[pr0gramm] implement InfoExtractor, Resolves #31433 (#31434)

* [pr0gramm] implement infoextractor

* [pr0gramm] remove misplaced comment, uncapture regex-group

* [pr0gramm]: specify utf-8 coding

* [pr0gramm]: add trailing comma to lists for maintainability

* [pr0gramm]: ie only sets upload_date attribute

* [pr0gramm]: add video_id to title

* [pr0gramm]: more forgiving _valid_url regex

* [pr0gramm]: add uploader to title, if set

* Discriminate URL pattern

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
pull/31019/head^2
Leon Etienne 2023-02-02 18:13:39 +01:00 committed by GitHub
parent 807e593a32
commit e9611a2a36
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 109 additions and 0 deletions

View File

@ -1667,3 +1667,7 @@ from .zingmp3 import (
)
from .zoom import ZoomIE
from .zype import ZypeIE
from .pr0gramm import (
Pr0grammIE,
Pr0grammStaticIE,
)

View File

@ -0,0 +1,105 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import re
from ..utils import (
merge_dicts,
)
class Pr0grammStaticIE(InfoExtractor):
# Possible urls:
# https://pr0gramm.com/static/5466437
_VALID_URL = r'https?://pr0gramm\.com/static/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://pr0gramm.com/static/5466437',
'md5': '52fa540d70d3edc286846f8ca85938aa',
'info_dict': {
'id': '5466437',
'ext': 'mp4',
'title': 'pr0gramm-5466437 by g11st',
'uploader': 'g11st',
'upload_date': '20221221',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# Fetch media sources
entries = self._parse_html5_media_entries(url, webpage, video_id)
media_info = entries[0]
# this raises if there are no formats
self._sort_formats(media_info.get('formats') or [])
# Fetch author
uploader = self._html_search_regex(r'by\W+([\w-]+)\W+', webpage, 'uploader')
# Fetch approx upload timestamp from filename
# Have None-defaults in case the extraction fails
uploadDay = None
uploadMon = None
uploadYear = None
uploadTimestr = None
# (//img.pr0gramm.com/2022/12/21/62ae8aa5e2da0ebf.mp4)
m = re.search(r'//img\.pr0gramm\.com/(?P<year>[\d]+)/(?P<mon>[\d]+)/(?P<day>[\d]+)/\w+\.\w{,4}', webpage)
if (m):
# Up to a day of accuracy should suffice...
uploadDay = m.groupdict().get('day')
uploadMon = m.groupdict().get('mon')
uploadYear = m.groupdict().get('year')
uploadTimestr = uploadYear + uploadMon + uploadDay
return merge_dicts({
'id': video_id,
'title': 'pr0gramm-%s%s' % (video_id, (' by ' + uploader) if uploader else ''),
'uploader': uploader,
'upload_date': uploadTimestr
}, media_info)
# This extractor is for the primary url (used for sharing, and appears in the
# location bar) Since this page loads the DOM via JS, yt-dl can't find any
# video information here. So let's redirect to a compatibility version of
# the site, which does contain the <video>-element by itself, without requiring
# js to be ran.
class Pr0grammIE(InfoExtractor):
# Possible urls:
# https://pr0gramm.com/new/546637
# https://pr0gramm.com/new/video/546637
# https://pr0gramm.com/top/546637
# https://pr0gramm.com/top/video/546637
# https://pr0gramm.com/user/g11st/uploads/5466437
# https://pr0gramm.com/user/froschler/dafur-ist-man-hier/5091290
# https://pr0gramm.com/user/froschler/reinziehen-1elf/5232030
# https://pr0gramm.com/user/froschler/1elf/5232030
# https://pr0gramm.com/new/5495710:comment62621020 <- this is not the id!
# https://pr0gramm.com/top/fruher war alles damals/5498175
_VALID_URL = r'https?:\/\/pr0gramm\.com\/(?!static/\d+).+?\/(?P<id>[\d]+)(:|$)'
_TEST = {
'url': 'https://pr0gramm.com/new/video/5466437',
'info_dict': {
'id': '5466437',
'ext': 'mp4',
'title': 'pr0gramm-5466437 by g11st',
'uploader': 'g11st',
'upload_date': '20221221',
}
}
def _generic_title():
return "oof"
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'https://pr0gramm.com/static/' + video_id,
video_id=video_id,
ie=Pr0grammStaticIE.ie_key())