diff options
| -rw-r--r-- | test/test_utils.py | 28 | ||||
| -rw-r--r-- | youtube_dl/extractor/nowvideo.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/ruutu.py | 43 | ||||
| -rw-r--r-- | youtube_dl/utils.py | 34 |
4 files changed, 71 insertions, 36 deletions
diff --git a/test/test_utils.py b/test/test_utils.py index a759b2da9..15a59692f 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -57,7 +57,9 @@ from youtube_dl.utils import ( urlencode_postdata, version_tuple, xpath_with_ns, + xpath_element, xpath_text, + xpath_attr, render_table, match_str, parse_dfxp_time_expr, @@ -264,6 +266,16 @@ class TestUtil(unittest.TestCase): self.assertEqual(find('media:song/media:author').text, 'The Author') self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3') + def test_xpath_element(self): + doc = xml.etree.ElementTree.Element('root') + div = xml.etree.ElementTree.SubElement(doc, 'div') + p = xml.etree.ElementTree.SubElement(div, 'p') + p.text = 'Foo' + self.assertEqual(xpath_element(doc, 'div/p'), p) + self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default') + self.assertTrue(xpath_element(doc, 'div/bar') is None) + self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True) + def test_xpath_text(self): testxml = '''<root> <div> @@ -272,9 +284,25 @@ class TestUtil(unittest.TestCase): </root>''' doc = xml.etree.ElementTree.fromstring(testxml) self.assertEqual(xpath_text(doc, 'div/p'), 'Foo') + self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default') self.assertTrue(xpath_text(doc, 'div/bar') is None) self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True) + def test_xpath_attr(self): + testxml = '''<root> + <div> + <p x="a">Foo</p> + </div> + </root>''' + doc = xml.etree.ElementTree.fromstring(testxml) + self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a') + self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None) + self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None) + self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default') + self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default') + self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True) + self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True) + def test_smuggle_url(self): data = {"ö": "ö", "abc": [3]} url = 'https://foo.bar/baz?x=y#a' diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index dec09cdfe..17baa9679 100644 --- a/youtube_dl/extractor/nowvideo.py +++ b/youtube_dl/extractor/nowvideo.py @@ -7,7 +7,7 @@ class NowVideoIE(NovaMovIE): IE_NAME = 'nowvideo' IE_DESC = 'NowVideo' - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co|li)'} + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|ec|sx|eu|at|ag|co|li)'} _HOST = 'www.nowvideo.ch' diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index 4e22628d0..c67ad25ce 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -6,19 +6,19 @@ from ..compat import compat_urllib_parse_urlparse from ..utils import ( determine_ext, int_or_none, + xpath_attr, xpath_text, ) class RuutuIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?ruutu\.fi/ohjelmat/(?:[^/?#]+/)*(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?ruutu\.fi/video/(?P<id>\d+)' _TESTS = [ { - 'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi', + 'url': 'http://www.ruutu.fi/video/2058907', 'md5': 'ab2093f39be1ca8581963451b3c0234f', 'info_dict': { 'id': '2058907', - 'display_id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi', 'ext': 'mp4', 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!', 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6', @@ -28,14 +28,13 @@ class RuutuIE(InfoExtractor): }, }, { - 'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa', + 'url': 'http://www.ruutu.fi/video/2057306', 'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9', 'info_dict': { 'id': '2057306', - 'display_id': 'superpesis-katso-koko-kausi-ruudussa', 'ext': 'mp4', 'title': 'Superpesis: katso koko kausi Ruudussa', - 'description': 'md5:44c44a99fdbe5b380ab74ebd75f0af77', + 'description': 'md5:da2736052fef3b2bd5e0005e63c25eac', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 40, 'age_limit': 0, @@ -44,29 +43,10 @@ class RuutuIE(InfoExtractor): ] def _real_extract(self, url): - display_id = self._match_id(url) + video_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - video_id = self._search_regex( - r'data-media-id="(\d+)"', webpage, 'media id') - - video_xml_url = None - - media_data = self._search_regex( - r'jQuery\.extend\([^,]+,\s*(.+?)\);', webpage, - 'media data', default=None) - if media_data: - media_json = self._parse_json(media_data, display_id, fatal=False) - if media_json: - xml_url = media_json.get('ruutuplayer', {}).get('xmlUrl') - if xml_url: - video_xml_url = xml_url.replace('{ID}', video_id) - - if not video_xml_url: - video_xml_url = 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id - - video_xml = self._download_xml(video_xml_url, video_id) + video_xml = self._download_xml( + 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id) formats = [] processed_urls = [] @@ -109,10 +89,9 @@ class RuutuIE(InfoExtractor): return { 'id': video_id, - 'display_id': display_id, - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True), + 'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'), + 'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'), 'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')), 'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')), 'formats': formats, diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index b7a423166..cc792be6a 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -141,7 +141,7 @@ def write_json_file(obj, fn): if sys.version_info >= (2, 7): def find_xpath_attr(node, xpath, key, val=None): """ Find the xpath xpath[@key=val] """ - assert re.match(r'^[a-zA-Z-]+$', key) + assert re.match(r'^[a-zA-Z_-]+$', key) if val: assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val) expr = xpath + ('[@%s]' % key if val is None else "[@%s='%s']" % (key, val)) @@ -176,12 +176,12 @@ def xpath_with_ns(path, ns_map): return '/'.join(replaced) -def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT): +def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT): if sys.version_info < (2, 7): # Crazy 2.6 xpath = xpath.encode('ascii') n = node.find(xpath) - if n is None or n.text is None: + if n is None: if default is not NO_DEFAULT: return default elif fatal: @@ -189,9 +189,37 @@ def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT): raise ExtractorError('Could not find XML element %s' % name) else: return None + return n + + +def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT): + n = xpath_element(node, xpath, name, fatal=fatal, default=default) + if n is None or n == default: + return n + if n.text is None: + if default is not NO_DEFAULT: + return default + elif fatal: + name = xpath if name is None else name + raise ExtractorError('Could not find XML element\'s text %s' % name) + else: + return None return n.text +def xpath_attr(node, xpath, key, name=None, fatal=False, default=NO_DEFAULT): + n = find_xpath_attr(node, xpath, key) + if n is None: + if default is not NO_DEFAULT: + return default + elif fatal: + name = '%s[@%s]' % (xpath, key) if name is None else name + raise ExtractorError('Could not find XML attribute %s' % name) + else: + return None + return n.attrib[key] + + def get_element_by_id(id, html): """Return the content of the tag with the specified ID in the passed HTML document""" return get_element_by_attribute("id", id, html) |