Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 08:24:01 +01:00
Code Issues Releases Activity

Prefer API to scraping HTML when possible

Browse Source 
Also changed instances of `var is None` to `var == None`, and replaced `var.replace('http%3A', 'http:')` with a regex
This commit is contained in:
geauxlo 2020-06-10 06:38:32 +00:00 committed by GitHub
parent bf52996740
commit 3951a7faae
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 40 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
youtube_dl/extractor/screencast.py
View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_parse_qs, compat_parse_qs,
@ -13,6 +15,8 @@
class ScreencastIE(InfoExtractor): class ScreencastIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?screencast\.com/t/(?P<id>[a-zA-Z0-9]+)' _VALID_URL = r'https?://(?:www\.)?screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
_API_URL = 'https://www.screencast.com/api/external/oembed?url=%s&format=json'
_TESTS = [{ _TESTS = [{
'url': 'http://www.screencast.com/t/3ZEjQXlT', 'url': 'http://www.screencast.com/t/3ZEjQXlT',
'md5': '917df1c13798a3e96211dd1561fded83', 'md5': '917df1c13798a3e96211dd1561fded83',
@ -60,13 +64,32 @@ class ScreencastIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
# The info JSON given by the API has a thumbnail URL,
# but it's inferior to the webpage's thumbnail.
# It also has no video description, so we
# definitely still need to get the webpage.
info = self._download_json(
self._API_URL % url, video_id,
'Downloading video info JSON')
video_url = info.get('url')
if video_url != None:
video_url_raw = compat_urllib_request.quote(video_url)
video_url = re.sub(r'^(?P<proto>https|http)%3A',
lambda match: '%s:' % match.group('proto'),
video_url_raw)
title = info.get('title')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex( if video_url == None:
r'<embed name="Video".*?src="([^"]+)"', webpage, video_url = self._html_search_regex(
'QuickTime embed', default=None) r'<embed name="Video".*?src="([^"]+)"', webpage,
'QuickTime embed', default=None)
if video_url is None: if video_url == None:
flash_vars_s = self._html_search_regex( flash_vars_s = self._html_search_regex(
r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars', r'<param name="flashVars" value="([^"]+)"', webpage, 'flash vars',
default=None) default=None)
@ -80,9 +103,11 @@ def _real_extract(self, url):
flash_vars = compat_parse_qs(flash_vars_s) flash_vars = compat_parse_qs(flash_vars_s)
video_url_raw = compat_urllib_request.quote( video_url_raw = compat_urllib_request.quote(
flash_vars['content'][0]) flash_vars['content'][0])
video_url = video_url_raw.replace('http%3A', 'http:') video_url = re.sub(r'^(?P<proto>http|https)%3A',
lambda match: '%s:' % match.group('proto'),
video_url_raw)
if video_url is None: if video_url == None:
video_meta = self._html_search_meta( video_meta = self._html_search_meta(
'og:video', webpage, default=None) 'og:video', webpage, default=None)
if video_meta: if video_meta:
@ -90,28 +115,31 @@ def _real_extract(self, url):
r'src=(.*?)(?:$|&)', video_meta, r'src=(.*?)(?:$|&)', video_meta,
'meta tag video URL', default=None) 'meta tag video URL', default=None)
if video_url is None: if video_url == None:
video_url = self._html_search_regex( video_url = self._html_search_regex(
r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1', r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video url', default=None, group='url') webpage, 'video url', default=None, group='url')
if video_url is None: if video_url == None:
video_url = self._html_search_meta( video_url = self._html_search_meta(
'og:video', webpage, default=None) 'og:video', webpage, default=None)
if video_url is None: if video_url == None:
raise ExtractorError('Cannot find video') raise ExtractorError('Cannot find video')
title = self._og_search_title(webpage, default=None) if title == None:
if title is None: title = self._og_search_title(webpage, default=None)
if title == None:
title = self._html_search_regex( title = self._html_search_regex(
[r'<b>Title:</b> ([^<]+)</div>', [r'<b>Title:</b> ([^<]+)</div>',
r'class="tabSeperator">></span><span class="tabText">(.+?)<', r'class="tabSeperator">></span><span class="tabText">(.+?)<',
r'<title>([^<]+)</title>'], r'<title>([^<]+)</title>'],
webpage, 'title') webpage, 'title')
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage, default=None) description = self._og_search_description(webpage, default=None)
if description is None: if description == None:
description = self._html_search_meta('description', webpage) description = self._html_search_meta('description', webpage)
return { return {