Created
July 24, 2014 07:12
-
-
Save albingeorge/fd11b65baf15f9e0395d to your computer and use it in GitHub Desktop.
Download all videos from a youtube channel
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import mechanize | |
import cookielib | |
from bs4 import BeautifulSoup | |
import re, urllib2, sys, json, os, resource | |
from pprint import pprint | |
from urlparse import urlparse, parse_qs | |
class Browser: | |
"""A browser to use to crawl the site""" | |
def __init__(self, user_agent): | |
self.browser = mechanize.Browser() | |
# Cookie Jar | |
cj = cookielib.LWPCookieJar() | |
self.browser.set_cookiejar(cj) | |
# Browser options | |
self.browser.set_handle_equiv(True) | |
# self.browser.set_handle_gzip(True) | |
self.browser.set_handle_redirect(True) | |
self.browser.set_handle_referer(True) | |
self.browser.set_handle_robots(False) | |
# Follows refresh 0 but not hangs on refresh > 0 | |
self.browser.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1) | |
self.browser.addheaders = [('User-agent', user_agent)] | |
def get_html_from_url(self, url): | |
r = self.browser.open(url) | |
return r.read() | |
url = sys.argv[1] | |
user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:29.0) Gecko/20100101 Firefox/29.0' | |
browser = Browser(user_agent) | |
html = browser.get_html_from_url(url) | |
soup = BeautifulSoup(html) | |
playlist = soup.findAll('li', {"class" : "yt-uix-scroller-scroll-unit"}) | |
urls = [] | |
for listelement in playlist: | |
for a in listelement.find_all('a', href=True): | |
urls.append("https://www.youtube.com" + a['href']) | |
# Yaay!! Got the urls | |
for url in urls: | |
print "Resource used: " + str(resource.getrusage(resource.RUSAGE_SELF).ru_maxrss) + "!!!" | |
html = browser.get_html_from_url(url) | |
soup = BeautifulSoup(html) | |
title = soup.title.string | |
title = re.sub(r'\W+', '_', title.title()) | |
target_file_name = title + ".flv" | |
if os.path.isfile(os.getcwd() + "/" + target_file_name) and os.stat(os.getcwd() + "/" + target_file_name).st_size != 0: | |
print "Ignoring downloading of the file " + target_file_name | |
continue | |
test = [elem.get_text() for elem in soup.findAll(['script']) if elem.get_text().startswith('var ytplayer')] | |
test = test[0] | |
start_string = 'ytplayer.config = ' | |
result = test[test.find(start_string) + len(start_string) : test.find(';(function() {var encoded')] | |
results = json.loads(result) | |
videos = results['args']['url_encoded_fmt_stream_map'] | |
queries_as_list = parse_qs(videos) | |
with open ('testfile.html', 'w') as f: f.write ('') | |
with open('testfile.html', 'wt') as out: | |
pprint(queries_as_list, stream=out) | |
itags = [] | |
for url in queries_as_list['url']: | |
itags.append(re.search('itag\=([0-9]+)',url).group(1)) | |
itags = map(int, itags) | |
index_max_itag = itags.index(max(itags)) | |
url = queries_as_list['url'][index_max_itag] | |
# Download file | |
tofile = open("./" + target_file_name,"w") | |
print "Downloading " + target_file_name | |
try: | |
r = browser.browser.open(url).read() | |
tofile.write(r) | |
except: | |
print "Download failed for file " + target_file_name | |
tofile.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment