Merge remote-tracking branch 'sahutd/master'

[youtube-dl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 536504e7e04f7e2925539750618980804ec7a7cd..8fa4cb67f3c0fd8344ad33e1bc3098d2653cc085 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -6,6 +6,7 @@ import datetime
 import email.utils
 import errno
 import gzip
+import itertools
 import io
 import json
 import locale
@@ -224,7 +225,7 @@ 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)
+        assert re.match(r'^[a-zA-Z0-9@\s:._]*$', val)
         expr = xpath + u"[@%s='%s']" % (key, val)
         return node.find(expr)
 else:
@@ -764,6 +765,7 @@ def unified_strdate(date_str):
         '%Y-%m-%d',
         '%d/%m/%Y',
         '%Y/%m/%d %H:%M:%S',
+        '%Y-%m-%d %H:%M:%S',
         '%d.%m.%Y %H:%M',
         '%Y-%m-%dT%H:%M:%SZ',
         '%Y-%m-%dT%H:%M:%S.%fZ',
@@ -817,6 +819,15 @@ def date_from_str(date_str):
         return today + delta
     return datetime.datetime.strptime(date_str, "%Y%m%d").date()
     
+def hyphenate_date(date_str):
+    """
+    Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
+    match = re.match(r'^(\d\d\d\d)(\d\d)(\d\d)$', date_str)
+    if match is not None:
+        return '-'.join(match.groups())
+    else:
+        return date_str
+
 class DateRange(object):
     """Represents a time interval between two dates"""
     def __init__(self, start=None, end=None):
@@ -1026,9 +1037,9 @@ def smuggle_url(url, data):
     return url + u'#' + sdata
 
 
-def unsmuggle_url(smug_url):
+def unsmuggle_url(smug_url, default=None):
     if not '#__youtubedl_smuggle' in smug_url:
-        return smug_url, None
+        return smug_url, default
     url, _, sdata = smug_url.rpartition(u'#')
     jsond = compat_parse_qs(sdata)[u'__youtubedl_smuggle'][0]
     data = json.loads(jsond)
@@ -1082,9 +1093,12 @@ def month_by_name(name):
         return None
 
 
-def fix_xml_all_ampersand(xml_str):
+def fix_xml_ampersands(xml_str):
     """Replace all the '&' by '&' in XML"""
-    return xml_str.replace(u'&', u'&')
+    return re.sub(
+        r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
+        u'&',
+        xml_str)
 
 
 def setproctitle(title):
@@ -1118,8 +1132,8 @@ class HEADRequest(compat_urllib_request.Request):
         return "HEAD"
 
 
-def int_or_none(v):
-    return v if v is None else int(v)
+def int_or_none(v, scale=1):
+    return v if v is None else (int(v) // scale)
 
 
 def parse_duration(s):
@@ -1141,3 +1155,60 @@ def parse_duration(s):
 def prepend_extension(filename, ext):
     name, real_ext = os.path.splitext(filename) 
     return u'{0}.{1}{2}'.format(name, ext, real_ext)
+
+
+def check_executable(exe, args=[]):
+    """ Checks if the given binary is installed somewhere in PATH, and returns its name.
+    args can be a list of arguments for a short output (like -version) """
+    try:
+        subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
+    except OSError:
+        return False
+    return exe
+
+
+class PagedList(object):
+    def __init__(self, pagefunc, pagesize):
+        self._pagefunc = pagefunc
+        self._pagesize = pagesize
+
+    def __len__(self):
+        # This is only useful for tests
+        return len(self.getslice())
+
+    def getslice(self, start=0, end=None):
+        res = []
+        for pagenum in itertools.count(start // self._pagesize):
+            firstid = pagenum * self._pagesize
+            nextfirstid = pagenum * self._pagesize + self._pagesize
+            if start >= nextfirstid:
+                continue
+
+            page_results = list(self._pagefunc(pagenum))
+
+            startv = (
+                start % self._pagesize
+                if firstid <= start < nextfirstid
+                else 0)
+
+            endv = (
+                ((end - 1) % self._pagesize) + 1
+                if (end is not None and firstid <= end <= nextfirstid)
+                else None)
+
+            if startv != 0 or endv is not None:
+                page_results = page_results[startv:endv]
+            res.extend(page_results)
+
+            # A little optimization - if current page is not "full", ie. does
+            # not contain page_size videos then we can assume that this page
+            # is the last one - there are no more ids on further pages -
+            # i.e. no need to query again.
+            if len(page_results) + startv < self._pagesize:
+                break
+
+            # If we got the whole page, but the next page is not interesting,
+            # break out early as well
+            if end == nextfirstid:
+                break
+        return res