taichino.com

# BeautifulSoup
def scrape_with_bs(html):
  from BeautifulSoup import BeautifulSoup  
  soup = BeautifulSoup(html)
  rows = soup.find('table', attrs={'class':'channel9'}).findAll('tr')
  channels = rows[0].findAll('td', attrs={'class':'station'})
  programs = rows[1].findAll('td', attrs={'class':'turnup'})
  res = []
  for ch, prog in zip(channels, programs):
    res.append((ch.find('span').string, ch.find('a').string, prog.find('a').string))
  return res
 
# lxml
def scrape_with_lxml(html):
  import lxml.html
  root = lxml.html.fromstring(html.decode('utf-8'))
  rows = root.xpath('//table[@class="channel9"]/tr')
  channels = rows[0].xpath('td[@class="station"]')
  programs = rows[1].xpath('td[@class="turnup"]')
  res = []
  for ch, prog in zip(channels, programs):
    res.append((ch.xpath('span/text()')[0], \
          ch.xpath('descendant::a/text()')[0], \
          prog.xpath('descendant::a/text()')[0]) )
  return res

[
    [
        "アナログ1ch", 
        "ＮＨＫ総合", 
        "ニュース"
    ], 
    [
        "アナログ3ch", 
        "ＮＨＫ教育", 
        "ハーバード白熱教室＠東京大学「イチローの年俸は..."
    ], 
    [
        "アナログ4ch", 
        "日本テレビ", 
        "真相報道　バンキシャ!"
    ], 
    [
        "アナログ6ch", 
        "ＴＢＳ", 
        "THE世界遺産「皇帝たちの地下宮殿」〜..."
    ], 
    [
        "アナログ8ch", 
        "フジテレビ", 
        "笑顔がごちそう　ウチゴハン"
    ], 
    [
        "アナログ10ch", 
        "テレビ朝日", 
        "ドライブ　A　GO!GO!「群馬格安温..."
    ], 
    [
        "アナログ12ch", 
        "テレビ東京", 
        "TOKYO　..."
    ], 
    [
        "アナログ14ch", 
        "TOKYO MX", 
        "芸術史と芸術理論( 10)第1回◇放送..."
    ]
]