[washingtonpost] Add extractor (Fixes #2622)

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 8b359cb77f9188baa9c0a1fcea322268992bd90d..29c9b1a4cb6fdef970617fd6b556454cb7eff07d 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+import calendar
 import contextlib
 import ctypes
 import datetime
@@ -501,13 +502,13 @@ 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
 
 
@@ -761,6 +762,31 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     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$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$',
+        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"""
 
@@ -1160,7 +1186,7 @@ def parse_duration(s):
         return None
 
     m = re.match(
-        r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?$', s)
+        r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?(?::[0-9]+)?$', s)
     if not m:
         return None
     res = int(m.group('secs'))
@@ -1302,3 +1328,7 @@ US_RATINGS = {
     'R': 16,
     'NC': 18,
 }
+
+
+def strip_jsonp(code):
+    return re.sub(r'(?s)^[a-zA-Z_]+\s*\(\s*(.*)\);\s*?\s*$', r'\1', code)