aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/crunchyroll.py97
-rw-r--r--youtube_dl/extractor/hornbunny.py44
-rw-r--r--youtube_dl/extractor/youtube.py6
4 files changed, 146 insertions, 2 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 459899861..f8cbfddc2 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -135,6 +135,7 @@ from .grooveshark import GroovesharkIE
from .hark import HarkIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
+from .hornbunny import HornBunnyIE
from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .howstuffworks import HowStuffWorksIE
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index 026a9177e..4903764f7 100644
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -5,6 +5,7 @@ import re
import json
import base64
import zlib
+import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
@@ -17,6 +18,7 @@ from ..utils import (
intlist_to_bytes,
unified_strdate,
clean_html,
+ urlencode_postdata,
)
from ..aes import (
aes_cbc_decrypt,
@@ -51,6 +53,26 @@ 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)
@@ -97,6 +119,75 @@ class CrunchyrollIE(InfoExtractor):
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')
@@ -158,6 +249,7 @@ class CrunchyrollIE(InfoExtractor):
})
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)
@@ -174,7 +266,10 @@ class CrunchyrollIE(InfoExtractor):
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,
diff --git a/youtube_dl/extractor/hornbunny.py b/youtube_dl/extractor/hornbunny.py
new file mode 100644
index 000000000..a42fba0cb
--- /dev/null
+++ b/youtube_dl/extractor/hornbunny.py
@@ -0,0 +1,44 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+class HornBunnyIE(InfoExtractor):
+ _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
+ _TEST = {
+ 'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
+ 'md5': '95e40865aedd08eff60272b704852ad7',
+ 'info_dict': {
+ 'id': '5227',
+ 'ext': 'flv',
+ 'title': 'panty slut jerk off instruction',
+ 'duration': 550
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+ title = self._html_search_regex(r'class="title">(.*?)</h2>', webpage, 'title')
+ redirect_url = self._html_search_regex(r'pg&settings=(.*?)\|0"\);', webpage, 'title')
+ webpage2 = self._download_webpage(redirect_url, video_id)
+ video_url = self._html_search_regex(r'flvMask:(.*?);', webpage2, 'video_url')
+
+ mobj = re.search(r'<strong>Runtime:</strong> (?P<minutes>\d+):(?P<seconds>\d+)</div>', webpage)
+ duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+ view_count = self._html_search_regex(r'<strong>Views:</strong> (\d+)</div>', webpage, 'view count', fatal=False)
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'ext': 'flv',
+ 'duration': duration,
+ 'view_count': int_or_none(view_count),
+ }
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index a8d7bc343..78f3b7e7b 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -316,6 +316,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
u"upload_date": u"20121002",
u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .",
u"categories": [u'Science & Technology'],
+ 'like_count': int,
+ 'dislike_count': int,
}
},
{
@@ -784,7 +786,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
upload_date = unified_strdate(upload_date)
- m_cat_container = get_element_by_id("eow-category", video_webpage)
+ m_cat_container = self._search_regex(
+ r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
+ video_webpage, 'categories', fatal=False)
if m_cat_container:
category = self._html_search_regex(
r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',