【プログラミング】Pythonで色々 スクレイピング（Beautiful Soup+Selenium+PhantomJS）とか形態素解析

import lxml.html
from selenium import webdriver
from bs4 import BeautifulSoup
import pandas as pd
import time

aaa = []
bbb = []
ccc = []

for page in range(1,2): # ページの上限は適宜設定　page=の後に番号が繰り上がるサイトのスクレイピング用です
    driver = webdriver.PhantomJS()
    driver.get('https://www.～～=page=' + str(page))
    data = driver.page_source.encode('utf-8')
    soup = BeautifulSoup(data, 'lxml')

    for o in soup.findAll('h3', class_='hoge'):
        aaa.append(o.string)

    for o1 in soup.findAll('h3', class_='hoge'):
        bbb.append(o1.string)

    for o2 in soup.findAll('div', class_='hoge'):
        ccc.append(o2.get_text())
    time.sleep(3)

df = pd.DataFrame({'aaa':aaa, 'bbb':bbb, 'ccc':ccc})

print(df)
df.to_csv('hogehoge.csv', index=False, encoding='utf-8')

driver.quit()