【Python3】PhontomJsを使ってCookieを登録してスクレイピング
PhontomJsを使ってCookieを登録してスクレイピングする。
環境
Windows10 cygwin python3.4 phantomjs-2.1.1
プログラム抜粋
def scraping(url): log_name = "/tmp/phantomjs.log" #ログを出力しない場合はos.path.devnull userAgent = "Mozilla/5.0 (iPhone; CPU iPhone OS 7_1_2 like Mac OS X) AppleWebKit/537.51.2 (KHTML, like Gecko) Version/7.0 Mobile/11D257 Safari/9537.53" driver = webdriver.PhantomJS( desired_capabilities={ 'phantomjs.page.settings.userAgent': userAgent, }, service_log_path=log_name ) cookieList = [ { "domain": ".hogehoge.com", "name": "test1", "path": "/", "value": "123" }, { "domain": ".hogehoge.com", "name": "foo", "path": "/", "value": "abc" } ] for c in cookieList: driver.add_cookie(c) driver.get(url) html = driver.page_source soup = BeautifulSoup(html, "lxml") header = soup.find("head") title = header.find("title").text print(title)