X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=cf2ea654e892c5f8882a4ecaae19bdcb5afbbbfd;hb=cbdbb7666540ba07ab7e4a3a7bc34759bf0ca6d9;hp=f2342b10a0e2521be52c8ffed0c279bceaa15e5c;hpb=086d7b4500dad720e548233e425b4c08bfe99e3e;p=youtube-dl diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index f2342b10a..cf2ea654e 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1,6 +1,7 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +import errno import gzip import io import json @@ -11,7 +12,7 @@ import sys import traceback import zlib import email.utils -import json +import socket import datetime try: @@ -34,6 +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 @@ -149,6 +155,13 @@ try: except NameError: compat_chr = chr +def compat_ord(c): + if type(c) is int: return c + else: return ord(c) + +# This is not clearly defined otherwise +compiled_regex_type = type(re.compile('')) + std_headers = { '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', @@ -190,6 +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]+$', key) + assert re.match(r'^[a-zA-Z@]*$', 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. @@ -334,12 +361,20 @@ def sanitize_open(filename, open_mode): stream = open(encodeFilename(filename), open_mode) return (stream, filename) except (IOError, OSError) as err: - # In case of error, try to remove win32 forbidden chars - filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename) + if err.errno in (errno.EACCES,): + raise - # An exception here should be caught in the caller - stream = open(encodeFilename(filename), open_mode) - return (stream, filename) + # In case of error, try to remove win32 forbidden chars + alt_filename = os.path.join( + re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part) + for path_part in os.path.split(filename) + ) + if alt_filename == filename: + raise + else: + # An exception here should be caught in the caller + stream = open(encodeFilename(filename), open_mode) + return (stream, alt_filename) def timeconvert(timestr): @@ -454,9 +489,17 @@ 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). """ + 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 self.exc_info = sys.exc_info() # preserve original exception @@ -599,7 +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]*$', '', date_str) - format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S'] + format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S', '%d.%m.%Y %H:%M'] for expression in format_expressions: try: upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') @@ -607,6 +650,13 @@ def unified_strdate(date_str): pass return upload_date +def determine_ext(url, default_ext=u'unknown_video'): + guess = url.partition(u'?')[0].rpartition(u'.')[2] + if re.match(r'^[A-Za-z0-9]+$', 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