Created
September 14, 2019 07:40
-
-
Save potaycat/335ff3e89363e2b51c0d2414145debb2 to your computer and use it in GitHub Desktop.
one of my first encounter to the web. a recreate of Tom Scott's youtube privacy demo in a presentation of his
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 urllib | |
import urllib2 | |
from bs4 import BeautifulSoup | |
from lxml import etree | |
def main(): | |
textToSearch = raw_input('tim video cho thuyet trinh: ') | |
query = urllib.quote(textToSearch) | |
url = "https://www.youtube.com/results?search_query=" + query | |
response = urllib2.urlopen(url) | |
html = response.read() | |
soup = BeautifulSoup(html) | |
htmlify(soup) | |
def htmlify(sup): | |
root = etree.Element('html') | |
a = etree.Element('body') | |
root.append(a) | |
b = etree.Element('text') | |
b.text = "Danh cho phan dan chung" | |
a.append(b) | |
etree.SubElement(b, 'br') | |
etree.SubElement(b, 'br') | |
for vid in range(0,6): | |
linka = sup.findAll(attrs={'class':'yt-uix-tile-link'})[vid] | |
fr = etree.Element('iframe') | |
fr.set('width',"420") | |
fr.set('height',"260") | |
fr.set('src', 'https://www.youtube.com/embed/' + linka['href'][9:9+11] + '?autoplay=1&vq=tiny' ) | |
etree.SubElement(fr, 'lazyWorkaround') | |
a.append(fr) | |
string = etree.tostring(root, pretty_print=True) | |
text_file = open("ytSrchPull.html", "w") | |
text_file.write(string) | |
text_file.close() | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment