + return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')] + + # Retrieve video webpage to extract further information + webpage = self._download_webpage('http://www.metacafe.com/watch/%s/' % video_id, video_id) + + # Extract URL, uploader and title from webpage + self.report_extraction(video_id) + mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage) + if mobj is not None: + mediaURL = compat_urllib_parse.unquote(mobj.group(1)) + video_extension = mediaURL[-3:] + + # Extract gdaKey if available + mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage) + if mobj is None: + video_url = mediaURL + else: + gdaKey = mobj.group(1) + video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) + else: + mobj = re.search(r' name="flashvars" value="(.*?)"', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract media URL') + vardict = compat_parse_qs(mobj.group(1)) + if 'mediaData' not in vardict: + raise ExtractorError(u'Unable to extract media URL') + mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0]) + if mobj is None: + raise ExtractorError(u'Unable to extract media URL') + mediaURL = mobj.group('mediaURL').replace('\\/', '/') + video_extension = mediaURL[-3:] + video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key')) + + mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = mobj.group(1).decode('utf-8') + + mobj = re.search(r'submitter=(.*?);', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract uploader nickname') + video_uploader = mobj.group(1) + + return [{ + 'id': video_id.decode('utf-8'), + 'url': video_url.decode('utf-8'), + 'uploader': video_uploader.decode('utf-8'), + 'upload_date': None, + 'title': video_title, + 'ext': video_extension.decode('utf-8'), + }] diff --git a/youtube_dl/extractor/statigram.py b/youtube_dl/extractor/statigram.py new file mode 100644 index 000000000..95d2ee3c0 --- /dev/null +++ b/youtube_dl/extractor/statigram.py @@ -0,0 +1,33 @@ +import re + +from .common import InfoExtractor + +class StatigramIE(InfoExtractor): + _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + webpage = self._download_webpage(url, video_id) + video_url = self._html_search_regex( + r'<meta property="og:video:secure_url" content="(.+?)">', + webpage, u'video URL') + thumbnail_url = self._html_search_regex( + r'<meta property="og:image" content="(.+?)" />', + webpage, u'thumbnail URL', fatal=False) + html_title = self._html_search_regex( + r'<title>(.+?)</title>', + webpage, u'title') + title = html_title.rpartition(u' | Statigram')[0] + uploader_id = self._html_search_regex( + r'@([^ ]+)', title, u'uploader name', fatal=False) + ext = 'mp4' + + return [{ + 'id': video_id, + 'url': video_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + 'uploader_id' : uploader_id + }] diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index a7cb88b5a..4aef85d0c 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1,5 +1,4 @@ # coding: utf-8 -from __future__ import absolute_import import json import netrc |