Downloading videos in flv format from youtube.

后端 未结 3 479
闹比i
闹比i 2021-01-31 06:08

I cant really understand how youtube serves videos but I have been reading through what I can, it seems like the old method get_video is now obsolete and can\'t be used any more

3条回答
  •  清酒与你
    2021-01-31 07:14

    Here is a quick Python script which downloads a Youtube video. No bells and whistles, just scrapes out the necessary urls, hits the generate_204 url and then streams the data to a file:

    import lxml.html
    import re
    import sys
    import urllib
    import urllib2
    
    _RE_G204 = re.compile('"(http:.+.youtube.com.*\/generate_204[^"]+")', re.M)
    _RE_URLS = re.compile('"fmt_url_map": "(\d*[^"]+)",.*', re.M)
    
    def _fetch_url(url, ref=None, path=None):
        opener = urllib2.build_opener()
        headers = {}
        if ref:
            headers['Referer'] = ref
        request = urllib2.Request(url, headers=headers)
        handle = urllib2.urlopen(request)
        if not path:
            return handle.read()
        sys.stdout.write('saving: ')
        # write result to file
        with open(path, 'wb') as out:
            while True:
                part = handle.read(65536)
                if not part:
                    break
                out.write(part)
                sys.stdout.write('.')
                sys.stdout.flush()
            sys.stdout.write('\nFinished.\n')
    
    def _extract(html):
        tree = lxml.html.fromstring(html)
        res = {'204': _RE_G204.findall(html)[0].replace('\\', '')}
        for script in tree.findall('.//script'):
            text = script.text_content()
            if 'fmt_url_map' not in text:
                continue
            # found it, extract the urls we need
            for tmp in _RE_URLS.findall(text)[0].split(','):
                url_id, url = tmp.split('|')
                res[url_id] = url.replace('\\', '')
            break
        return res
    
    def main():
        target = sys.argv[1]
        dest = sys.argv[2]
        html = _fetch_url(target)
        res = dict(_extract(html))
        # hit the 'generate_204' url first and remove it
        _fetch_url(res['204'], ref=target)
        del res['204']
        # download the video. now i grab the first 'download' url and use it.
        first = res.values()[0]
        _fetch_url(first, ref=target, path=dest)
    
    if __name__ == '__main__':
        main()
    

    Running it:

    python youdown.py 'http://www.youtube.com/watch?v=Je_iqbgGXFw' stevegadd.flv
    saving: ........................... finished.
    

提交回复
热议问题