Question

我尝试将搜索结果打印到控制台，即使用python语言中的selenium

import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys

browser = webdriver.Chrome('/Users/Downloads/chromedriver')
browser.get('http://www.google.com')
search = browser.find_element_by_name('q')
search.send_keys("youtube")
search.send_keys(Keys.RETURN)
print(browser)
time.sleep(10)
browser.quit()

打印方法不正确。

Answer 1

我写了一个你可以使用的简单类，你只需要改变webdriver的路径。它是为PhantomJS制作的（您可以下载here。），但如果您想使用Chrome（或任何其他网络驱动程序），只需将行self.driver = webdriver.PhantomJS(path)替换为self.driver = webdriver.Chrome(path)。下面是代码示例：

import time
from urllib.parse import quote_plus
from selenium import webdriver


class Browser:

    def __init__(self, path, initiate=True, implicit_wait_time = 10, explicit_wait_time = 2):
        self.path = path
        self.implicit_wait_time = implicit_wait_time    # http://www.aptuz.com/blog/selenium-implicit-vs-explicit-waits/
        self.explicit_wait_time = explicit_wait_time    # http://www.aptuz.com/blog/selenium-implicit-vs-explicit-waits/
        if initiate:
            self.start()
        return

    def start(self):
        self.driver = webdriver.PhantomJS(self.path)
        self.driver.implicitly_wait(self.implicit_wait_time)
        return

    def end(self):
        self.driver.quit()
        return

    def go_to_url(self, url, wait_time = None):
        if wait_time is None:
            wait_time = self.explicit_wait_time
        self.driver.get(url)
        print('[*] Fetching results from: {}'.format(url))
        time.sleep(wait_time)
        return

    def get_search_url(self, query, page_num=0, per_page=10, lang='en'):
        query = quote_plus(query)
        url = 'https://www.google.hr/search?q={}&num={}&start={}&nl={}'.format(query, per_page, page_num*per_page, lang)
        return url

    def scrape(self):
        #xpath migth change in future
        links = self.driver.find_elements_by_xpath("//h3[@class='r']/a[@href]") # searches for all links insede h3 tags with class "r"
        results = []
        for link in links:
            d = {'url': link.get_attribute('href'),
                 'title': link.text}
            results.append(d)
        return results

    def search(self, query, page_num=0, per_page=10, lang='en', wait_time = None):
        if wait_time is None:
            wait_time = self.explicit_wait_time
        url = self.get_search_url(query, page_num, per_page, lang)
        self.go_to_url(url, wait_time)
        results = self.scrape()
        return results




path = '<YOUR PATH TO PHANTOMJS>/phantomjs-2.1.1-windows/bin/phantomjs.exe' ## SET YOU PATH TO phantomjs
br = Browser(path)
results = br.search('site:facebook.com inurl:login')
for r in results:
    print(r)

br.end()

Answer 2

在java中，它将如下所示： -

List<WebElement> print = driver.findElements(By.xpath("//div[@class='sbqs_c']"));
System.out.println(print.size());
for ( WebElement we: print) { 
    System.out.println(we.getText());
}

我不是蟒蛇人，但可能会像： -

    browser = webdriver.Chrome('/Users/Downloads/chromedriver')
    browser.get('http://www.google.com')
    search = browser.find_element_by_name('q')
    search.send_keys("youtube")
       ids = driver.find_elements_by_xpath("//div[@class='sbqs_c']")
       for ii in ids:
       #print ii.text
       print ii.text

资料来源： - Iterate a list with indexes in Python

希望它会对你有所帮助:)。

Answer 3

soup=BeautifulSoup(html)
for link in soup.find_all('a'):
    print(link.get('href'))

使用美丽的汤找到了我自己的问题的答案

使用Python中的selenium打印谷歌搜索结果

3 个答案: