X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=68424aeb6b987bd2c11bf592c706f57a967be7d7;hb=b9e12a814096c9225cedde8e0c7ce2a977e8a668;hp=ed5ee222f5ccdf75563681266777c8e9c132df80;hpb=65697b3bf3bf6eaeb91a34e5308a6d2239118071;p=youtube-dl diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index ed5ee222f..68424aeb6 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1,10 +1,14 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +import calendar +import codecs +import contextlib import ctypes import datetime import email.utils import errno +import getpass import gzip import itertools import io @@ -17,9 +21,11 @@ import platform import re import ssl import socket +import struct import subprocess import sys import traceback +import xml.etree.ElementTree import zlib try: @@ -173,6 +179,11 @@ try: except NameError: compat_chr = chr +try: + from xml.etree.ElementTree import ParseError as compat_xml_parse_error +except ImportError: # Python 2.6 + from xml.parsers.expat import ExpatError as compat_xml_parse_error + def compat_ord(c): if type(c) is int: return c else: return ord(c) @@ -492,13 +503,13 @@ def orderedSet(iterable): res.append(el) return res + def unescapeHTML(s): - """ - @param s a string - """ - assert type(s) == type(u'') + if s is None: + return None + assert type(s) == compat_str - result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s) + result = re.sub(r'(?u)&(.+?);', htmlentity_transform, s) return result @@ -529,7 +540,6 @@ def encodeFilename(s, for_subprocess=False): encoding = 'utf-8' return s.encode(encoding, 'ignore') - def decodeOption(optval): if optval is None: return optval @@ -751,31 +761,66 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): https_request = http_request https_response = http_response + +def parse_iso8601(date_str): + """ Return a UNIX timestamp from the given date """ + + if date_str is None: + return None + + m = re.search( + r'Z$| ?(?P\+|-)(?P[0-9]{2}):?(?P[0-9]{2})$', + date_str) + if not m: + timezone = datetime.timedelta() + else: + date_str = date_str[:-len(m.group(0))] + if not m.group('sign'): + timezone = datetime.timedelta() + else: + sign = 1 if m.group('sign') == '+' else -1 + timezone = datetime.timedelta( + hours=sign * int(m.group('hours')), + minutes=sign * int(m.group('minutes'))) + + dt = datetime.datetime.strptime(date_str, '%Y-%m-%dT%H:%M:%S') - timezone + return calendar.timegm(dt.timetuple()) + + def unified_strdate(date_str): """Return a string with the date in the format YYYYMMDD""" + + if date_str is None: + return None + upload_date = None #Replace commas - date_str = date_str.replace(',',' ') + date_str = date_str.replace(',', ' ') # %z (UTC offset) is only supported in python>=3.2 - date_str = re.sub(r' (\+|-)[\d]*$', '', date_str) + date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str) format_expressions = [ '%d %B %Y', + '%d %b %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', + '%d.%m.%Y', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S', '%Y-%m-%d %H:%M:%S', '%d.%m.%Y %H:%M', + '%d.%m.%Y %H.%M', '%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%dT%H:%M:%S.%fZ', '%Y-%m-%dT%H:%M:%S.%f0Z', '%Y-%m-%dT%H:%M:%S', + '%Y-%m-%dT%H:%M:%S.%f', + '%Y-%m-%dT%H:%M', ] for expression in format_expressions: try: upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') - except: + except ValueError: pass if upload_date is None: timetuple = email.utils.parsedate_tz(date_str) @@ -865,25 +910,21 @@ def platform_name(): return res -def write_string(s, out=None): +def write_string(s, out=None, encoding=None): if out is None: out = sys.stderr assert type(s) == compat_str if ('b' in getattr(out, 'mode', '') or sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr - s = s.encode(preferredencoding(), 'ignore') - try: + byt = s.encode(encoding or preferredencoding(), 'ignore') + out.write(byt) + elif hasattr(out, 'buffer'): + enc = encoding or getattr(out, 'encoding', None) or preferredencoding() + byt = s.encode(enc, 'ignore') + out.buffer.write(byt) + else: out.write(s) - except UnicodeEncodeError: - # In Windows shells, this can fail even when the codec is just charmap!? - # See https://wiki.python.org/moin/PrintFails#Issue - if sys.platform == 'win32' and hasattr(out, 'encoding'): - s = s.encode(out.encoding, 'ignore').decode(out.encoding) - out.write(s) - else: - raise - out.flush() @@ -1107,11 +1148,11 @@ def setproctitle(title): libc = ctypes.cdll.LoadLibrary("libc.so.6") except OSError: return - title = title - buf = ctypes.create_string_buffer(len(title) + 1) - buf.value = title.encode('utf-8') + title_bytes = title.encode('utf-8') + buf = ctypes.create_string_buffer(len(title_bytes)) + buf.value = title_bytes try: - libc.prctl(15, ctypes.byref(buf), 0, 0, 0) + libc.prctl(15, buf, 0, 0, 0) except AttributeError: return # Strange libc, just skip this @@ -1132,8 +1173,12 @@ class HEADRequest(compat_urllib_request.Request): return "HEAD" -def int_or_none(v, scale=1): - return v if v is None else (int(v) // scale) +def int_or_none(v, scale=1, default=None): + return default if v is None else (int(v) // scale) + + +def float_or_none(v, scale=1, default=None): + return default if v is None else (float(v) / scale) def parse_duration(s): @@ -1141,7 +1186,7 @@ def parse_duration(s): return None m = re.match( - r'(?:(?:(?P[0-9]+):)?(?P[0-9]+):)?(?P[0-9]+)$', s) + r'(?:(?:(?P[0-9]+)[:h])?(?P[0-9]+)[:m])?(?P[0-9]+)s?(?::[0-9]+)?$', s) if not m: return None res = int(m.group('secs')) @@ -1172,6 +1217,10 @@ class PagedList(object): self._pagefunc = pagefunc self._pagesize = pagesize + def __len__(self): + # This is only useful for tests + return len(self.getslice()) + def getslice(self, start=0, end=None): res = [] for pagenum in itertools.count(start // self._pagesize): @@ -1208,3 +1257,80 @@ class PagedList(object): if end == nextfirstid: break return res + + +def uppercase_escape(s): + unicode_escape = codecs.getdecoder('unicode_escape') + return re.sub( + r'\\U[0-9a-fA-F]{8}', + lambda m: unicode_escape(m.group(0))[0], + s) + +try: + struct.pack(u'!I', 0) +except TypeError: + # In Python 2.6 (and some 2.7 versions), struct requires a bytes argument + def struct_pack(spec, *args): + if isinstance(spec, compat_str): + spec = spec.encode('ascii') + return struct.pack(spec, *args) + + def struct_unpack(spec, *args): + if isinstance(spec, compat_str): + spec = spec.encode('ascii') + return struct.unpack(spec, *args) +else: + struct_pack = struct.pack + struct_unpack = struct.unpack + + +def read_batch_urls(batch_fd): + def fixup(url): + if not isinstance(url, compat_str): + url = url.decode('utf-8', 'replace') + BOM_UTF8 = u'\xef\xbb\xbf' + if url.startswith(BOM_UTF8): + url = url[len(BOM_UTF8):] + url = url.strip() + if url.startswith(('#', ';', ']')): + return False + return url + + with contextlib.closing(batch_fd) as fd: + return [url for url in map(fixup, fd) if url] + + +def urlencode_postdata(*args, **kargs): + return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii') + + +def parse_xml(s): + class TreeBuilder(xml.etree.ElementTree.TreeBuilder): + def doctype(self, name, pubid, system): + pass # Ignore doctypes + + parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder()) + kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {} + return xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs) + + +if sys.version_info < (3, 0) and sys.platform == 'win32': + def compat_getpass(prompt, *args, **kwargs): + if isinstance(prompt, compat_str): + prompt = prompt.encode(preferredencoding()) + return getpass.getpass(prompt, *args, **kwargs) +else: + compat_getpass = getpass.getpass + + +US_RATINGS = { + 'G': 0, + 'PG': 10, + 'PG-13': 13, + 'R': 16, + 'NC': 18, +} + + +def strip_jsonp(code): + return re.sub(r'(?s)^[a-zA-Z_]+\s*\(\s*(.*)\);\s*?\s*$', r'\1', code)