X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Futils.py;h=0720fe9ebb180b15e55c5c308e600063feae6026;hb=0980426559741bb9a8b2ea39b581073cf2738f5a;hp=c18c9beedb85904578dad654c624d97ccc1f68a0;hpb=056d857571158264aefb8d9f7d47c0dad768be63;p=youtube-dl.git
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index c18c9beed..0720fe9eb 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1,16 +1,21 @@
#!/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 pipes
+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
@@ -32,6 +37,11 @@ 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
@@ -52,6 +62,17 @@ 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 urllib.request import urlretrieve as compat_urlretrieve
+except ImportError: # Python 2
+ from urllib import urlretrieve as compat_urlretrieve
+
+
try:
from subprocess import DEVNULL
compat_subprocess_get_DEVNULL = lambda: DEVNULL
@@ -147,13 +168,21 @@ 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',
+ 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
}
+
def preferredencoding():
"""Get preferred encoding.
@@ -187,6 +216,32 @@ 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]+$', key)
+ assert re.match(r'^[a-zA-Z0-9@\s]*$', 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
+
+# On python2.6 the xml.etree.ElementTree.Element methods don't support
+# the namespace parameter
+def xpath_with_ns(path, ns_map):
+ components = [c.split(':') for c in path.split('/')]
+ replaced = []
+ for c in components:
+ if len(c) == 1:
+ replaced.append(c[0])
+ else:
+ ns, tag = c
+ replaced.append('{%s}%s' % (ns_map[ns], tag))
+ return '/'.join(replaced)
def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a character.
@@ -214,7 +269,17 @@ def htmlentity_transform(matchobj):
return (u'&%s;' % entity)
compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
-class AttrParser(compat_html_parser.HTMLParser):
+class BaseHTMLParser(compat_html_parser.HTMLParser):
+ def __init(self):
+ compat_html_parser.HTMLParser.__init__(self)
+ self.html = None
+
+ def loads(self, html):
+ self.html = html
+ self.feed(html)
+ self.close()
+
+class AttrParser(BaseHTMLParser):
"""Modified HTMLParser that isolates a tag with the specified attribute"""
def __init__(self, attribute, value):
self.attribute = attribute
@@ -222,10 +287,9 @@ class AttrParser(compat_html_parser.HTMLParser):
self.result = None
self.started = False
self.depth = {}
- self.html = None
self.watch_startpos = False
self.error_count = 0
- compat_html_parser.HTMLParser.__init__(self)
+ BaseHTMLParser.__init__(self)
def error(self, message):
if self.error_count > 10 or self.started:
@@ -234,11 +298,6 @@ class AttrParser(compat_html_parser.HTMLParser):
self.error_count += 1
self.goahead(1)
- def loads(self, html):
- self.html = html
- self.feed(html)
- self.close()
-
def handle_starttag(self, tag, attrs):
attrs = dict(attrs)
if self.started:
@@ -279,6 +338,12 @@ 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"""
@@ -293,17 +358,50 @@ def get_element_by_attribute(attribute, value, html):
pass
return parser.get_result()
+class MetaParser(BaseHTMLParser):
+ """
+ Modified HTMLParser that isolates a meta tag with the specified name
+ attribute.
+ """
+ def __init__(self, name):
+ BaseHTMLParser.__init__(self)
+ self.name = name
+ self.content = None
+ self.result = None
+
+ def handle_starttag(self, tag, attrs):
+ if tag != 'meta':
+ return
+ attrs = dict(attrs)
+ if attrs.get('name') == self.name:
+ self.result = attrs.get('content')
+
+ def get_result(self):
+ return self.result
+
+def get_meta_content(name, html):
+ """
+ Return the content attribute from the meta tag with the given name attribute.
+ """
+ parser = MetaParser(name)
+ try:
+ parser.loads(html)
+ except compat_html_parser.HTMLParseError:
+ pass
+ return parser.get_result()
+
def clean_html(html):
"""Clean an HTML snippet into a readable string"""
# Newline vs
html = html.replace('\n', ' ')
- html = re.sub('\s*<\s*br\s*/?\s*>\s*', '\n', html)
+ html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
+ html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
# Strip html tags
html = re.sub('<.*?>', '', html)
# Replace html entities
html = unescapeHTML(html)
- return html
+ return html.strip()
def sanitize_open(filename, open_mode):
@@ -321,16 +419,24 @@ 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:
- # 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):
@@ -407,7 +513,69 @@ 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
+
+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, 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:
+ return None
+ return u''.join(traceback.format_tb(self.traceback))
+
+
+class RegexNotFoundError(ExtractorError):
+ """Error when a regex didn't match"""
+ pass
+
class DownloadError(Exception):
"""Download Error exception.
@@ -416,7 +584,10 @@ 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):
@@ -434,7 +605,8 @@ 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. """
@@ -499,22 +671,42 @@ 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):
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':
@@ -525,3 +717,273 @@ 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]*$', '', date_str)
+ format_expressions = [
+ '%d %B %Y',
+ '%B %d %Y',
+ '%b %d %Y',
+ '%Y-%m-%d',
+ '%d/%m/%Y',
+ '%Y/%m/%d %H:%M:%S',
+ '%d.%m.%Y %H:%M',
+ '%Y-%m-%dT%H:%M:%SZ',
+ '%Y-%m-%dT%H:%M:%S.%fZ',
+ '%Y-%m-%dT%H:%M:%S.%f0Z',
+ '%Y-%m-%dT%H:%M:%S',
+ ]
+ for expression in format_expressions:
+ try:
+ upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
+ except:
+ pass
+ return upload_date
+
+def determine_ext(url, default_ext=u'unknown_video'):
+ guess = url.partition(u'?')[0].rpartition(u'.')[2]
+ if re.match(r'^[A-Za-z0-9]+$', 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