X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=59eeaf4a89084783e1ca2607840b3b7dfc4670f5;hb=0f90943e455fd0e4f323fa6d43092060c8b1db61;hp=4d415bd611ec4020052a3c18cfe5fb6dbd6309fc;hpb=515d7a5e73082c0f2e35bf7e778573bb2bbd576e;p=youtube-dl diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 4d415bd61..59eeaf4a8 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -35,6 +35,11 @@ try: except ImportError: # Python 2 from urlparse import urlparse as compat_urllib_parse_urlparse +try: + import urllib.parse as compat_urlparse +except ImportError: # Python 2 + import urlparse as compat_urlparse + try: import http.cookiejar as compat_cookiejar except ImportError: # Python 2 @@ -198,6 +203,20 @@ else: with open(fn, 'w', encoding='utf-8') as f: json.dump(obj, f) +if sys.version_info >= (2,7): + def find_xpath_attr(node, xpath, key, val): + """ Find the xpath xpath[@key=val] """ + assert re.match(r'^[a-zA-Z]+$', key) + assert re.match(r'^[a-zA-Z@\s]*$', val) + expr = xpath + u"[@%s='%s']" % (key, val) + return node.find(expr) +else: + def find_xpath_attr(node, xpath, key, val): + for f in node.findall(xpath): + if f.attrib.get(key) == val: + return f + return None + def htmlentity_transform(matchobj): """Transforms an HTML entity to a character. @@ -470,11 +489,15 @@ def make_HTTPS_handler(opts): class ExtractorError(Exception): """Error during info extraction.""" - def __init__(self, msg, tb=None): - """ tb, if given, is the original traceback (so that it can be printed out). """ - - if not sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError): - msg = msg + u'; please report this issue on http://yt-dl.org/bug' + def __init__(self, msg, tb=None, expected=False): + """ tb, if given, is the original traceback (so that it can be printed out). + If expected is set, this is a normal error message and most likely not a bug in youtube-dl. + """ + + if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError): + expected = True + if not expected: + msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output.' super(ExtractorError, self).__init__(msg) self.traceback = tb @@ -619,7 +642,7 @@ def unified_strdate(date_str): date_str = date_str.replace(',',' ') # %z (UTC offset) is only supported in python>=3.2 date_str = re.sub(r' (\+|-)[\d]*$', '', date_str) - format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S'] + format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S', '%d.%m.%Y %H:%M'] for expression in format_expressions: try: upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') @@ -627,6 +650,13 @@ def unified_strdate(date_str): pass return upload_date +def determine_ext(url, default_ext=u'unknown_video'): + guess = url.partition(u'?')[0].rpartition(u'.')[2] + if re.match(r'^[A-Za-z0-9]+$', guess): + return guess + else: + return default_ext + def date_from_str(date_str): """ Return a datetime object from a string in the format YYYYMMDD or