Merge tag 'upstream/2017.03.07'

[youtubedl] / youtube_dl / extractor / promptfile.py

diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py
index 7fcde086c0b234f7020cfa9811425d22355808a3..23ac93d7e248bce034fcb221d26089d8be412ee2 100644 (file)
--- a/youtube_dl/extractor/promptfile.py
+++ b/youtube_dl/extractor/promptfile.py
@@ -5,23 +5,22 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     determine_ext,
-    compat_urllib_parse,
-    compat_urllib_request,
+    ExtractorError,
+    urlencode_postdata,
 )
 
 
 class PromptFileIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
     _TEST = {
-        'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
-        'md5': 'd1451b6302da7215485837aaea882c4c',
+        'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416',
+        'md5': '5a7e285a26e0d66d9a263fae91bc92ce',
         'info_dict': {
-            'id': 'D21B4746E9-F01462F0FF',
+            'id': '86D1CE8462-576CAAE416',
             'ext': 'mp4',
-            'title': 'Birds.mp4',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'title': 'oceans.mp4',
+            'thumbnail': r're:^https?://.*\.jpg$',
         }
     }
 
@@ -33,17 +32,23 @@ class PromptFileIE(InfoExtractor):
             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')
+        chash = self._search_regex(
+            r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash')
+        fields = self._hidden_inputs(webpage)
+        keys = list(fields.keys())
+        chash_key = keys[0] if len(keys) == 1 else next(
+            key for key in keys if key.startswith('cha'))
+        fields[chash_key] = chash + fields[chash_key]
+
         webpage = self._download_webpage(
-            req, video_id, 'Downloading video page')
+            url, video_id, 'Downloading video page',
+            data=urlencode_postdata(fields),
+            headers={'Content-type': 'application/x-www-form-urlencoded'})
 
-        url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL')
+        video_url = self._search_regex(
+            (r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*Download File',
+             r'<a[^>]+href=(["\'])(?P<url>https?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'),
+            webpage, 'video url', group='url')
         title = self._html_search_regex(
             r'<span.+title="([^"]+)">', webpage, 'title')
         thumbnail = self._html_search_regex(
@@ -52,7 +57,7 @@ class PromptFileIE(InfoExtractor):
 
         formats = [{
             'format_id': 'sd',
-            'url': url,
+            'url': video_url,
             'ext': determine_ext(title),
         }]
         self._sort_formats(formats)