X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=40d6823a0f8ddbbf42a54bf4b0aea9e344825600;hb=1a9c655e3b1569f315d4193e877cba0b4a863c63;hp=737cca8e13ad03fffa6848178c65415ec7d7ec7d;hpb=d11d05d07acdd11a93b02d750852dea4ae32be3b;p=youtube-dl diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 737cca8e1..40d6823a0 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -11,40 +11,39 @@ import sys import zlib import urllib2 import email.utils +import json try: import cStringIO as StringIO except ImportError: import StringIO - -try: - import json -except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): - import trivialjson as json std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1', + 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'en-us,en;q=0.5', } +try: + compat_str = unicode # Python 2 +except NameError: + compat_str = str + def preferredencoding(): """Get preferred encoding. Returns the best encoding scheme for the system, based on locale.getpreferredencoding() and some further tweaks. """ - def yield_preferredencoding(): - try: - pref = locale.getpreferredencoding() - u'TEST'.encode(pref) - except: - pref = 'UTF-8' - while True: - yield pref - return yield_preferredencoding().next() + try: + pref = locale.getpreferredencoding() + u'TEST'.encode(pref) + except: + pref = 'UTF-8' + + return pref def htmlentity_transform(matchobj): @@ -73,11 +72,90 @@ def htmlentity_transform(matchobj): # Unknown entity in name, return its literal representation return (u'&%s;' % entity) +HTMLParser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix +class IDParser(HTMLParser.HTMLParser): + """Modified HTMLParser that isolates a tag with the specified id""" + def __init__(self, id): + self.id = id + self.result = None + self.started = False + self.depth = {} + self.html = None + self.watch_startpos = False + self.error_count = 0 + HTMLParser.HTMLParser.__init__(self) + + def error(self, message): + if self.error_count > 10 or self.started: + raise HTMLParser.HTMLParseError(message, self.getpos()) + self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line + self.error_count += 1 + self.goahead(1) + + def loads(self, html): + self.html = html + self.feed(html) + self.close() + + def handle_starttag(self, tag, attrs): + attrs = dict(attrs) + if self.started: + self.find_startpos(None) + if 'id' in attrs and attrs['id'] == self.id: + self.result = [tag] + self.started = True + self.watch_startpos = True + if self.started: + if not tag in self.depth: self.depth[tag] = 0 + self.depth[tag] += 1 + + def handle_endtag(self, tag): + if self.started: + if tag in self.depth: self.depth[tag] -= 1 + if self.depth[self.result[0]] == 0: + self.started = False + self.result.append(self.getpos()) + + def find_startpos(self, x): + """Needed to put the start position of the result (self.result[1]) + after the opening tag with the requested id""" + if self.watch_startpos: + self.watch_startpos = False + self.result.append(self.getpos()) + handle_entityref = handle_charref = handle_data = handle_comment = \ + handle_decl = handle_pi = unknown_decl = find_startpos + + def get_result(self): + if self.result == None: return None + if len(self.result) != 3: return None + lines = self.html.split('\n') + lines = lines[self.result[1][0]-1:self.result[2][0]] + lines[0] = lines[0][self.result[1][1]:] + if len(lines) == 1: + lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] + lines[-1] = lines[-1][:self.result[2][1]] + return '\n'.join(lines).strip() + +def get_element_by_id(id, html): + """Return the content of the tag with the specified id in the passed HTML document""" + parser = IDParser(id) + try: + parser.loads(html) + except HTMLParser.HTMLParseError: + pass + return parser.get_result() + -def sanitize_title(utitle): - """Sanitizes a video title so it could be used as part of a filename.""" - utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) - return utitle.replace(unicode(os.sep), u'%') +def clean_html(html): + """Clean an HTML snippet into a readable string""" + # Newline vs
+ html = html.replace('\n', ' ') + html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html) + # Strip html tags + html = re.sub('<.*?>', '', html) + # Replace html entities + html = unescapeHTML(html) + return html def sanitize_open(filename, open_mode): @@ -115,9 +193,35 @@ def timeconvert(timestr): timestamp = email.utils.mktime_tz(timetuple) return timestamp -def simplify_title(title): - expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE) - return expr.sub(u'_', title).strip(u'_') +def sanitize_filename(s, restricted=False): + """Sanitizes a string so it could be used as part of a filename. + If restricted is set, use a stricter subset of allowed characters. + """ + def replace_insane(char): + if char == '?' or ord(char) < 32 or ord(char) == 127: + return '' + elif char == '"': + return '' if restricted else '\'' + elif char == ':': + return '_-' if restricted else ' -' + elif char in '\\/|*<>': + return '_' + if restricted and (char in '!&\'' or char.isspace()): + return '_' + if restricted and ord(char) > 127: + return '_' + return char + + result = u''.join(map(replace_insane, s)) + while '__' in result: + result = result.replace('__', '_') + result = result.strip('_') + # Common case of "Foreign band name - English song title" + if restricted and result.startswith('-_'): + result = result[2:] + if not result: + result = '_' + return result def orderedSet(iterable): """ Remove all duplicates from the input iterable """ @@ -133,8 +237,8 @@ def unescapeHTML(s): """ assert type(s) == type(u'') - htmlParser = HTMLParser.HTMLParser() - return htmlParser.unescape(s) + result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s) + return result def encodeFilename(s): """ @@ -143,7 +247,7 @@ def encodeFilename(s): assert type(s) == type(u'') - if sys.platform == 'win32' and sys.getwindowsversion().major >= 5: + if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: # Pass u'' directly to use Unicode APIs on Windows 2000 and up # (Detecting Windows NT 4 is tricky because 'major >= 4' would # match Windows 9x series as well. Besides, NT 4 is obsolete.) @@ -208,6 +312,13 @@ class ContentTooShortError(Exception): self.expected = expected +class Trouble(Exception): + """Trouble helper exception + + This is an exception to be handled with + FileDownloader.trouble + """ + class YoutubeDLHandler(urllib2.HTTPHandler): """Handler for HTTP requests and responses.