+# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..compat import compat_urllib_request
from ..utils import (
float_or_none,
- unescapeHTML,
+ xpath_text,
+ remove_end,
+ int_or_none,
+ ExtractorError,
+ sanitized_Request,
)
class TwitterCardIE(InfoExtractor):
+ IE_NAME = 'twitter:card'
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
_TESTS = [
{
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
- 'md5': 'a74f50b310c83170319ba16de6955192',
+ 'md5': '4fa26a35f9d1bf4b646590ba8e84be19',
'info_dict': {
'id': '560070183650213889',
'ext': 'mp4',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 80.155,
},
+ },
+ {
+ 'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
+ 'md5': 'b6f35e8b08a0bec6c8af77a2f4b3a814',
+ 'info_dict': {
+ 'id': 'dq4Oj5quskI',
+ 'ext': 'mp4',
+ 'title': 'Ubuntu 11.10 Overview',
+ 'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/',
+ 'upload_date': '20111013',
+ 'uploader': 'OMG! Ubuntu!',
+ 'uploader_id': 'omgubuntu',
+ },
+ 'add_ie': ['Youtube'],
+ },
+ {
+ 'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568',
+ 'md5': 'ab2745d0b0ce53319a534fccaa986439',
+ 'info_dict': {
+ 'id': 'iBb2x00UVlv',
+ 'ext': 'mp4',
+ 'upload_date': '20151113',
+ 'uploader_id': '1189339351084113920',
+ 'uploader': '@ArsenalTerje',
+ 'title': 'Vine by @ArsenalTerje',
+ },
+ 'add_ie': ['Vine'],
}
]
config = None
formats = []
for user_agent in USER_AGENTS:
- request = compat_urllib_request.Request(url)
+ request = sanitized_Request(url)
request.add_header('User-Agent', user_agent)
webpage = self._download_webpage(request, video_id)
- config = self._parse_json(
- unescapeHTML(self._search_regex(
- r'data-player-config="([^"]+)"', webpage, 'data player config')),
+ iframe_url = self._html_search_regex(
+ r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
+ webpage, 'video iframe', default=None)
+ if iframe_url:
+ return self.url_result(iframe_url)
+
+ config = self._parse_json(self._html_search_regex(
+ r'data-player-config="([^"]+)"', webpage, 'data player config'),
video_id)
if 'playlist' not in config:
if 'vmapUrl' in config:
- webpage = self._download_webpage(config['vmapUrl'], video_id + ' (xml)')
- video_url = self._search_regex(
- r'<MediaFile>\s*<!\[CDATA\[(https?://.+?)\]\]>', webpage, 'data player config (xml)')
- f = {
+ vmap_data = self._download_xml(config['vmapUrl'], video_id)
+ video_url = xpath_text(vmap_data, './/MediaFile').strip()
+ formats.append({
'url': video_url,
- }
- ext = re.search(r'\.([a-z0-9]{2,4})(\?.+)?$', video_url)
- if ext:
- f['ext'] = ext.group(1)
- formats.append(f)
+ })
break # same video regardless of UA
continue
}
-class TwitterIE(TwitterCardIE):
- _VALID_URL = r'https?://(?:www|m|mobile)?\.?twitter\.com/(?P<id>[^/]+/status/\d+)'
+class TwitterIE(InfoExtractor):
+ IE_NAME = 'twitter'
+ _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
+ _TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
_TESTS = [{
- 'url': 'https://m.twitter.com/thereaIbanksy/status/614301758345490432',
- 'md5': '8bbccb487bd7a31349b775915fcd412f',
+ 'url': 'https://twitter.com/freethenipple/status/643211948184596480',
+ 'md5': 'db6612ec5d03355953c3ca9250c97e5e',
'info_dict': {
- 'id': '614301758345490432',
+ 'id': '643211948184596480',
'ext': 'mp4',
- 'title': 'thereaIbanksy - This time lapse is so pretty \U0001f60d\U0001f60d',
+ 'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
'thumbnail': 're:^https?://.*\.jpg',
- 'duration': 29.5,
- 'description': 'banksy on Twitter: "This time lapse is so pretty \U0001f60d\U0001f60d http://t.co/QB8DDbqiR1"',
- 'uploader': 'banksy',
- 'uploader_id': 'thereaIbanksy',
+ 'duration': 12.922,
+ 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
+ 'uploader': 'FREE THE NIPPLE',
+ 'uploader_id': 'freethenipple',
+ },
+ }, {
+ 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
+ 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42',
+ 'info_dict': {
+ 'id': '657991469417025536',
+ 'ext': 'mp4',
+ 'title': 'Gifs - tu vai cai tu vai cai tu nao eh capaz disso tu vai cai',
+ 'description': 'Gifs on Twitter: "tu vai cai tu vai cai tu nao eh capaz disso tu vai cai https://t.co/tM46VHFlO5"',
+ 'thumbnail': 're:^https?://.*\.png',
+ 'uploader': 'Gifs',
+ 'uploader_id': 'giphz',
+ },
+ }, {
+ 'url': 'https://twitter.com/starwars/status/665052190608723968',
+ 'md5': '39b7199856dee6cd4432e72c74bc69d4',
+ 'info_dict': {
+ 'id': '665052190608723968',
+ 'ext': 'mp4',
+ 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.',
+ 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."',
+ 'uploader_id': 'starwars',
+ 'uploader': 'Star Wars',
},
}]
def _real_extract(self, url):
- id = self._match_id(url)
- username, twid = re.match(r'([^/]+)/status/(\d+)', id).groups()
- name = username
- url = re.sub(r'https?://(m|mobile)\.', 'https://', url)
- webpage = self._download_webpage(url, 'tweet: ' + url)
- description = unescapeHTML(self._search_regex('<title>\s*(.+?)\s*</title>', webpage, 'title'))
- title = description.replace('\n', ' ')
- splitdesc = re.match(r'^(.+?)\s*on Twitter:\s* "(.+?)"$', title)
- if splitdesc:
- name, title = splitdesc.groups()
- title = re.sub(r'\s*https?://[^ ]+', '', title) # strip 'https -_t.co_BJYgOjSeGA' junk from filenames
- card_id = self._search_regex(r'["\']/i/cards/tfw/v1/(\d+)', webpage, '/i/card/...')
- card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
- return {
- '_type': 'url_transparent',
- 'ie_key': 'TwitterCard',
- 'uploader_id': username,
- 'uploader': name,
- 'url': card_url,
+ mobj = re.match(self._VALID_URL, url)
+ user_id = mobj.group('user_id')
+ twid = mobj.group('id')
+
+ webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)
+
+ username = remove_end(self._og_search_title(webpage), ' on Twitter')
+
+ title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”')
+
+ # strip 'https -_t.co_BJYgOjSeGA' junk from filenames
+ title = re.sub(r'\s+(https?://[^ ]+)', '', title)
+
+ info = {
+ 'uploader_id': user_id,
+ 'uploader': username,
'webpage_url': url,
- 'description': description,
+ 'description': '%s on Twitter: "%s"' % (username, description),
'title': username + ' - ' + title,
}
+
+ card_id = self._search_regex(
+ r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None)
+ if card_id:
+ card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
+ info.update({
+ '_type': 'url_transparent',
+ 'ie_key': 'TwitterCard',
+ 'url': card_url,
+ })
+ return info
+
+ mobj = re.search(r'''(?x)
+ <video[^>]+class="animated-gif"[^>]+
+ (?:data-height="(?P<height>\d+)")?[^>]+
+ (?:data-width="(?P<width>\d+)")?[^>]+
+ (?:poster="(?P<poster>[^"]+)")?[^>]*>\s*
+ <source[^>]+video-src="(?P<url>[^"]+)"
+ ''', webpage)
+
+ if mobj:
+ info.update({
+ 'id': twid,
+ 'url': mobj.group('url'),
+ 'height': int_or_none(mobj.group('height')),
+ 'width': int_or_none(mobj.group('width')),
+ 'thumbnail': mobj.group('poster'),
+ })
+ return info
+
+ raise ExtractorError('There\'s not video in this tweet.')
projects / youtube-dl / blobdiff