Credit @adamvoss for bandcamp:weekly (#12758)

[youtube-dl] / youtube_dl / extractor / bbc.py

diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 0e05b782b7ddbcbe8a3bb84215ad5128f54c86ac..7cd4446b44ed4f487cca7df258005efd9f836500 100644 (file)
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -6,14 +6,18 @@ import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
     dict_get,
     ExtractorError,
     float_or_none,
+    get_element_by_class,
     int_or_none,
     parse_duration,
     parse_iso8601,
     try_get,
     unescapeHTML,
+    urlencode_postdata,
+    urljoin,
 )
 from ..compat import (
     compat_etree_fromstring,
@@ -38,6 +42,9 @@ class BBCCoUkIE(InfoExtractor):
                         (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
                     ''' % _ID_REGEX
 
+    _LOGIN_URL = 'https://account.bbc.com/signin'
+    _NETRC_MACHINE = 'bbc'
+
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
         # with geolocation in some cases when it's even not geo restricted at all (e.g.
@@ -227,6 +234,39 @@ class BBCCoUkIE(InfoExtractor):
 
     _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
 
+    def _login(self):
+        username, password = self._get_login_info()
+        if username is None:
+            return
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading signin page')
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'username': username,
+            'password': password,
+        })
+
+        post_url = urljoin(self._LOGIN_URL, self._search_regex(
+            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
+            'post url', default=self._LOGIN_URL, group='url'))
+
+        response, urlh = self._download_webpage_handle(
+            post_url, None, 'Logging in', data=urlencode_postdata(login_form),
+            headers={'Referer': self._LOGIN_URL})
+
+        if self._LOGIN_URL in urlh.geturl():
+            error = clean_html(get_element_by_class('form-message', response))
+            if error:
+                raise ExtractorError(
+                    'Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+    def _real_initialize(self):
+        self._login()
+
     class MediaSelectionError(Exception):
         def __init__(self, id):
             self.id = id
@@ -409,7 +449,7 @@ class BBCCoUkIE(InfoExtractor):
                 description = smp_config['summary']
                 for item in smp_config['items']:
                     kind = item['kind']
-                    if kind != 'programme' and kind != 'radioProgramme':
+                    if kind not in ('programme', 'radioProgramme'):
                         continue
                     programme_id = item.get('vpid')
                     duration = int_or_none(item.get('duration'))
@@ -450,7 +490,7 @@ class BBCCoUkIE(InfoExtractor):
 
         for item in self._extract_items(playlist):
             kind = item.get('kind')
-            if kind != 'programme' and kind != 'radioProgramme':
+            if kind not in ('programme', 'radioProgramme'):
                 continue
             title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
             description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)