Python Selenium wait for several elements to load(Python Selenium等待几个元素加载)

问题描述

我有一个由Ajax动态加载的列表。 首先，在加载时，代码是这样的：

<ul><li class="last"><a class="loading" href="#"><ins>&nbsp;</ins>Загрузка...</a></li></ul>

加载列表时，所有的li和a都会更改。而且总是超过1里。 如下所示：

<ul class="ltr">
<li id="t_b_68" class="closed" rel="simple">
<a id="t_a_68" href="javascript:void(0)">Category 1</a>
</li>
<li id="t_b_64" class="closed" rel="simple">
<a id="t_a_64" href="javascript:void(0)">Category 2</a>
</li>
...

我需要检查列表是否加载，所以我检查它是否有几个li。

到目前为止我已尝试：

1)自定义等待条件

class more_than_one(object):
    def __init__(self, selector):
        self.selector = selector

    def __call__(self, driver):
        elements = driver.find_elements_by_css_selector(self.selector)
        if len(elements) > 1:
            return True
        return False

.

try:
        query = WebDriverWait(driver, 30).until(more_than_one('li'))
    except:
        print "Bad crap"
    else:
        # Then load ready list

2)基于FIND_ELEMENTS_BY的自定义函数

def wait_for_several_elements(driver, selector, min_amount, limit=60):
    """
    This function provides awaiting of <min_amount> of elements found by <selector> with
    time limit = <limit>
    """
    step = 1   # in seconds; sleep for 500ms
    current_wait = 0
    while current_wait < limit:
        try:
            print "Waiting... " + str(current_wait)
            query = driver.find_elements_by_css_selector(selector)
            if len(query) > min_amount:
                print "Found!"
                return True
            else:
                time.sleep(step)
                current_wait += step
        except:
            time.sleep(step)
            current_wait += step

    return False

这不起作用，因为驱动程序(传递给此函数的当前元素)在DOM中丢失。UL未更改，但由于某些原因，Selenium找不到它。

3)异常等待。这太糟糕了，因为有些列表是立即加载的，而有些列表需要10秒以上的时间才能加载。如果我使用这种技术，我每次都要等待最长时间，这对我的情况非常不利。

4)另外，我无法正确等待带有XPath的子元素。此选项只期望出现ul。

try:
    print "Going to nested list..."
    #time.sleep(WAIT_TIME)
    query = WebDriverWait(driver, 30).until(EC.presence_of_element_located((By.XPATH, './/ul')))
    nested_list = child.find_element_by_css_selector('ul')

请告诉我正确的方法以确保为指定元素加载了多个继承人元素。

附注。所有这些检查和搜索都应与当前元素相关。

css

记住先生和Arran的注释，我在推荐答案选择器上完全遍历了我的列表。棘手的部分是关于我自己的列表结构和标记(更改类等)，以及如何在飞翔上创建所需的选择器并在遍历过程中将它们保存在内存中。

我通过搜索任何不是加载状态的元素来处理等待几个元素。您也可以使用"：nth-Child"选择器，如下所示：

#in for loop with enumerate for i    
selector.append(' > li:nth-child(%i)' % (i + 1))  # identify child <li> by its order pos

这是我的硬注释代码解决方案，例如：

def parse_crippled_shifted_list(driver, frame, selector, level=1, parent_id=0, path=None):
    """
    Traversal of html list of special structure (you can't know if element has sub list unless you enter it).
    Supports start from remembered list element.

    Nested lists have classes "closed" and "last closed" when closed and "open" and "last open" when opened (on <li>).
    Elements themselves have classes "leaf" and "last leaf" in both cases.
    Nested lists situate in <li> element as <ul> list. Each <ul> appears after clicking <a> in each <li>.
    If you click <a> of leaf, page in another frame will load.

    driver - WebDriver; frame - frame of the list; selector - selector to current list (<ul>);
    level - level of depth, just for console output formatting, parent_id - id of parent category (in DB),
    path - remained path in categories (ORM objects) to target category to start with.
    """

    # Add current level list elements
    # This method selects all but loading. Just what is needed to exclude.
    selector.append(' > li > a:not([class=loading])')

    # Wait for child list to load
    try:
        query = WebDriverWait(driver, WAIT_LONG_TIME).until(
            EC.presence_of_all_elements_located((By.CSS_SELECTOR, ''.join(selector))))

    except TimeoutException:
        print "%s timed out" % ''.join(selector)

    else:
        # List is loaded
        del selector[-1]  # selector correction: delete last part aimed to get loaded content
        selector.append(' > li')

        children = driver.find_elements_by_css_selector(''.join(selector))  # fetch list elements

        # Walk the whole list
        for i, child in enumerate(children):

            del selector[-1]  # delete non-unique li tag selector
            if selector[-1] != ' > ul' and selector[-1] != 'ul.ltr':
                del selector[-1]

            selector.append(' > li:nth-child(%i)' % (i + 1))  # identify child <li> by its order pos
            selector.append(' > a')  # add 'li > a' reference to click

            child_link = driver.find_element_by_css_selector(''.join(selector))

            # If we parse freely further (no need to start from remembered position)
            if not path:
                # Open child
                try:
                    double_click(driver, child_link)
                except InvalidElementStateException:
                        print "

ERROR
", InvalidElementStateException.message(), '

'
                else:
                    # Determine its type
                    del selector[-1]  # delete changed and already useless link reference
                    # If <li> is category, it would have <ul> as child now and class="open"
                    # Check by class is priority, because <li> exists for sure.
                    current_li = driver.find_element_by_css_selector(''.join(selector))

                    # Category case - BRANCH
                    if current_li.get_attribute('class') == 'open' or current_li.get_attribute('class') == 'last open':
                        new_parent_id = process_category_case(child_link, parent_id, level)  # add category to DB
                        selector.append(' > ul')  # forward to nested list
                        # Wait for nested list to load
                        try:
                            query = WebDriverWait(driver, WAIT_LONG_TIME).until(
                                EC.presence_of_all_elements_located((By.CSS_SELECTOR, ''.join(selector))))

                        except TimeoutException:
                            print "	" * level,  "%s timed out (%i secs). Failed to load nested list." %
                                                 ''.join(selector), WAIT_LONG_TIME
                        # Parse nested list
                        else:
                            parse_crippled_shifted_list(driver, frame, selector, level + 1, new_parent_id)

                    # Page case - LEAF
                    elif current_li.get_attribute('class') == 'leaf' or current_li.get_attribute('class') == 'last leaf':
                        process_page_case(driver, child_link, level)
                    else:
                        raise Exception('Damn! Alien class: %s' % current_li.get_attribute('class'))

            # If it's required to continue from specified category
            else:
                # Check if it's required category
                if child_link.text == path[0].name:
                    # Open required category
                    try:
                        double_click(driver, child_link)

                    except InvalidElementStateException:
                            print "

ERROR
", InvalidElementStateException.msg, '

'

                    else:
                        # This element of list must be always category (have nested list)
                        del selector[-1]  # delete changed and already useless link reference
                        # If <li> is category, it would have <ul> as child now and class="open"
                        # Check by class is priority, because <li> exists for sure.
                        current_li = driver.find_element_by_css_selector(''.join(selector))

                        # Category case - BRANCH
                        if current_li.get_attribute('class') == 'open' or current_li.get_attribute('class') == 'last open':
                            selector.append(' > ul')  # forward to nested list
                            # Wait for nested list to load
                            try:
                                query = WebDriverWait(driver, WAIT_LONG_TIME).until(
                                    EC.presence_of_all_elements_located((By.CSS_SELECTOR, ''.join(selector))))

                            except TimeoutException:
                                print "	" * level, "%s timed out (%i secs). Failed to load nested list." %
                                                     ''.join(selector), WAIT_LONG_TIME
                            # Process this nested list
                            else:
                                last = path.pop(0)
                                if len(path) > 0:  # If more to parse
                                    print "	" * level, "Going deeper to: %s" % ''.join(selector)
                                    parse_crippled_shifted_list(driver, frame, selector, level + 1,
                                                                parent_id=last.id, path=path)
                                else:  # Current is required
                                    print "	" * level,  "Returning target category: ", ''.join(selector)
                                    path = None
                                    parse_crippled_shifted_list(driver, frame, selector, level + 1, last.id, path=None)

                        # Page case - LEAF
                        elif current_li.get_attribute('class') == 'leaf':
                            pass
                else:
                    print "dummy"

        del selector[-2:]

这篇关于Python Selenium等待几个元素加载的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持编程学习网！