github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[crunchyroll] Tidy and modernize

Browse source
This commit is contained in:
Sergey M 2014-02-25 20:26:11 +07:00
parent ea5a0be811
commit 344400951c
1 changed files with 15 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/extractor/crunchyroll.py
View file

@ -1,7 +1,10 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re, base64, zlib import re
import base64
import zlib
from hashlib import sha1 from hashlib import sha1
from math import pow, sqrt, floor from math import pow, sqrt, floor
from .common import InfoExtractor from .common import InfoExtractor
@ -19,13 +22,15 @@
inc, inc,
) )
class CrunchyrollIE(InfoExtractor): class CrunchyrollIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)' _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_TESTS = [{ _TEST = {
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'file': '645513.flv',
#'md5': 'b1639fd6ddfaa43788c85f6d1dddd412', #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
'info_dict': { 'info_dict': {
'id': '645513',
'ext': 'flv',
'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!', 'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
'description': 'md5:2d17137920c64f2f49981a7797d275ef', 'description': 'md5:2d17137920c64f2f49981a7797d275ef',
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg', 'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
@ -36,7 +41,7 @@ class CrunchyrollIE(InfoExtractor):
# rtmp # rtmp
'skip_download': True, 'skip_download': True,
}, },
}] }
_FORMAT_IDS = { _FORMAT_IDS = {
'360': ('60', '106'), '360': ('60', '106'),
@ -68,7 +73,7 @@ def obfuscate_key(key):
shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest()) shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
# Extend 160 Bit hash to 256 Bit # Extend 160 Bit hash to 256 Bit
return shaHash + [0] * 12 return shaHash + [0] * 12
key = obfuscate_key(id) key = obfuscate_key(id)
class Counter: class Counter:
__value = iv __value = iv
@ -80,7 +85,7 @@ def next_value(self):
return zlib.decompress(decrypted_data) return zlib.decompress(decrypted_data)
def _convert_subtitles_to_srt(self, subtitles): def _convert_subtitles_to_srt(self, subtitles):
i=1 i = 1
output = '' output = ''
for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles): for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
start = start.replace('.', ',') start = start.replace('.', ',')
@ -90,7 +95,7 @@ def _convert_subtitles_to_srt(self, subtitles):
if not text: if not text:
continue continue
output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text) output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
i+=1 i += 1
return output return output
def _real_extract(self,url): def _real_extract(self,url):
@ -123,7 +128,7 @@ def _real_extract(self,url):
playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url}) playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info') playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id') stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False) video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
@ -175,4 +180,4 @@ def _real_extract(self,url):
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'subtitles': subtitles, 'subtitles': subtitles,
'formats': formats, 'formats': formats,
} }