trends_scrape.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from selenium import webdriver
import re

# 取得する年齢層と性別と値域
age = '18-24'
gen = 'male'
loc = 'jpn'  # '--'だとアメリカ

# ブラウザ起動
driver = webdriver.Firefox()
url = 'http://www.youtube.com/trendsdashboard#age0=' + \
    age + '&gen0=' + gen + '&loc0=' + loc
driver.get(url)

# 動画URL抽出
html = driver.page_source.encode('utf-8')
r = re.compile("/watch\?.+\>")
m = r.findall(html)

# ダブるので奇数番目だけ
for url in m[0::2]:
    print 'http://www.youtube.com' + url[:-2]

driver.quit()