[golem] Simplify (#3828)

This commit is contained in:
Philipp Hagemeister 2014-09-28 10:34:55 +02:00
parent 92f7963f6e
commit b14f3a4c1d
2 changed files with 56 additions and 91 deletions

View File

@ -22,6 +22,7 @@
clean_html, clean_html,
compiled_regex_type, compiled_regex_type,
ExtractorError, ExtractorError,
float_or_none,
int_or_none, int_or_none,
RegexNotFoundError, RegexNotFoundError,
sanitize_filename, sanitize_filename,
@ -720,6 +721,28 @@ def _live_title(self, name):
now_str = now.strftime("%Y-%m-%d %H:%M") now_str = now.strftime("%Y-%m-%d %H:%M")
return name + ' ' + now_str return name + ' ' + now_str
def _int(self, v, name, fatal=False, **kwargs):
res = int_or_none(v, **kwargs)
if 'get_attr' in kwargs:
print(getattr(v, kwargs['get_attr']))
if res is None:
msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
if fatal:
raise ExtractorError(msg)
else:
self._downloader.report_warning(msg)
return res
def _float(self, v, name, fatal=False, **kwargs):
res = float_or_none(v, **kwargs)
if res is None:
msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
if fatal:
raise ExtractorError(msg)
else:
self._downloader.report_warning(msg)
return res
class SearchInfoExtractor(InfoExtractor): class SearchInfoExtractor(InfoExtractor):
""" """

View File

@ -4,7 +4,10 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import compat_urlparse from ..utils import (
compat_urlparse,
determine_ext,
)
class GolemIE(InfoExtractor): class GolemIE(InfoExtractor):
@ -17,115 +20,54 @@ class GolemIE(InfoExtractor):
'format_id': 'high', 'format_id': 'high',
'ext': 'mp4', 'ext': 'mp4',
'title': 'iPhone 6 und 6 Plus - Test', 'title': 'iPhone 6 und 6 Plus - Test',
'duration': 300, 'duration': 300.44,
'filesize': 65309548, 'filesize': 65309548,
} }
} }
_CONFIG = 'https://video.golem.de/xml/{0}.xml'
_PREFIX = 'http://video.golem.de' _PREFIX = 'http://video.golem.de'
def _warn(self, fmt, *args):
self.report_warning(fmt.format(*args), self._id)
def _extract_format(self, elem):
format_id = elem.tag
url = elem.findtext('./url')
if url == '':
self._warn("{0}: url: empty, skipping", format_id)
return None
fmt = {
'format_id': format_id,
'url': compat_urlparse.urljoin(self._PREFIX, url)
}
try:
_, ext = elem.findtext('./filename', '').rsplit('.', 1)
except ValueError:
self._warn('{0}: ext: missing extension', format_id)
else:
fmt['ext'] = ext
filesize = elem.findtext('./filesize')
if filesize is not None:
try:
fmt['filesize'] = int(filesize)
except ValueError as e:
self._warn('{0}: filesize: {1}', format_id, e)
width = elem.get('width')
if width is not None:
try:
fmt['width'] = int(width)
except ValueError as e:
self._warn('{0}: width: {1}', format_id, e)
height = elem.get('height')
if height is not None:
try:
fmt['height'] = int(height)
except ValueError as e:
self._warn('{0}: height: {1}', format_id, e)
return fmt
def _extract_thumbnail(self, elem):
url = elem.findtext('./url')
if url == '':
return None
thumb = {
'url': compat_urlparse.urljoin(self._PREFIX, url)
}
width = elem.get('width')
if width is not None:
try:
thumb['width'] = int(width)
except ValueError as e:
self._warn('thumbnail: width: {0}', e)
height = elem.get('height')
if height is not None:
try:
thumb['height'] = int(height)
except ValueError as e:
self._warn('thumbnail: height: {0}', e)
return thumb
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
self._id = mobj.group('id')
config = self._download_xml(self._CONFIG.format(self._id), self._id) config = self._download_xml(
'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)
info = { info = {
'id': self._id, 'id': video_id,
'title': config.findtext('./title', 'golem') 'title': config.findtext('./title', 'golem'),
'duration': self._float(config.findtext('./playtime'), 'duration'),
} }
formats = [] formats = []
for e in config.findall('./*[url]'): for e in config.findall('./*[url]'):
fmt = self._extract_format(e) url = e.findtext('./url')
if fmt is not None: if not url:
formats.append(fmt) self._downloader.report_warning(
"{0}: url: empty, skipping".format(e.tag))
continue
formats.append({
'format_id': e.tag,
'url': compat_urlparse.urljoin(self._PREFIX, url),
'height': self._int(e.get('height'), 'height'),
'width': self._int(e.get('width'), 'width'),
'filesize': self._int(e.findtext('filesize'), 'filesize'),
'ext': determine_ext(e.findtext('./filename')),
})
self._sort_formats(formats) self._sort_formats(formats)
info['formats'] = formats info['formats'] = formats
thumbnails = [] thumbnails = []
for e in config.findall('.//teaser[url]'): for e in config.findall('.//teaser[url]'):
thumb = self._extract_thumbnail(e) url = e.findtext('./url')
if thumb is not None: if not url:
thumbnails.append(thumb) continue
thumbnails.append({
'url': compat_urlparse.urljoin(self._PREFIX, url),
'width': self._int(e.get('width'), 'thumbnail width'),
'height': self._int(e.get('height'), 'thumbnail height'),
})
info['thumbnails'] = thumbnails info['thumbnails'] = thumbnails
playtime = config.findtext('./playtime')
if playtime is not None:
try:
info['duration'] = round(float(playtime))
except ValueError as e:
self._warn('duration: {0}', e)
return info return info