diff options
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/Utils.py | 118 | ||||
-rw-r--r-- | youtube_dl/trivialjson.py | 109 |
2 files changed, 114 insertions, 113 deletions
diff --git a/youtube_dl/Utils.py b/youtube_dl/Utils.py index f924b98f7..737cca8e1 100644 --- a/youtube_dl/Utils.py +++ b/youtube_dl/Utils.py @@ -16,6 +16,11 @@ 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', @@ -260,116 +265,3 @@ class YoutubeDLHandler(urllib2.HTTPHandler): resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code) resp.msg = old_resp.msg return resp - -try: - import json -except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson): - import re - class json(object): - @staticmethod - def loads(s): - s = s.decode('UTF-8') - def raiseError(msg, i): - raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) - def skipSpace(i, expectMore=True): - while i < len(s) and s[i] in ' \t\r\n': - i += 1 - if expectMore: - if i >= len(s): - raiseError('Premature end', i) - return i - def decodeEscape(match): - esc = match.group(1) - _STATIC = { - '"': '"', - '\\': '\\', - '/': '/', - 'b': unichr(0x8), - 'f': unichr(0xc), - 'n': '\n', - 'r': '\r', - 't': '\t', - } - if esc in _STATIC: - return _STATIC[esc] - if esc[0] == 'u': - if len(esc) == 1+4: - return unichr(int(esc[1:5], 16)) - if len(esc) == 5+6 and esc[5:7] == '\\u': - hi = int(esc[1:5], 16) - low = int(esc[7:11], 16) - return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) - raise ValueError('Unknown escape ' + str(esc)) - def parseString(i): - i += 1 - e = i - while True: - e = s.index('"', e) - bslashes = 0 - while s[e-bslashes-1] == '\\': - bslashes += 1 - if bslashes % 2 == 1: - e += 1 - continue - break - rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') - stri = rexp.sub(decodeEscape, s[i:e]) - return (e+1,stri) - def parseObj(i): - i += 1 - res = {} - i = skipSpace(i) - if s[i] == '}': # Empty dictionary - return (i+1,res) - while True: - if s[i] != '"': - raiseError('Expected a string object key', i) - i,key = parseString(i) - i = skipSpace(i) - if i >= len(s) or s[i] != ':': - raiseError('Expected a colon', i) - i,val = parse(i+1) - res[key] = val - i = skipSpace(i) - if s[i] == '}': - return (i+1, res) - if s[i] != ',': - raiseError('Expected comma or closing curly brace', i) - i = skipSpace(i+1) - def parseArray(i): - res = [] - i = skipSpace(i+1) - if s[i] == ']': # Empty array - return (i+1,res) - while True: - i,val = parse(i) - res.append(val) - i = skipSpace(i) # Raise exception if premature end - if s[i] == ']': - return (i+1, res) - if s[i] != ',': - raiseError('Expected a comma or closing bracket', i) - i = skipSpace(i+1) - def parseDiscrete(i): - for k,v in {'true': True, 'false': False, 'null': None}.items(): - if s.startswith(k, i): - return (i+len(k), v) - raiseError('Not a boolean (or null)', i) - def parseNumber(i): - mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) - if mobj is None: - raiseError('Not a number', i) - nums = mobj.group(1) - if '.' in nums or 'e' in nums or 'E' in nums: - return (i+len(nums), float(nums)) - return (i+len(nums), int(nums)) - CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} - def parse(i): - i = skipSpace(i) - i,res = CHARMAP.get(s[i], parseNumber)(i) - i = skipSpace(i, False) - return (i,res) - i,res = parse(0) - if i < len(s): - raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') - return res diff --git a/youtube_dl/trivialjson.py b/youtube_dl/trivialjson.py new file mode 100644 index 000000000..7cce2a98f --- /dev/null +++ b/youtube_dl/trivialjson.py @@ -0,0 +1,109 @@ +"""trivialjson (https://github.com/phihag/trivialjson)""" + +import re +def loads(s): + s = s.decode('UTF-8') + def raiseError(msg, i): + raise ValueError(msg + ' at position ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:])) + def skipSpace(i, expectMore=True): + while i < len(s) and s[i] in ' \t\r\n': + i += 1 + if expectMore: + if i >= len(s): + raiseError('Premature end', i) + return i + def decodeEscape(match): + esc = match.group(1) + _STATIC = { + '"': '"', + '\\': '\\', + '/': '/', + 'b': unichr(0x8), + 'f': unichr(0xc), + 'n': '\n', + 'r': '\r', + 't': '\t', + } + if esc in _STATIC: + return _STATIC[esc] + if esc[0] == 'u': + if len(esc) == 1+4: + return unichr(int(esc[1:5], 16)) + if len(esc) == 5+6 and esc[5:7] == '\\u': + hi = int(esc[1:5], 16) + low = int(esc[7:11], 16) + return unichr((hi - 0xd800) * 0x400 + low - 0xdc00 + 0x10000) + raise ValueError('Unknown escape ' + str(esc)) + def parseString(i): + i += 1 + e = i + while True: + e = s.index('"', e) + bslashes = 0 + while s[e-bslashes-1] == '\\': + bslashes += 1 + if bslashes % 2 == 1: + e += 1 + continue + break + rexp = re.compile(r'\\(u[dD][89aAbB][0-9a-fA-F]{2}\\u[0-9a-fA-F]{4}|u[0-9a-fA-F]{4}|.|$)') + stri = rexp.sub(decodeEscape, s[i:e]) + return (e+1,stri) + def parseObj(i): + i += 1 + res = {} + i = skipSpace(i) + if s[i] == '}': # Empty dictionary + return (i+1,res) + while True: + if s[i] != '"': + raiseError('Expected a string object key', i) + i,key = parseString(i) + i = skipSpace(i) + if i >= len(s) or s[i] != ':': + raiseError('Expected a colon', i) + i,val = parse(i+1) + res[key] = val + i = skipSpace(i) + if s[i] == '}': + return (i+1, res) + if s[i] != ',': + raiseError('Expected comma or closing curly brace', i) + i = skipSpace(i+1) + def parseArray(i): + res = [] + i = skipSpace(i+1) + if s[i] == ']': # Empty array + return (i+1,res) + while True: + i,val = parse(i) + res.append(val) + i = skipSpace(i) # Raise exception if premature end + if s[i] == ']': + return (i+1, res) + if s[i] != ',': + raiseError('Expected a comma or closing bracket', i) + i = skipSpace(i+1) + def parseDiscrete(i): + for k,v in {'true': True, 'false': False, 'null': None}.items(): + if s.startswith(k, i): + return (i+len(k), v) + raiseError('Not a boolean (or null)', i) + def parseNumber(i): + mobj = re.match('^(-?(0|[1-9][0-9]*)(\.[0-9]*)?([eE][+-]?[0-9]+)?)', s[i:]) + if mobj is None: + raiseError('Not a number', i) + nums = mobj.group(1) + if '.' in nums or 'e' in nums or 'E' in nums: + return (i+len(nums), float(nums)) + return (i+len(nums), int(nums)) + CHARMAP = {'{': parseObj, '[': parseArray, '"': parseString, 't': parseDiscrete, 'f': parseDiscrete, 'n': parseDiscrete} + def parse(i): + i = skipSpace(i) + i,res = CHARMAP.get(s[i], parseNumber)(i) + i = skipSpace(i, False) + return (i,res) + i,res = parse(0) + if i < len(s): + raise ValueError('Extra data at end of input (index ' + str(i) + ' of ' + repr(s) + ': ' + repr(s[i:]) + ')') + return res |