X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=6c5b5df4cc138254e0d7680ef7477fc0f11e6ed0;hb=c43e57242e10eae327d4348390cfb9e574fad5dd;hp=8f856ee8c073dd9095f2b62b1567eabdb321c117;hpb=258d5850c91e0d37a36c6bae0a25314f8149b05a;p=youtube-dl

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 8f856ee8c..6c5b5df4c 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -12,6 +12,7 @@ import traceback
 import zlib
 import email.utils
 import json
+import datetime
 
 try:
     import urllib.request as compat_urllib_request
@@ -280,6 +281,12 @@ 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("</scr'+'ipt>")
+        if self.rawdata[i:].startswith("</scr'+'ipt>")
+        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"""
@@ -305,7 +312,7 @@ 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):
@@ -323,7 +330,7 @@ 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:
@@ -409,8 +416,19 @@ 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 Besides, NT 4 is obsolete.)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."""
@@ -418,6 +436,7 @@ class ExtractorError(Exception):
         """ 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:
@@ -432,7 +451,10 @@ 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):
@@ -450,7 +472,8 @@ 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. """
@@ -515,14 +538,19 @@ 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):
@@ -541,3 +569,70 @@ 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']
+    for expression in format_expressions:
+        try:
+            upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
+        except:
+            pass
+    return upload_date
+
+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<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
+    if match is not None:
+        sign = match.group('sign')
+        time = int(match.group('time'))
+        if sign == '-':
+            time = -time
+        unit = match.group('unit')
+        #A bad aproximation?
+        if unit == 'month':
+            unit = 'day'
+            time *= 30
+        elif unit == 'year':
+            unit = 'day'
+            time *= 365
+        unit += 's'
+        delta = datetime.timedelta(**{unit: time})
+        return today + delta
+    return datetime.datetime.strptime(date_str, "%Y%m%d").date()
+    
+class DateRange(object):
+    """Represents a time interval between two dates"""
+    def __init__(self, start=None, end=None):
+        """start and end must be strings in the format accepted by date"""
+        if start is not None:
+            self.start = date_from_str(start)
+        else:
+            self.start = datetime.datetime.min.date()
+        if end is not None:
+            self.end = date_from_str(end)
+        else:
+            self.end = datetime.datetime.max.date()
+        if self.start > self.end:
+            raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
+    @classmethod
+    def day(cls, day):
+        """Returns a range that only contains the given day"""
+        return cls(day,day)
+    def __contains__(self, date):
+        """Check if the date is in the range"""
+        if not isinstance(date, datetime.date):
+            date = date_from_str(date)
+        return self.start <= date <= self.end
+    def __str__(self):
+        return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())