From 723e04d0be85fbdbbbda52512f322331d8fda760 Mon Sep 17 00:00:00 2001 From: Adam Date: Fri, 29 Aug 2014 22:32:03 +0100 Subject: [PATCH 1/4] Add login support to Crunchyroll extractor --- youtube_dl/extractor/crunchyroll.py | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 026a9177e..7642b868e 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -17,6 +17,7 @@ intlist_to_bytes, unified_strdate, clean_html, + urlencode_postdata, ) from ..aes import ( aes_cbc_decrypt, @@ -51,6 +52,24 @@ class CrunchyrollIE(InfoExtractor): '1080': ('80', '108'), } + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + self.report_login() + login_url = 'https://www.crunchyroll.com/?a=formhandler' + data = urlencode_postdata({ + 'formname': 'RpcApiUser_Login', + 'name': username, + 'password': password, + }) + login_request = compat_urllib_request.Request(login_url, data) + login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + self._download_webpage(login_request, None, False, 'Wrong login info') + + def _real_initialize(self): + self._login() + def _decrypt_subtitles(self, data, iv, id): data = bytes_to_intlist(data) iv = bytes_to_intlist(iv) From 78272a076e96bea48525e415e42fa4d95d4d66fa Mon Sep 17 00:00:00 2001 From: Adam Date: Sat, 30 Aug 2014 12:48:56 +0100 Subject: [PATCH 2/4] Add SSA (.ass) subtitle output for Crunchyroll --- youtube_dl/extractor/crunchyroll.py | 78 ++++++++++++++++++++++++++++- 1 file changed, 77 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 7642b868e..4903764f7 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -5,6 +5,7 @@ import json import base64 import zlib +import xml.etree.ElementTree from hashlib import sha1 from math import pow, sqrt, floor @@ -67,9 +68,11 @@ def _login(self): login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') self._download_webpage(login_request, None, False, 'Wrong login info') + def _real_initialize(self): self._login() + def _decrypt_subtitles(self, data, iv, id): data = bytes_to_intlist(data) iv = bytes_to_intlist(iv) @@ -116,6 +119,75 @@ def _convert_subtitles_to_srt(self, subtitles): output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text) return output + def _convert_subtitles_to_ass(self, subtitles): + output = '' + + def ass_bool(strvalue): + assvalue = '0' + if strvalue == '1': + assvalue = '-1' + return assvalue + + sub_root = xml.etree.ElementTree.fromstring(subtitles) + if not sub_root: + return output + + output = '[Script Info]\n' + output += 'Title: %s\n' % sub_root.attrib["title"] + output += 'ScriptType: v4.00+\n' + output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"] + output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"] + output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"] + output += """ScaledBorderAndShadow: yes + +[V4+ Styles] +Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding +""" + for style in sub_root.findall('./styles/style'): + output += 'Style: ' + style.attrib["name"] + output += ',' + style.attrib["font_name"] + output += ',' + style.attrib["font_size"] + output += ',' + style.attrib["primary_colour"] + output += ',' + style.attrib["secondary_colour"] + output += ',' + style.attrib["outline_colour"] + output += ',' + style.attrib["back_colour"] + output += ',' + ass_bool(style.attrib["bold"]) + output += ',' + ass_bool(style.attrib["italic"]) + output += ',' + ass_bool(style.attrib["underline"]) + output += ',' + ass_bool(style.attrib["strikeout"]) + output += ',' + style.attrib["scale_x"] + output += ',' + style.attrib["scale_y"] + output += ',' + style.attrib["spacing"] + output += ',' + style.attrib["angle"] + output += ',' + style.attrib["border_style"] + output += ',' + style.attrib["outline"] + output += ',' + style.attrib["shadow"] + output += ',' + style.attrib["alignment"] + output += ',' + style.attrib["margin_l"] + output += ',' + style.attrib["margin_r"] + output += ',' + style.attrib["margin_v"] + output += ',' + style.attrib["encoding"] + output += '\n' + + output += """ +[Events] +Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text +""" + for event in sub_root.findall('./events/event'): + output += 'Dialogue: 0' + output += ',' + event.attrib["start"] + output += ',' + event.attrib["end"] + output += ',' + event.attrib["style"] + output += ',' + event.attrib["name"] + output += ',' + event.attrib["margin_l"] + output += ',' + event.attrib["margin_r"] + output += ',' + event.attrib["margin_v"] + output += ',' + event.attrib["effect"] + output += ',' + event.attrib["text"] + output += '\n' + + return output + def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') @@ -177,6 +249,7 @@ def _real_extract(self,url): }) subtitles = {} + sub_format = self._downloader.params.get('subtitlesformat', 'srt') for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\ video_id, note='Downloading subtitles for '+sub_name) @@ -193,7 +266,10 @@ def _real_extract(self,url): lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue - subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) + if sub_format == 'ass': + subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle) + else: + subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) return { 'id': video_id, From 7eb21356f98315b15fc05d9e616951511253076f Mon Sep 17 00:00:00 2001 From: peugeot Date: Sun, 31 Aug 2014 12:48:34 +0200 Subject: [PATCH 3/4] Add support for sunporno.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/sunporno.py | 57 ++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 youtube_dl/extractor/sunporno.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1479d998a..72b01505d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -322,6 +322,7 @@ from .steam import SteamIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE +from .sunporno import SunPornoIE from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py new file mode 100644 index 000000000..2a193dee3 --- /dev/null +++ b/youtube_dl/extractor/sunporno.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, +) + + +class SunPornoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P\d+)' + _TEST = { + 'url': 'http://www.sunporno.com/videos/807778/', + 'md5': '6457d3c165fd6de062b99ef6c2ff4c86', + 'info_dict': { + 'id': '807778', + 'ext': 'flv', + 'title': 'md5:0a400058e8105d39e35c35e7c5184164', + 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', + 'duration': 302, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'videoSource\s*=\s*\'([^<]*)', webpage, 'title') + + description = self._html_search_regex( + r'Duration: (\d+:\d+)', webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._html_search_regex( + r'(\d+)', webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + } From ae7246e7d57654381fb629be46662f8e4ded615f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 1 Sep 2014 01:08:19 +0700 Subject: [PATCH 4/4] [sunporno] Extract all formats and metadata --- youtube_dl/extractor/sunporno.py | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py index 2a193dee3..c7a46eb71 100644 --- a/youtube_dl/extractor/sunporno.py +++ b/youtube_dl/extractor/sunporno.py @@ -6,6 +6,8 @@ from ..utils import ( parse_duration, int_or_none, + qualities, + determine_ext, ) @@ -19,6 +21,7 @@ class SunPornoIE(InfoExtractor): 'ext': 'flv', 'title': 'md5:0a400058e8105d39e35c35e7c5184164', 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', + 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 302, } } @@ -29,29 +32,37 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'videoSource\s*=\s*\'([^<]*)', webpage, 'title') - - description = self._html_search_regex( - r'([^<]+)', webpage, 'title') + description = self._html_search_meta('description', webpage, 'description') thumbnail = self._html_search_regex( - r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False) + r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._search_regex( r'Duration: (\d+:\d+)', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( r'(\d+)', webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._html_search_regex( + r'(\d+) Comments?', webpage, 'comment count', fatal=False)) + + formats = [] + quality = qualities(['mp4', 'flv']) + for video_url in re.findall(r'