1
0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-22 01:17:22 +00:00
youtube-dl/youtube_dl/extractor/promptfile.py
2016-09-26 23:20:58 +07:00

69 lines
2.2 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
sanitized_Request,
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/86D1CE8462-576CAAE416',
'md5': '5a7e285a26e0d66d9a263fae91bc92ce',
'info_dict': {
'id': '86D1CE8462-576CAAE416',
'ext': 'mp4',
'title': 'oceans.mp4',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
chash_pattern = r'\$\("#chash"\)\.val\("(.+)"\+\$\("#chash"\)'
chash = self._html_search_regex(chash_pattern, webpage, "chash")
fields = self._hidden_inputs(webpage)
k = list(fields)[0]
fields[k] = chash + fields[k]
post = urlencode_postdata(fields)
req = sanitized_Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(
req, video_id, 'Downloading video page')
url_pattern = r'<a href="(http://www\.promptfile\.com/file/[^"]+)'
url = self._html_search_regex(url_pattern, 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),
}]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}