我正在尝试从航班搜索页面中抓取一些数据。
此页面的工作方式如下:
您填写表格,然后单击按钮搜索-可以。当您单击按钮时,您将被重定向到包含结果的页面,这就是问题所在。例如,此页面会持续添加一分钟的结果,这没什么大不了的- 问题是要获得所有这些结果。在实际的浏览器中,您必须向下滚动页面,然后才会显示这些结果。因此,我尝试使用Selenium向下滚动。它可能在页面底部如此之快地向下滚动,或者是跳转而不是滚动,以致该页面不加载任何新结果。
当您缓慢向下滚动时,它将重新加载结果,但是如果您做得很快,它将停止加载。
我不确定我的代码是否有助于理解这一点,所以我附上了它。
SEARCH_STRING = """URL""" class spider(): def __init__(self): self.driver = webdriver.Firefox() @staticmethod def prepare_get(dep_airport,arr_airport,dep_date,arr_date): string = SEARCH_STRING%(dep_airport,arr_airport,arr_airport,dep_airport,dep_date,arr_date) return string def find_flights_html(self,dep_airport, arr_airport, dep_date, arr_date): if isinstance(dep_airport, list): airports_string = str(r'%20').join(dep_airport) dep_airport = airports_string wait = WebDriverWait(self.driver, 60) # wait for results self.driver.get(spider.prepare_get(dep_airport, arr_airport, dep_date, arr_date)) wait.until(EC.invisibility_of_element_located((By.XPATH, '//img[contains(@src, "loading")]'))) wait.until(EC.invisibility_of_element_located((By.XPATH, u'//div[. = "Poprosíme o trpezlivosť, hľadáme pre Vás ešte viac letov"]/preceding-sibling::img'))) self.driver.execute_script("window.scrollTo(0,document.body.scrollHeight);") self.driver.find_element_by_xpath('//body').send_keys(Keys.CONTROL+Keys.END) return self.driver.page_source @staticmethod def get_info_from_borderbox(div): arrival = div.find('div',class_='departure').text price = div.find('div',class_='pricebox').find('div',class_=re.compile('price')) departure = div.find_all('div',class_='departure')[1].contents date_departure = departure[1].text airport_departure = departure[5].text arrival = div.find_all('div', class_= 'arrival')[0].contents date_arrival = arrival[1].text airport_arrival = arrival[3].text[1:] print 'DEPARTURE: ' print date_departure,airport_departure print 'ARRIVAL: ' print date_arrival,airport_arrival @staticmethod def get_flights_from_result_page(html): def match_tag(tag, classes): return (tag.name == 'div' and 'class' in tag.attrs and all([c in tag['class'] for c in classes])) soup = mLib.getSoup_html(html) divs = soup.find_all(lambda t: match_tag(t, ['borderbox', 'flightbox', 'p2'])) for div in divs: spider.get_info_from_borderbox(div) print len(divs) spider_inst = spider() print spider.get_flights_from_result_page(spider_inst.find_flights_html(['BTS','BRU','PAR'], 'MAD', '2015-07-15', '2015-08-15'))
因此,主要问题是我认为滚动速度太快而无法触发结果的新加载。
你知道如何使它起作用吗?
这是一种对我有用的不同方法,其中涉及 滚动到 最后一个搜索结果的 视图 ,并等待其他元素加载后再次滚动:
# -*- coding: utf-8 -*- from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import WebDriverWait from selenium.common.exceptions import StaleElementReferenceException from selenium.webdriver.support import expected_conditions as EC class wait_for_more_than_n_elements(object): def __init__(self, locator, count): self.locator = locator self.count = count def __call__(self, driver): try: count = len(EC._find_elements(driver, self.locator)) return count >= self.count except StaleElementReferenceException: return False driver = webdriver.Firefox() dep_airport = ['BTS', 'BRU', 'PAR'] arr_airport = 'MAD' dep_date = '2015-07-15' arr_date = '2015-08-15' airports_string = str(r'%20').join(dep_airport) dep_airport = airports_string url = "https://www.pelikan.sk/sk/flights/list?dfc=C%s&dtc=C%s&rfc=C%s&rtc=C%s&dd=%s&rd=%s&px=1000&ns=0&prc=&rng=1&rbd=0&ct=0" % (dep_airport, arr_airport, arr_airport, dep_airport, dep_date, arr_date) driver.maximize_window() driver.get(url) wait = WebDriverWait(driver, 60) wait.until(EC.invisibility_of_element_located((By.XPATH, '//img[contains(@src, "loading")]'))) wait.until(EC.invisibility_of_element_located((By.XPATH, u'//div[. = "Poprosíme o trpezlivosť, hľadáme pre Vás ešte viac letov"]/preceding-sibling::img'))) while True: # TODO: make the endless loop end results = driver.find_elements_by_css_selector("div.flightbox") print "Results count: %d" % len(results) # scroll to the last element driver.execute_script("arguments[0].scrollIntoView();", results[-1]) # wait for more results to load wait.until(wait_for_more_than_n_elements((By.CSS_SELECTOR, 'div.flightbox'), len(results)))
笔记:
len(results)
wait_for_more_than_n_elements