summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorNaglis Jonaitis <[email protected]>2014-08-29 00:20:10 +0300
committerNaglis Jonaitis <[email protected]>2014-08-29 00:20:10 +0300
commit8e72edfb19b5f6f87210f62f02fe876789641dbe (patch)
treeef27101535f5cd5ba861f7f61f4a5a49fbb23479
parent863f08a92e3dd9202bae874c656d929bc29acd72 (diff)
downloadyoutube-dl-8e72edfb19b5f6f87210f62f02fe876789641dbe.tar.gz
youtube-dl-8e72edfb19b5f6f87210f62f02fe876789641dbe.zip
[promptfile] Add new extractor
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/promptfile.py67
2 files changed, 68 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 17ed69ba4..1479d998a 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -257,6 +257,7 @@ from .podomatic import PodomaticIE
from .pornhd import PornHdIE
from .pornhub import PornHubIE
from .pornotube import PornotubeIE
+from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE
from .radiofrance import RadioFranceIE
diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py
new file mode 100644
index 000000000..9ef49b19a
--- /dev/null
+++ b/youtube_dl/extractor/promptfile.py
@@ -0,0 +1,67 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ determine_ext,
+ compat_urllib_parse,
+ compat_urllib_request,
+)
+
+
+class PromptFileIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
+ _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]'
+ _TEST = {
+ 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
+ 'md5': 'd1451b6302da7215485837aaea882c4c',
+ 'info_dict': {
+ 'id': 'D21B4746E9-F01462F0FF',
+ 'ext': 'mp4',
+ 'title': 'Birds.mp4',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+
+ if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+ raise ExtractorError('Video %s does not exist' % video_id,
+ expected=True)
+
+ fields = dict(re.findall(r'''(?x)type="hidden"\s+
+ name="(.+?)"\s+
+ value="(.*?)"
+ ''', webpage))
+ post = compat_urllib_parse.urlencode(fields)
+ req = compat_urllib_request.Request(url, post)
+ req.add_header('Content-type', 'application/x-www-form-urlencoded')
+ webpage = self._download_webpage(
+ req, video_id, 'Downloading video page')
+
+ url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
+ title = self._html_search_regex(
+ r'<span.+title="([^"]+)">', webpage, 'title')
+ thumbnail = self._html_search_regex(
+ r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
+ webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
+
+ formats = [{
+ 'format_id': 'sd',
+ 'url': url,
+ 'ext': determine_ext(title),
+ 'quality': 1,
+ }]
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'formats': formats,
+ }