diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-09-16 03:32:53 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-09-16 03:32:53 +0200 |
commit | ef66b0c6effb9d8741807abb12b059560c97c8da (patch) | |
tree | 8230663fc475477863b78884078bba918a1edea4 /youtube_dl/utils.py | |
parent | 22b50ecb2f7f9e0469d281a4c401d4a531c1cc5b (diff) | |
parent | 5a6fecc3dee35f95f3590a31e51670819db5a1fe (diff) |
Merge remote-tracking branch 'origin/master'
Diffstat (limited to 'youtube_dl/utils.py')
-rw-r--r-- | youtube_dl/utils.py | 63 |
1 files changed, 54 insertions, 9 deletions
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 201802cee..5558d4737 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -249,7 +249,17 @@ 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 @@ -257,10 +267,9 @@ 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: @@ -269,11 +278,6 @@ 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: @@ -334,6 +338,38 @@ 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""" @@ -664,7 +700,16 @@ def unified_strdate(date_str): 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'] + 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', + ] for expression in format_expressions: try: upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d') |