dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[playvid] Simplify (#2539)

This commit is contained in:
Philipp Hagemeister 2014-03-10 20:55:47 +01:00
parent 777ac90791
commit db95dc13a1
2 changed files with 34 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/YoutubeDL.py
View File

@ -701,8 +701,11 @@ class YoutubeDL(object):
else: else:
formats = info_dict['formats'] formats = info_dict['formats']
if not formats:
raise ExtractorError('No video formats found!')
# We check that all the formats have the format and format_id fields # We check that all the formats have the format and format_id fields
for (i, format) in enumerate(formats): for i, format in enumerate(formats):
if format.get('format_id') is None: if format.get('format_id') is None:
format['format_id'] = compat_str(i) format['format_id'] = compat_str(i)
if format.get('format') is None: if format.get('format') is None:

65
youtube_dl/extractor/playvid.py
View File

@ -5,17 +5,17 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse, compat_urllib_parse,
determine_ext,
) )
class PlayvidIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(#|$)' class PlayvidIE(InfoExtractor):
_VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
_TEST = { _TEST = {
'url': 'http://www.playvid.com/watch/agbDDi7WZTV', 'url': 'http://www.playvid.com/watch/agbDDi7WZTV',
'file': 'agbDDi7WZTV.mp4',
'md5': '44930f8afa616efdf9482daf4fe53e1e', 'md5': '44930f8afa616efdf9482daf4fe53e1e',
'info_dict': { 'info_dict': {
'id': 'agbDDi7WZTV',
'ext': 'mp4',
'title': 'Michelle Lewin in Miami Beach', 'title': 'Michelle Lewin in Miami Beach',
'duration': 240, 'duration': 240,
'age_limit': 18, 'age_limit': 18,
@ -28,46 +28,41 @@ class PlayvidIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
video_title = None video_title = None
duration = None duration = None
video_thumbnail = None video_thumbnail = None
formats = [] formats = []
# most of the information is stored in the flashvars # most of the information is stored in the flashvars
flashvars_match = re.search(r'flashvars="(.+?)"',webpage) flashvars = self._html_search_regex(
r'flashvars="(.+?)"', webpage, 'flashvars')
if flashvars_match: infos = compat_urllib_parse.unquote(flashvars).split(r'&')
infos = compat_urllib_parse.unquote(flashvars_match.group(1)).split(r'&amp;') for info in infos:
for info in infos: videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$',info) if videovars_match:
if videovars_match: key = videovars_match.group(1)
key = videovars_match.group(1) val = videovars_match.group(2)
val = videovars_match.group(2)
if key == 'title': if key == 'title':
video_title = val.replace('+',' ') video_title = compat_urllib_parse.unquote_plus(val)
if key == 'duration': if key == 'duration':
try: try:
duration = val duration = int(val)
except ValueError: except ValueError:
duration = None pass
if key == 'big_thumb': if key == 'big_thumb':
video_thumbnail = val video_thumbnail = val
videourl_match = re.match(r'^video_urls\]\[(?P<resolution>\d+)p',key) videourl_match = re.match(
if videourl_match: r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
resolution = int(videourl_match.group('resolution')) if videourl_match:
formats.append({ height = int(videourl_match.group('resolution'))
'resolution': resolution, # 360, 480, ... formats.append({
'ext': determine_ext(val), 'height': height,
'url': val 'url': val,
}) })
self._sort_formats(formats)
# fatal error, if no download url is found
if len(formats) == 0:
raise ExtractorError,'no video url found'
# Extract title - should be in the flashvars; if not, look elsewhere # Extract title - should be in the flashvars; if not, look elsewhere
if video_title is None: if video_title is None: