X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=aaa5c24c8565fffb85295188daf7bbd52f5aae89;hb=49a25557b082a147c875015ceeecb370671f025c;hp=05b24387165fd5678cd77a7e37918bb2ce354d51;hpb=44dbe8903580e1e62ea6f3881b2fa469853c4a83;p=youtube-dl diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 05b243871..aaa5c24c8 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -14,6 +14,8 @@ from ..utils import ( clean_html, compiled_regex_type, ExtractorError, + RegexNotFoundError, + unescapeHTML, ) class InfoExtractor(object): @@ -34,6 +36,8 @@ class InfoExtractor(object): title: Video title, unescaped. ext: Video filename extension. + Instead of url and ext, formats can also specified. + The following fields are optional: format: The video format, defaults to ext (used for --get-format) @@ -46,12 +50,28 @@ class InfoExtractor(object): uploader_id: Nickname or id of the video uploader. location: Physical location of the video. player_url: SWF Player URL (used for rtmpdump). - subtitles: The subtitle file contents. + subtitles: The subtitle file contents as a dictionary in the format + {language: subtitles}. view_count: How many users have watched the video on the platform. urlhandle: [internal] The urlHandle to be used to download the file, like returned by urllib.request.urlopen - - The fields should all be Unicode strings. + age_limit: Age restriction for the video, as an integer (years) + formats: A list of dictionaries for each format available, it must + be ordered from worst to best quality. Potential fields: + * url Mandatory. The URL of the video file + * ext Will be calculated from url if missing + * format A human-readable description of the format + ("mp4 container with h264/opus"). + Calculated from the format_id, width, height + and format_note fields if missing. + * format_id A short description of the format + ("mp4_h264_opus" or "19") + * format_note Additional info about the format + ("3D" or "DASH video") + * width Width of the video, if known + * height Height of the video, if known + + Unless mentioned otherwise, the fields should be Unicode strings. Subclasses of this one should re-define the _real_initialize() and _real_extract() methods and define a _VALID_URL regexp. @@ -76,7 +96,13 @@ class InfoExtractor(object): @classmethod def suitable(cls, url): """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url) is not None + + # This does not use has/getattr intentionally - we want to know whether + # we have cached the regexp for *this* class, whereas getattr would also + # match the superclass + if '_VALID_URL_RE' not in cls.__dict__: + cls._VALID_URL_RE = re.compile(cls._VALID_URL) + return cls._VALID_URL_RE.match(url) is not None @classmethod def working(cls): @@ -106,6 +132,11 @@ class InfoExtractor(object): """Real extraction process. Redefine in subclasses.""" pass + @classmethod + def ie_key(cls): + """A string for getting the InfoExtractor with get_info_extractor""" + return cls.__name__[:-2] + @property def IE_NAME(self): return type(self).__name__[:-2] @@ -121,18 +152,28 @@ class InfoExtractor(object): except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: if errnote is None: errnote = u'Unable to download webpage' - raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) + raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err) def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): """ Returns a tuple (page content as string, URL handle) """ + + # Strip hashes from the URL (#1038) + if isinstance(url_or_request, (compat_str, str)): + url_or_request = url_or_request.partition('#')[0] + urlh = self._request_webpage(url_or_request, video_id, note, errnote) content_type = urlh.headers.get('Content-Type', '') + webpage_bytes = urlh.read() m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) if m: encoding = m.group(1) else: - encoding = 'utf-8' - webpage_bytes = urlh.read() + m = re.search(br']+charset=[\'"]?([^\'")]+)[ /\'">]', + webpage_bytes[:1024]) + if m: + encoding = m.group(1).decode('ascii') + else: + encoding = 'utf-8' if self._downloader.params.get('dump_intermediate_pages', False): try: url = url_or_request.get_full_url() @@ -191,7 +232,7 @@ class InfoExtractor(object): Perform a regex search on the given string, using a single or a list of patterns returning the first matching group. In case of failure return a default value or raise a WARNING or a - ExtractorError, depending on fatal, specifying the field name. + RegexNotFoundError, depending on fatal, specifying the field name. """ if isinstance(pattern, (str, compat_str, compiled_regex_type)): mobj = re.search(pattern, string, flags) @@ -211,7 +252,7 @@ class InfoExtractor(object): elif default is not None: return default elif fatal: - raise ExtractorError(u'Unable to extract %s' % _name) + raise RegexNotFoundError(u'Unable to extract %s' % _name) else: self._downloader.report_warning(u'unable to extract %s; ' u'please report this issue on http://yt-dl.org/bug' % _name) @@ -259,16 +300,17 @@ class InfoExtractor(object): # Helper functions for extracting OpenGraph info @staticmethod - def _og_regex(property): - return r'