Merge pull request #3 from unit193/master

[youtubedl] / youtube_dl / extractor / openload.py

diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index b50d6c77b4e2fad46bf3d5ada798f1cb8f255a29..0c20d0177e0f2abbc5c0503babf51ba66715f374 100644 (file)
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -3,21 +3,17 @@ from __future__ import unicode_literals
 
 import json
 import os
 
 import json
 import os

-import re

 import subprocess
 import tempfile
 
 import subprocess
 import tempfile
 

-from .common import InfoExtractor

 from ..compat import (
     compat_urlparse,
     compat_kwargs,
 )
 from ..utils import (
     check_executable,
 from ..compat import (
     compat_urlparse,
     compat_kwargs,
 )
 from ..utils import (
     check_executable,

-    determine_ext,

     encodeArgument,
     ExtractorError,
     encodeArgument,
     ExtractorError,

-    get_element_by_id,

     get_exe_version,
     is_outdated_version,
     std_headers,
     get_exe_version,
     is_outdated_version,
     std_headers,


@@ -42,9 +38,9 @@ def cookie_to_dict(cookie):
     if cookie.discard is not None:
         cookie_dict['discard'] = cookie.discard
     try:
     if cookie.discard is not None:
         cookie_dict['discard'] = cookie.discard
     try:

-        if (cookie.has_nonstandard_attr('httpOnly') or
-                cookie.has_nonstandard_attr('httponly') or
-                cookie.has_nonstandard_attr('HttpOnly')):
+        if (cookie.has_nonstandard_attr('httpOnly')
+                or cookie.has_nonstandard_attr('httponly')
+                or cookie.has_nonstandard_attr('HttpOnly')):

             cookie_dict['httponly'] = True
     except TypeError:
         pass
             cookie_dict['httponly'] = True
     except TypeError:
         pass


@@ -112,6 +108,8 @@ class PhantomJSwrapper(object):
         return get_exe_version('phantomjs', version_re=r'([0-9.]+)')
 
     def __init__(self, extractor, required_version=None, timeout=10000):
         return get_exe_version('phantomjs', version_re=r'([0-9.]+)')
 
     def __init__(self, extractor, required_version=None, timeout=10000):

+        self._TMP_FILES = {}
+

         self.exe = check_executable('phantomjs', ['-v'])
         if not self.exe:
             raise ExtractorError('PhantomJS executable not found in PATH, '
         self.exe = check_executable('phantomjs', ['-v'])
         if not self.exe:
             raise ExtractorError('PhantomJS executable not found in PATH, '


@@ -130,7 +128,6 @@ class PhantomJSwrapper(object):
         self.options = {
             'timeout': timeout,
         }
         self.options = {
             'timeout': timeout,
         }

-        self._TMP_FILES = {}

         for name in self._TMP_FILE_NAMES:
             tmp = tempfile.NamedTemporaryFile(delete=False)
             tmp.close()
         for name in self._TMP_FILE_NAMES:
             tmp = tempfile.NamedTemporaryFile(delete=False)
             tmp.close()


@@ -140,7 +137,7 @@ class PhantomJSwrapper(object):
         for name in self._TMP_FILE_NAMES:
             try:
                 os.remove(self._TMP_FILES[name].name)
         for name in self._TMP_FILE_NAMES:
             try:
                 os.remove(self._TMP_FILES[name].name)

-            except:
+            except (IOError, OSError, KeyError):

                 pass
 
     def _save_cookies(self, url):
                 pass
 
     def _save_cookies(self, url):


@@ -239,99 +236,3 @@ class PhantomJSwrapper(object):
         self._load_cookies()
 
         return (html, encodeArgument(out))
         self._load_cookies()
 
         return (html, encodeArgument(out))

-
-
-class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
-
-    _TESTS = [{
-        'url': 'https://openload.co/f/kUEfGclsU9o',
-        'md5': 'bf1c059b004ebc7a256f89408e65c36e',
-        'info_dict': {
-            'id': 'kUEfGclsU9o',
-            'ext': 'mp4',
-            'title': 'skyrim_no-audio_1080.mp4',
-            'thumbnail': r're:^https?://.*\.jpg$',
-        },
-    }, {
-        'url': 'https://openload.co/embed/rjC09fkPLYs',
-        'info_dict': {
-            'id': 'rjC09fkPLYs',
-            'ext': 'mp4',
-            'title': 'movie.mp4',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'subtitles': {
-                'en': [{
-                    'ext': 'vtt',
-                }],
-            },
-        },
-        'params': {
-            'skip_download': True,  # test subtitles only
-        },
-    }, {
-        'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
-        'only_matching': True,
-    }, {
-        'url': 'https://openload.io/f/ZAn6oz-VZGE/',
-        'only_matching': True,
-    }, {
-        'url': 'https://openload.co/f/_-ztPaZtMhM/',
-        'only_matching': True,
-    }, {
-        # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
-        # for title and ext
-        'url': 'https://openload.co/embed/Sxz5sADo82g/',
-        'only_matching': True,
-    }, {
-        'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
-        'only_matching': True,
-    }]
-
-    _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
-
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
-            webpage)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        url = 'https://openload.co/embed/%s/' % video_id
-        headers = {
-            'User-Agent': self._USER_AGENT,
-        }
-
-        webpage = self._download_webpage(url, video_id, headers=headers)
-
-        if 'File not found' in webpage or 'deleted by the owner' in webpage:
-            raise ExtractorError('File not found', expected=True, video_id=video_id)
-
-        phantom = PhantomJSwrapper(self, required_version='2.0')
-        webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers)
-
-        decoded_id = get_element_by_id('streamurl', webpage)
-
-        video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id
-
-        title = self._og_search_title(webpage, default=None) or self._search_regex(
-            r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
-            'title', default=None) or self._html_search_meta(
-            'description', webpage, 'title', fatal=True)
-
-        entries = self._parse_html5_media_entries(url, webpage, video_id)
-        entry = entries[0] if entries else {}
-        subtitles = entry.get('subtitles')
-
-        info_dict = {
-            'id': video_id,
-            'title': title,
-            'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
-            'url': video_url,
-            # Seems all videos have extensions in their titles
-            'ext': determine_ext(title, 'mp4'),
-            'subtitles': subtitles,
-            'http_headers': headers,
-        }
-        return info_dict