X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=64ab3091070013f840e44bf6c29a808fa75c47d1;hb=c496ca96e7639e5dd0020074b7ada18c2bd4ae3e;hp=d366c417360a70678dac87a0567a3d96f3a97c74;hpb=46b9d8295d43bb4a5954da95293ef2490eb28b5e;p=youtube-dl diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index d366c4173..64ab30910 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1,17 +1,20 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +import datetime +import email.utils +import errno import gzip import io import json import locale import os +import platform import re +import socket import sys import traceback import zlib -import email.utils -import json try: import urllib.request as compat_urllib_request @@ -33,6 +36,11 @@ 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 @@ -53,6 +61,11 @@ try: except ImportError: # Python 2 import httplib as compat_http_client +try: + from urllib.error import HTTPError as compat_HTTPError +except ImportError: # Python 2 + from urllib2 import HTTPError as compat_HTTPError + try: from subprocess import DEVNULL compat_subprocess_get_DEVNULL = lambda: DEVNULL @@ -148,6 +161,13 @@ 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', @@ -189,6 +209,20 @@ 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. @@ -333,12 +367,20 @@ 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): @@ -429,12 +471,44 @@ def decodeOption(optval): assert isinstance(optval, compat_str) return optval +def formatSeconds(secs): + if secs > 3600: + return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60) + elif secs > 60: + return '%d:%02d' % (secs // 60, secs % 60) + else: + return '%d' % secs + +def make_HTTPS_handler(opts): + if sys.version_info < (3,2): + # Python's 2.x handler is very simplistic + return compat_urllib_request.HTTPSHandler() + else: + import ssl + context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) + context.set_default_verify_paths() + + context.verify_mode = (ssl.CERT_NONE + if opts.no_check_certificate + else ssl.CERT_REQUIRED) + return compat_urllib_request.HTTPSHandler(context=context) + 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, cause=None): + """ 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. Make sure you are using the latest version; type youtube-dl -U to update.' super(ExtractorError, self).__init__(msg) + self.traceback = tb + self.exc_info = sys.exc_info() # preserve original exception + self.cause = cause def format_traceback(self): if self.traceback is None: @@ -449,7 +523,10 @@ class DownloadError(Exception): configured to continue on errors. They will contain the appropriate error message. """ - pass + def __init__(self, msg, exc_info=None): + """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """ + super(DownloadError, self).__init__(msg) + self.exc_info = exc_info class SameFileError(Exception): @@ -552,8 +629,23 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): old_resp = resp # gzip if resp.headers.get('Content-encoding', '') == 'gzip': - gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r') - resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) + content = resp.read() + gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb') + try: + uncompressed = io.BytesIO(gz.read()) + except IOError as original_ioerror: + # There may be junk add the end of the file + # See http://stackoverflow.com/q/4928560/35070 for details + for i in range(1, 1024): + try: + gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb') + uncompressed = io.BytesIO(gz.read()) + except IOError: + continue + break + else: + raise original_ioerror + resp = self.addinfourl_wrapper(uncompressed, old_resp.headers, old_resp.url, old_resp.code) resp.msg = old_resp.msg # deflate if resp.headers.get('Content-encoding', '') == 'deflate': @@ -564,3 +656,90 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): https_request = http_request https_response = http_response + +def unified_strdate(date_str): + """Return a string with the date in the format YYYYMMDD""" + upload_date = None + #Replace commas + date_str = date_str.replace(',',' ') + # %z (UTC offset) is only supported in python>=3.2 + date_str = re.sub(r' (\+|-)[\d]*$', '', date_str) + format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S', '%d.%m.%Y %H:%M'] + for expression in format_expressions: + try: + upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') + except: + pass + return upload_date + +def determine_ext(url, default_ext=u'unknown_video'): + guess = url.partition(u'?')[0].rpartition(u'.')[2] + if re.match(r'^[A-Za-z0-9]+$', guess): + return guess + else: + return default_ext + +def subtitles_filename(filename, sub_lang, sub_format): + return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format + +def date_from_str(date_str): + """ + Return a datetime object from a string in the format YYYYMMDD or + (now|today)[+-][0-9](day|week|month|year)(s)?""" + today = datetime.date.today() + if date_str == 'now'or date_str == 'today': + return today + match = re.match('(now|today)(?P[+-])(?P