R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[Go90] Use UplynkPreplayIE to extract data

Browse Source
This commit is contained in:
Jeremie J. Jarosh 2017-02-04 12:11:21 -06:00
parent f4b3346573
commit f7fe731cbf
1 changed files with 30 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
youtube_dl/extractor/go90.py
View File

@ -1,10 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import urllib #DEBUG
from .common import InfoExtractor
from .uplynk import UplynkPreplayIE
from ..utils import sanitize_url
class Go90IE(InfoExtractor):
@ -16,7 +15,7 @@ class Go90IE(InfoExtractor):
'id': '07d47f43a7b04eb5b693252f2bd1086b',
'ext': 'mp4',
'title': 't@gged S1:E1 #shotgun',
'thumbnail': 're:^https?://.*\.jpg$',
'thumbnail': r're:^https?://.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
@ -29,52 +28,31 @@ class Go90IE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
#title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
series_title = self._html_search_regex(r'<h1\b[^>]* data-reactid="90">(.+?)</h1>', webpage, 'series_title')
season_episode_numbers = self._html_search_regex(r'<!-- react-text: 92 -->(.+?)<!-- /react-text -->', webpage, 'season_episode_numbers')
episode_title = self._html_search_regex(r'<!-- react-text: 93 -->(.+?)<!-- /react-text -->', webpage, 'episode_title')
title = series_title + " " + season_episode_numbers + " " + episode_title
#print "[!!!] " + title
#page_data_json = self._search_regex(r'<script\b[^>]*>window\.__data=(.+?);\s*</script>', webpage, 'page_data', flags=re.DOTALL)
#print self.transform_source(page_data_json)
#page_data = self._parse_json(page_data_json, video_id, transform_source=self.transform_source)
video_api = "https://www.go90.com/api/metadata/video/" + video_id
video_api_data = self._download_json(video_api, video_id) #TODO: overwrite `note=` to output better explanation
#print "[!!!] " + video_api_data['url']
video_token_url = re.sub(r'^//', 'https://', video_api_data['url']) #TODO: use utils.sanitize_url()
#print "[!!!] " + video_token_url
video_token_data = self._download_json(video_token_url, video_id) #TODO: overwrite `note=` to output better explanation
#print "[!!!] " + video_token_data['playURL']
m3u8_url = video_token_data['playURL']
#DEBUG
testfile = urllib.URLopener()
testfile.retrieve(m3u8_url, video_id + ".m3u8")
#/DEBUG
formats = []
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'formats': formats,
#'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
#def transform_source(self, json_string):
# return re.sub(re.sub(r':function.*?},([\[{"])', ':"",\g<1>', json_string, flags=re.DOTALL)
# scrape data from webpage
page_data = {}
self.to_screen("Scrape data from webpage")
page_data['id'] = video_id
video_title = self._html_search_regex(
r'<title\b[^>]*>\s*(.*)\s*</title>', webpage, 'title')
page_data['title'] = video_title
self.to_screen("Title: " + page_data['title'])
# retrieve upLynk data
video_api = "https://www.go90.com/api/metadata/video/" + video_id
video_api_data = self._download_json(video_api, video_id) #TODO: overwrite `note=` to output better explanation
video_token_url = sanitize_url(video_api_data['url'])
uplynk_preplay = UplynkPreplayIE(self._downloader)
uplynk_data = uplynk_preplay.extract(video_token_url)
# merge data
video_data = uplynk_data.copy()
video_data.update(page_data)
# TODO more properties (see youtube_dl/extractor/common.py)
return video_data