您需要做的是:
实现方式:
from selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECimport pandas as pdurls = [ 'http://www.oddsportal.com/hockey/austria/ebel-2014-2015/results/#/page/', 'http://www.oddsportal.com/hockey/austria/ebel-2013-2014/results/#/page/']data = []driver = webdriver.PhantomJS()driver.implicitly_wait(10)wait = WebDriverWait(driver, 10)for url in urls: for page in range(1, 8): driver.get(url + str(page)) # wait for the page to load wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div#tournamentTable tr.deactivate"))) for match in driver.find_elements_by_css_selector("div#tournamentTable tr.deactivate"): home, away = match.find_element_by_class_name("table-participant").text.split(" - ") date = match.find_element_by_xpath(".//preceding::th[contains(@class, 'first2')][1]").text if " - " in date: date, event = date.split(" - ") else: event = "Not specified" data.append({ "home": home.strip(), "away": away.strip(), "date": date.strip(), "event": event.strip() })driver.close()df = pd.Dataframe(data)print(df)
印刷品:
away date event home0 Salzburg 14 Apr 2015 Play Offs Vienna Capitals1 Vienna Capitals 12 Apr 2015 Play Offs Salzburg2 Salzburg 10 Apr 2015 Play Offs Vienna Capitals3 Vienna Capitals 07 Apr 2015 Play Offs Salzburg4 Vienna Capitals 31 Mar 2015 Play Offs Liwest Linz5 Salzburg 29 Mar 2015 Play Offs Klagenfurt6Liwest Linz 29 Mar 2015 Play Offs Vienna Capitals7 Klagenfurt 26 Mar 2015 Play Offs Salzburg8 Vienna Capitals 26 Mar 2015 Play Offs Liwest Linz9Liwest Linz 24 Mar 2015 Play Offs Vienna Capitals10 Salzburg 24 Mar 2015 Play Offs Klagenfurt11Klagenfurt 22 Mar 2015 Play Offs Salzburg12 Vienna Capitals 22 Mar 2015 Play Offs Liwest Linz13 Bolzano 20 Mar 2015 Play Offs Liwest Linz14 Fehervar AV19 18 Mar 2015 Play Offs Vienna Capitals15 Liwest Linz 17 Mar 2015 Play Offs Bolzano16 Vienna Capitals 16 Mar 2015 Play Offs Fehervar AV1917 Villach 15 Mar 2015 Play Offs Salzburg18Klagenfurt 15 Mar 2015 Play Offs Znojmo19 Bolzano 15 Mar 2015 Play Offs Liwest Linz20 Liwest Linz 13 Mar 2015 Play Offs Bolzano21 Fehervar AV19 13 Mar 2015 Play Offs Vienna Capitals22 Znojmo 13 Mar 2015 Play Offs Klagenfurt23 Salzburg 13 Mar 2015 Play Offs Villach24Klagenfurt 10 Mar 2015 Play Offs Znojmo25 Vienna Capitals 10 Mar 2015 Play Offs Fehervar AV1926 Bolzano 10 Mar 2015 Play Offs Liwest Linz27 Villach 10 Mar 2015 Play Offs Salzburg28 Liwest Linz 08 Mar 2015 Play Offs Bolzano29 Znojmo 08 Mar 2015 Play Offs Klagenfurt.. ... ... ... ...670 TWK Innsbruck 28 Sep 2013 Not specified Znojmo671 Liwest Linz 27 Sep 2013 Not specified Dornbirn672 Bolzano 27 Sep 2013 Not specified Graz 99ers673 Klagenfurt 27 Sep 2013 Not specified Olimpija Ljubljana674 Fehervar AV19 27 Sep 2013 Not specified Salzburg675 TWK Innsbruck 27 Sep 2013 Not specified Vienna Capitals676 Villach 27 Sep 2013 Not specified Znojmo677 Salzburg 24 Sep 2013 Not specified Olimpija Ljubljana678 Dornbirn 22 Sep 2013 Not specified TWK Innsbruck679 Graz 99ers 22 Sep 2013 Not specified Klagenfurt680 Vienna Capitals 22 Sep 2013 Not specified Villach681 Fehervar AV19 21 Sep 2013 Not specified Bolzano682 Dornbirn 20 Sep 2013 Not specified Bolzano683 Villach 20 Sep 2013 Not specified Graz 99ers684 Znojmo 20 Sep 2013 Not specified Klagenfurt685 Olimpija Ljubljana 20 Sep 2013 Not specified Liwest Linz686 Fehervar AV19 20 Sep 2013 Not specified TWK Innsbruck687 Salzburg 20 Sep 2013 Not specified Vienna Capitals688 Villach 15 Sep 2013 Not specified Klagenfurt689 Liwest Linz 15 Sep 2013 Not specified Dornbirn690 Vienna Capitals 15 Sep 2013 Not specified Fehervar AV19691 TWK Innsbruck 15 Sep 2013 Not specified Salzburg692 Graz 99ers 15 Sep 2013 Not specified Znojmo693 Olimpija Ljubljana 14 Sep 2013 Not specified Dornbirn694 Bolzano 14 Sep 2013 Not specified Fehervar AV19695 Klagenfurt 13 Sep 2013 Not specified Graz 99ers696 Znojmo 13 Sep 2013 Not specified Salzburg697 Olimpija Ljubljana 13 Sep 2013 Not specified TWK Innsbruck698 Bolzano 13 Sep 2013 Not specified Vienna Capitals699 Liwest Linz 13 Sep 2013 Not specified Villach[700 rows x 4 columns]
欢迎分享,转载请注明来源:内存溢出
评论列表(0条)