我无法自动检索Youtube视频.这是代码.问题是最后一部分.download = urllib.request.urlopen(download_url).read()
# Youtube video download script
# 10n1z3d[at]w[dot]cn
import urllib.request
import sys
print("\n--------------------------")
print (" Youtube Video Downloader")
print ("--------------------------\n")
try:
video_url = sys.argv[1]
except:
video_url = input('[+] Enter video URL: ')
print("[+] Connecting...")
try:
if(video_url.endswith('&feature=related')):
video_id = video_url.split('www.youtube.com/watch?v=')[1].split('&feature=related')[0]
elif(video_url.endswith('&feature=dir')):
video_id = video_url.split('www.youtube.com/watch?v=')[1].split('&feature=dir')[0]
elif(video_url.endswith('&feature=fvst')):
video_id = video_url.split('www.youtube.com/watch?v=')[1].split('&feature=fvst')[0]
elif(video_url.endswith('&feature=channel_page')):
video_id = video_url.split('www.youtube.com/watch?v=')[1].split('&feature=channel_page')[0]
else:
video_id = video_url.split('www.youtube.com/watch?v=')[1]
except:
print("[-] Invalid URL.")
exit(1)
print("[+] Parsing token...")
try:
url = str(urllib.request.urlopen('http://www.youtube.com/get_video_info?&video_id=' + video_id).read())
token_value = url.split('video_id='+video_id+'&token=')[1].split('&thumbnail_url')[0]
download_url = "http://www.youtube.com/get_video?video_id=" + video_id + "&t=" + token_value + "&fmt=18"
except:
url = str(urllib.request.urlopen('www.youtube.com/watch?v=' + video_id))
exit(1)
v_url=str(urllib.request.urlopen('http://'+video_url).read())
video_title = v_url.split('"rv.2.title": "')[1].split('", "rv.4.rating"')[0]
if '"' in video_title:
video_title = video_title.replace('"','"')
elif '&' in video_title:
video_title = video_title.replace('&','&')
print("[+] Downloading " + '"' + video_title + '"...')
try:
print(download_url)
file = open(video_title + '.mp4', 'wb')
download = urllib.request.urlopen(download_url).read()
print(download)
for line in download:
file.write(line)
file.close()
except:
print("[-] Error downloading. Quitting.")
exit(1)
print("\n[+] Done. The video is saved to the current working directory(cwd).\n")
有一条错误消息:(感谢Wooble)
Traceback (most recent call last): File "C:/Python31/MyLib/DrawingBoard/youtube_download-.py", line 52, indownload = urllib.request.urlopen(download_url).read() File "C:\Python31\lib\urllib\request.py", line 119, in urlopen return _opener.open(url, data, timeout) File "C:\Python31\lib\urllib\request.py", line 353, in open response = meth(req, response) File "C:\Python31\lib\urllib\request.py", line 465, in http_response 'http', request, response, code, msg, hdrs) File "C:\Python31\lib\urllib\request.py", line 385, in error result = self._call_chain(*args) File "C:\Python31\lib\urllib\request.py", line 325, in _call_chain result = func(*args) File "C:\Python31\lib\urllib\request.py", line 560, in http_error_302 return self.parent.open(new, timeout=req.timeout) File "C:\Python31\lib\urllib\request.py", line 353, in open response = meth(req, response) File "C:\Python31\lib\urllib\request.py", line 465, in http_response 'http', request, response, code, msg, hdrs) File "C:\Python31\lib\urllib\request.py", line 391, in error return self._call_chain(*args) File "C:\Python31\lib\urllib\request.py", line 325, in _call_chain result = func(*args) File "C:\Python31\lib\urllib\request.py", line 473, in http_error_default raise HTTPError(req.full_url, code, msg, hdrs, fp) urllib.error.HTTPError: HTTP Error 403: Forbidden
rbp.. 18
原始问题的代码依赖于关于youtube页面和url内容的几个假设(用"url.split('something =')[1]"等结构表示),这可能并不总是正确的.我测试了它,甚至可能取决于页面上显示的相关视频.你可能已经绊倒了这些特殊性.
这是一个更干净的版本,它使用urllib来解析网址和查询字符串,并成功下载视频.为清楚起见,我删除了一些尝试/除了没有做太多但是退出的尝试.顺便提一下,它通过从保存视频的文件名中删除非ascii字符来处理unicode视频标题.它还需要任意数量的youtube网址并将其全部下载.最后,它将其用户代理屏蔽为Chrome for Mac(这是我目前使用的).
#!/usr/bin/env python3
import sys
import urllib.request
from urllib.request import urlopen, FancyURLopener
from urllib.parse import urlparse, parse_qs, unquote
class UndercoverURLopener(FancyURLopener):
version = "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.342.9 Safari/533.2"
urllib.request._urlopener = UndercoverURLopener()
def youtube_download(video_url):
video_id = parse_qs(urlparse(video_url).query)['v'][0]
url_data = urlopen('http://www.youtube.com/get_video_info?&video_id=' + video_id).read()
url_info = parse_qs(unquote(url_data.decode('utf-8')))
token_value = url_info['token'][0]
download_url = "http://www.youtube.com/get_video?video_id={0}&t={1}&fmt=18".format(
video_id, token_value)
video_title = url_info['title'][0] if 'title' in url_info else ''
# Unicode filenames are more trouble than they're worth
filename = video_title.encode('ascii', 'ignore').decode('ascii').replace("/", "-") + '.mp4'
print("\t Downloading '{}' to '{}'...".format(video_title, filename))
try:
download = urlopen(download_url).read()
f = open(filename, 'wb')
f.write(download)
f.close()
except Exception as e:
print("\t Downlad failed! {}".format(str(e)))
print("\t Skipping...")
else:
print("\t Done.")
def main():
print("\n--------------------------")
print (" Youtube Video Downloader")
print ("--------------------------\n")
try:
video_urls = sys.argv[1:]
except:
video_urls = input('Enter (space-separated) video URLs: ')
for u in video_urls:
youtube_download(u)
print("\n Done.")
if __name__ == '__main__':
main()
Jake Wharton.. 6
我将无耻地插入我的脚本,自动检查有效格式,自动选择最佳质量格式的视频,并适用于YouTube页面的Flash和html5变体(以及Vimeo).
如果您编写了该脚本,那么请查看我的源代码以获取灵感并随意窃取一些代码.我挑战你,请写一些更好的东西.开源在竞争中茁壮成长!
但是,如果您复制了该脚本并且只是想让它运行起来,我建议您尝试一下我的脚本,看看它是否适合您.您可以从命令行作为脚本或甚至作为另一个python文件中的模块来访问它.
(编辑:制造维基.不寻找声誉.)
原始问题的代码依赖于关于youtube页面和url内容的几个假设(用"url.split('something =')[1]"等结构表示),这可能并不总是正确的.我测试了它,甚至可能取决于页面上显示的相关视频.你可能已经绊倒了这些特殊性.
这是一个更干净的版本,它使用urllib来解析网址和查询字符串,并成功下载视频.为清楚起见,我删除了一些尝试/除了没有做太多但是退出的尝试.顺便提一下,它通过从保存视频的文件名中删除非ascii字符来处理unicode视频标题.它还需要任意数量的youtube网址并将其全部下载.最后,它将其用户代理屏蔽为Chrome for Mac(这是我目前使用的).
#!/usr/bin/env python3
import sys
import urllib.request
from urllib.request import urlopen, FancyURLopener
from urllib.parse import urlparse, parse_qs, unquote
class UndercoverURLopener(FancyURLopener):
version = "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/533.2 (KHTML, like Gecko) Chrome/5.0.342.9 Safari/533.2"
urllib.request._urlopener = UndercoverURLopener()
def youtube_download(video_url):
video_id = parse_qs(urlparse(video_url).query)['v'][0]
url_data = urlopen('http://www.youtube.com/get_video_info?&video_id=' + video_id).read()
url_info = parse_qs(unquote(url_data.decode('utf-8')))
token_value = url_info['token'][0]
download_url = "http://www.youtube.com/get_video?video_id={0}&t={1}&fmt=18".format(
video_id, token_value)
video_title = url_info['title'][0] if 'title' in url_info else ''
# Unicode filenames are more trouble than they're worth
filename = video_title.encode('ascii', 'ignore').decode('ascii').replace("/", "-") + '.mp4'
print("\t Downloading '{}' to '{}'...".format(video_title, filename))
try:
download = urlopen(download_url).read()
f = open(filename, 'wb')
f.write(download)
f.close()
except Exception as e:
print("\t Downlad failed! {}".format(str(e)))
print("\t Skipping...")
else:
print("\t Done.")
def main():
print("\n--------------------------")
print (" Youtube Video Downloader")
print ("--------------------------\n")
try:
video_urls = sys.argv[1:]
except:
video_urls = input('Enter (space-separated) video URLs: ')
for u in video_urls:
youtube_download(u)
print("\n Done.")
if __name__ == '__main__':
main()
我将无耻地插入我的脚本,自动检查有效格式,自动选择最佳质量格式的视频,并适用于YouTube页面的Flash和html5变体(以及Vimeo).
如果您编写了该脚本,那么请查看我的源代码以获取灵感并随意窃取一些代码.我挑战你,请写一些更好的东西.开源在竞争中茁壮成长!
但是,如果您复制了该脚本并且只是想让它运行起来,我建议您尝试一下我的脚本,看看它是否适合您.您可以从命令行作为脚本或甚至作为另一个python文件中的模块来访问它.
(编辑:制造维基.不寻找声誉.)
京公网安备 11010802040832号 | 京ICP备19059560号-6 