src/you_get/extractors/imgur.py - develop - githubmirror/you-get

src/you_get/extractors/imgur.py
77 строк3 KB
Mort Yao
[imgur] fix extraction
20 май 2024, 05:56
20 май 2024, 05:560b9fec5
#!/usr/bin/env python

from ..common import *
from ..extractor import VideoExtractor
from .universal import *

class Imgur(VideoExtractor):
    name = "Imgur"

    stream_types = [
        {'id': 'original'},
        {'id': 'thumbnail'},
    ]

    def prepare(self, **kwargs):
        self.ua = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/123.0.2420.97'

        if re.search(r'imgur\.com/a/', self.url):
            # album
            content = get_content(self.url, headers=fake_headers)
            album = match1(content, r'album\s*:\s*({.*}),') or \
                    match1(content, r'image\s*:\s*({.*}),')
            album = json.loads(album)
            count = album['album_images']['count']
            images = album['album_images']['images']
            ext = images[0]['ext']
            self.streams = {
                'original': {
                    'src': ['http://i.imgur.com/%s%s' % (i['hash'], ext)
                            for i in images],
                    'size': sum([i['size'] for i in images]),
                    'container': ext[1:]
                },
                'thumbnail': {
                    'src': ['http://i.imgur.com/%ss%s' % (i['hash'], '.jpg')
                            for i in images],
                    'container': 'jpg'
                }
            }
            self.title = album['title']

        elif re.search(r'i\.imgur\.com/', self.url):
            # direct image
            _, container, size = url_info(self.url, faker=True)
            self.streams = {
                'original': {
                    'src': [self.url],
                    'size': size,
                    'container': container
                }
            }
            self.title = r1(r'i\.imgur\.com/([^./]*)', self.url)

        else:
            # gallery image
            content = get_content(self.url, headers=fake_headers)
            url = match1(content, r'meta property="og:video"[^>]+(https?://i.imgur.com/[^"?]+)') or \
                match1(content, r'meta property="og:image"[^>]+(https?://i.imgur.com/[^"?]+)')
            _, container, size = url_info(url, headers={'User-Agent': fake_headers['User-Agent']})
            self.streams = {
                'original': {
                    'src': [url],
                    'size': size,
                    'container': container
                }
            }
            self.title = r1(r'i\.imgur\.com/([^./]*)', url)

    def extract(self, **kwargs):
        if 'stream_id' in kwargs and kwargs['stream_id']:
            i = kwargs['stream_id']
            if 'size' not in self.streams[i]:
                self.streams[i]['size'] = urls_size(self.streams[i]['src'])

site = Imgur()
download = site.download_by_url
download_playlist = site.download_by_url