X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b238854ce845f3796daac74edab2e8a373e8ba1a..d018d3313032e12968a6add6800e51d412e2f602:/youtube_dl/extractor/facebook.py?ds=sidebyside

diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py
index 3b21071..fd85441 100644
--- a/youtube_dl/extractor/facebook.py
+++ b/youtube_dl/extractor/facebook.py
@@ -1,53 +1,87 @@
+from __future__ import unicode_literals
+
 import json
 import re
 import socket
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
-    compat_urllib_parse,
-    compat_urllib_request,
-
+    compat_urllib_parse_unquote,
+)
+from ..utils import (
     ExtractorError,
+    limit_length,
+    sanitized_Request,
+    urlencode_postdata,
+    get_element_by_id,
+    clean_html,
 )
 
 
 class FacebookIE(InfoExtractor):
-    """Information Extractor for Facebook"""
-
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+    _VALID_URL = r'''(?x)
+        https?://(?:\w+\.)?facebook\.com/
+        (?:[^#]*?\#!/)?
+        (?:
+            (?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
+            (?:v|video_id)=|
+            [^/]+/videos/(?:[^/]+/)?
+        )
+        (?P<id>[0-9]+)
+        (?:.*)'''
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
-    IE_NAME = u'facebook'
-    _TEST = {
-        u'url': u'https://www.facebook.com/photo.php?v=120708114770723',
-        u'file': u'120708114770723.mp4',
-        u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
-        u'info_dict': {
-            u"duration": 279, 
-            u"title": u"PEOPLE ARE AWESOME 2013"
+    IE_NAME = 'facebook'
+    _TESTS = [{
+        'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
+        'md5': '6a40d33c0eccbb1af76cf0485a052659',
+        'info_dict': {
+            'id': '637842556329505',
+            'ext': 'mp4',
+            'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
+            'uploader': 'Tennis on Facebook',
         }
-    }
-
-    def report_login(self):
-        """Report attempt to log in."""
-        self.to_screen(u'Logging in')
+    }, {
+        'note': 'Video without discernible title',
+        'url': 'https://www.facebook.com/video.php?v=274175099429670',
+        'info_dict': {
+            'id': '274175099429670',
+            'ext': 'mp4',
+            'title': 'Facebook video #274175099429670',
+            'uploader': 'Asif Nawab Butt',
+        },
+        'expected_warnings': [
+            'title'
+        ]
+    }, {
+        'url': 'https://www.facebook.com/video.php?v=10204634152394104',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
+        'only_matching': True,
+    }]
 
     def _login(self):
         (useremail, password) = self._get_login_info()
         if useremail is None:
             return
 
-        login_page_req = compat_urllib_request.Request(self._LOGIN_URL)
+        login_page_req = sanitized_Request(self._LOGIN_URL)
         login_page_req.add_header('Cookie', 'locale=en_US')
-        self.report_login()
-        login_page = self._download_webpage(login_page_req, None, note=False,
-            errnote=u'Unable to download login page')
-        lsd = self._search_regex(r'"lsd":"(\w*?)"', login_page, u'lsd')
-        lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, u'lgnrnd')
+        login_page = self._download_webpage(login_page_req, None,
+                                            note='Downloading login page',
+                                            errnote='Unable to download login page')
+        lsd = self._search_regex(
+            r'<input type="hidden" name="lsd" value="([^"]*)"',
+            login_page, 'lsd')
+        lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd')
 
         login_form = {
             'email': useremail,
@@ -59,39 +93,37 @@ class FacebookIE(InfoExtractor):
             'legacy_return': '1',
             'timezone': '-60',
             'trynum': '1',
-            }
-        request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+        }
+        request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         try:
-            login_results = compat_urllib_request.urlopen(request).read()
+            login_results = self._download_webpage(request, None,
+                                                   note='Logging in', errnote='unable to fetch login page')
             if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
-                self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+                self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
                 return
 
             check_form = {
-                'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, u'fb_dtsg'),
-                'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, u'nh'),
+                'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
+                'h': self._search_regex(
+                    r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
-                'submit[Continue]': self._search_regex(r'<input value="(.*?)" name="submit\[Continue\]"', login_results, u'continue'),
             }
-            check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, compat_urllib_parse.urlencode(check_form))
+            check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
             check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            check_response = compat_urllib_request.urlopen(check_req).read()
+            check_response = self._download_webpage(check_req, None,
+                                                    note='Confirming login')
             if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
-                self._downloader.report_warning(u'Unable to confirm login, you have to login in your brower and authorize the login.')
+                self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.')
         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))
+            self._downloader.report_warning('unable to log in: %s' % compat_str(err))
             return
 
     def _real_initialize(self):
         self._login()
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        video_id = mobj.group('ID')
-
+        video_id = self._match_id(url)
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)
 
@@ -102,31 +134,45 @@ class FacebookIE(InfoExtractor):
             m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
             if m_msg is not None:
                 raise ExtractorError(
-                    u'The video is not available, Facebook said: "%s"' % m_msg.group(1),
+                    'The video is not available, Facebook said: "%s"' % m_msg.group(1),
                     expected=True)
             else:
-                raise ExtractorError(u'Cannot parse data')
+                raise ExtractorError('Cannot parse data')
         data = dict(json.loads(m.group(1)))
-        params_raw = compat_urllib_parse.unquote(data['params'])
+        params_raw = compat_urllib_parse_unquote(data['params'])
         params = json.loads(params_raw)
-        video_data = params['video_data'][0]
-        video_url = video_data.get('hd_src')
-        if not video_url:
-            video_url = video_data['sd_src']
-        if not video_url:
-            raise ExtractorError(u'Cannot find video URL')
-        video_duration = int(video_data['video_duration'])
-        thumbnail = video_data['thumbnail_src']
 
-        video_title = self._html_search_regex(
-            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, u'title')
+        formats = []
+        for format_id, f in params['video_data'].items():
+            if not f or not isinstance(f, list):
+                continue
+            for quality in ('sd', 'hd'):
+                for src_type in ('src', 'src_no_ratelimit'):
+                    src = f[0].get('%s_%s' % (quality, src_type))
+                    if src:
+                        formats.append({
+                            'format_id': '%s_%s_%s' % (format_id, quality, src_type),
+                            'url': src,
+                            'preference': -10 if format_id == 'progressive' else 0,
+                        })
+        if not formats:
+            raise ExtractorError('Cannot find video formats')
 
-        info = {
+        video_title = self._html_search_regex(
+            r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
+            default=None)
+        if not video_title:
+            video_title = self._html_search_regex(
+                r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
+                webpage, 'alternative title', fatal=False)
+            video_title = limit_length(video_title, 80)
+        if not video_title:
+            video_title = 'Facebook video #%s' % video_id
+        uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
+
+        return {
             'id': video_id,
             'title': video_title,
-            'url': video_url,
-            'ext': 'mp4',
-            'duration': video_duration,
-            'thumbnail': thumbnail,
+            'formats': formats,
+            'uploader': uploader,
         }
-        return [info]