-from ..utils import (
- ExtractorError,
- compat_html_parser,
- #compat_urllib_request,
- #compat_urllib_parse,
-)
-
-
-class PatreonHTMLParser(compat_html_parser.HTMLParser):
- _PREFIX = 'http://www.patreon.com'
- _ATTACH_TAGS = 5 * ['div']
- _ATTACH_CLASSES = [
- 'fancyboxhidden', 'box photo', 'boxwrapper',
- 'hiddendisplay shareinfo', 'attach'
- ]
- _INFO_TAGS = 4 * ['div']
- _INFO_CLASSES = [
- 'fancyboxhidden', 'box photo', 'boxwrapper',
- 'hiddendisplay shareinfo'
- ]
-
- def _match(self, attrs_classes, desired):
- if attrs_classes == desired:
- return True
- elif len(attrs_classes) == len(desired):
- return all(
- x.startswith(y)
- for x, y in zip(attrs_classes, desired)
- )
- return False
-
- def get_creation_info(self, html_data):
- self.tag_stack = []
- self.attrs_stack = []
- self.creation_info = {}
- self.feed(html_data)
-
- def handle_starttag(self, tag, attrs):
- self.tag_stack.append(tag.lower())
- self.attrs_stack.append(dict(attrs))
-
- def handle_endtag(self, tag):
- self.tag_stack.pop()
- self.attrs_stack.pop()
-
- def handle_data(self, data):
- # Check first if this is a creation attachment
- if self.tag_stack[-6:-1] == self._ATTACH_TAGS:
- attrs_classes = [
- x.get('class', '').lower() for x in self.attrs_stack[-6:-1]
- ]
- if self._match(attrs_classes, self._ATTACH_CLASSES):
- if self.tag_stack[-1] == 'a':
- url = self._PREFIX + self.attrs_stack[-1].get('href')
- self.creation_info['url'] = url
- if '.' in data:
- self.creation_info['ext'] = data.rsplit('.')[-1]
- # Next, check if this is within the div containing the creation info
- if self.tag_stack[-5:-1] == self._INFO_TAGS:
- attrs_classes = [
- x.get('class', '').lower() for x in self.attrs_stack[-5:-1]
- ]
- if self._match(attrs_classes, self._INFO_CLASSES):
- if self.attrs_stack[-1].get('class') == 'utitle':
- self.creation_info['title'] = data.strip()