X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Futils.py;h=463804e183117b23efd8f0e4b0ad9b132e519ddb;hb=3bb6165927c277c3af73d5ef1ffb6ce9ea663d10;hp=4dcf18991487d7a180a5d4b903bad4b38b3165db;hpb=796173d08b514182eedc704541eb55d5c9e1dc0d;p=youtube-dl

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 4dcf18991..463804e18 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -3,6 +3,7 @@
 
 import gzip
 import io
+import json
 import locale
 import os
 import re
@@ -51,6 +52,12 @@ try:
 except ImportError: # Python 2
     import httplib as compat_http_client
 
+try:
+    from subprocess import DEVNULL
+    compat_subprocess_get_DEVNULL = lambda: DEVNULL
+except ImportError:
+    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+
 try:
     from urllib.parse import parse_qs as compat_parse_qs
 except ImportError: # Python 2
@@ -169,6 +176,18 @@ else:
         assert type(s) == type(u'')
         print(s)
 
+# In Python 2.x, json.dump expects a bytestream.
+# In Python 3.x, it writes to a character stream
+if sys.version_info < (3,0):
+    def write_json_file(obj, fn):
+        with open(fn, 'wb') as f:
+            json.dump(obj, f)
+else:
+    def write_json_file(obj, fn):
+        with open(fn, 'w', encoding='utf-8') as f:
+            json.dump(obj, f)
+
+
 def htmlentity_transform(matchobj):
     """Transforms an HTML entity to a character.
 
@@ -195,10 +214,11 @@ 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 IDParser(compat_html_parser.HTMLParser):
-    """Modified HTMLParser that isolates a tag with the specified id"""
-    def __init__(self, id):
-        self.id = id
+class AttrParser(compat_html_parser.HTMLParser):
+    """Modified HTMLParser that isolates a tag with the specified attribute"""
+    def __init__(self, attribute, value):
+        self.attribute = attribute
+        self.value = value
         self.result = None
         self.started = False
         self.depth = {}
@@ -223,7 +243,7 @@ class IDParser(compat_html_parser.HTMLParser):
         attrs = dict(attrs)
         if self.started:
             self.find_startpos(None)
-        if 'id' in attrs and attrs['id'] == self.id:
+        if self.attribute in attrs and attrs[self.attribute] == self.value:
             self.result = [tag]
             self.started = True
             self.watch_startpos = True
@@ -261,8 +281,12 @@ class IDParser(compat_html_parser.HTMLParser):
         return '\n'.join(lines).strip()
 
 def get_element_by_id(id, html):
-    """Return the content of the tag with the specified id in the passed HTML document"""
-    parser = IDParser(id)
+    """Return the content of the tag with the specified ID in the passed HTML document"""
+    return get_element_by_attribute("id", id, html)
+
+def get_element_by_attribute(attribute, value, html):
+    """Return the content of the tag with the specified attribute in the passed HTML document"""
+    parser = AttrParser(attribute, value)
     try:
         parser.loads(html)
     except compat_html_parser.HTMLParseError:
@@ -274,7 +298,8 @@ def clean_html(html):
     """Clean an HTML snippet into a readable string"""
     # Newline vs <br />
     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
@@ -441,14 +466,6 @@ class ContentTooShortError(Exception):
         self.downloaded = downloaded
         self.expected = expected
 
-
-class Trouble(Exception):
-    """Trouble helper exception
-
-    This is an exception to be handled with
-    FileDownloader.trouble
-    """
-
 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 
@@ -506,3 +523,6 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
             resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
             resp.msg = old_resp.msg
         return resp
+
+    https_request = http_request
+    https_response = http_response