X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=017f06c42e9a019e18e25480c5e5d8d3aaaef335;hb=e3700fc9e44c7820e1c38264c84a315c5f91bb2d;hp=463804e183117b23efd8f0e4b0ad9b132e519ddb;hpb=a7c0f8602e91cc96962c7eade10860b61afc3728;p=youtube-dl diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 463804e18..017f06c42 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -8,6 +8,7 @@ import locale import os import re import sys +import traceback import zlib import email.utils import json @@ -154,6 +155,7 @@ std_headers = { 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'en-us,en;q=0.5', } + def preferredencoding(): """Get preferred encoding. @@ -187,7 +189,6 @@ else: with open(fn, 'w', encoding='utf-8') as f: json.dump(obj, f) - def htmlentity_transform(matchobj): """Transforms an HTML entity to a character. @@ -279,6 +280,12 @@ class AttrParser(compat_html_parser.HTMLParser): lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] lines[-1] = lines[-1][:self.result[2][1]] return '\n'.join(lines).strip() +# Hack for https://github.com/rg3/youtube-dl/issues/662 +if sys.version_info < (2, 7, 3): + AttrParser.parse_endtag = (lambda self, i: + i + len("") + if self.rawdata[i:].startswith("") + else compat_html_parser.HTMLParser.parse_endtag(self, i)) def get_element_by_id(id, html): """Return the content of the tag with the specified ID in the passed HTML document""" @@ -304,7 +311,7 @@ def clean_html(html): html = re.sub('<.*?>', '', html) # Replace html entities html = unescapeHTML(html) - return html + return html.strip() def sanitize_open(filename, open_mode): @@ -322,7 +329,7 @@ def sanitize_open(filename, open_mode): if sys.platform == 'win32': import msvcrt msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) - return (sys.stdout, filename) + return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename) stream = open(encodeFilename(filename), open_mode) return (stream, filename) except (IOError, OSError) as err: @@ -408,7 +415,33 @@ def encodeFilename(s): # match Windows 9x series as well. Besides, NT 4 is obsolete.) return s else: - return s.encode(sys.getfilesystemencoding(), 'ignore') + encoding = sys.getfilesystemencoding() + if encoding is None: + encoding = 'utf-8' + return s.encode(encoding, 'ignore') + +def decodeOption(optval): + if optval is None: + return optval + if isinstance(optval, bytes): + optval = optval.decode(preferredencoding()) + + assert isinstance(optval, compat_str) + return optval + +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). """ + super(ExtractorError, self).__init__(msg) + self.traceback = tb + self.exc_info = sys.exc_info() # preserve original exception + + def format_traceback(self): + if self.traceback is None: + return None + return u''.join(traceback.format_tb(self.traceback)) + class DownloadError(Exception): """Download Error exception. @@ -417,7 +450,10 @@ 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): @@ -435,7 +471,8 @@ class PostProcessingError(Exception): This exception may be raised by PostProcessor's .run() method to indicate an error in the postprocessing task. """ - pass + def __init__(self, msg): + self.msg = msg class MaxDownloadsReached(Exception): """ --max-downloads limit has been reached. """ @@ -500,14 +537,19 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): return ret def http_request(self, req): - for h in std_headers: + for h,v in std_headers.items(): if h in req.headers: del req.headers[h] - req.add_header(h, std_headers[h]) + req.add_header(h, v) if 'Youtubedl-no-compression' in req.headers: if 'Accept-encoding' in req.headers: del req.headers['Accept-encoding'] del req.headers['Youtubedl-no-compression'] + if 'Youtubedl-user-agent' in req.headers: + if 'User-agent' in req.headers: + del req.headers['User-agent'] + req.headers['User-agent'] = req.headers['Youtubedl-user-agent'] + del req.headers['Youtubedl-user-agent'] return req def http_response(self, req, resp):