run.py 文件源码

def parseFanGroupPhotoPage(url):
    # ????
    driver.get(url)

    # ?? ESC?????????
    driver.find_element_by_tag_name('body').send_keys(Keys.ESCAPE)

    # ??????????????????????? 1 ??????? ??????
    time.sleep(1)

    # ????? All Photos ???????
    elm_div = driver.find_elements_by_css_selector("div._2eec div._2eea")

    # ?? list ???????
    for index, div in enumerate(elm_div):
        # ????????? div??????????
        div.click()

        # ????????????????????????FB ?????????
        # ????????????????????????????
        time.sleep(3)

        # ??????????
        elm_img = driver.find_element_by_css_selector('img.spotlight')
        image_src = elm_img.get_attribute("src")

        # ??????????????????
        p = re.compile('([0-9]+[_0-9a-zA-Z]+\.(png|jpg|gif))')
        m = p.findall(image_src)

        # ???????????????
        driver.find_element_by_css_selector('a._418x').click()

        # ????????
        try:
            image = urlopen(image_src)
            f = open( os.path.join(os.getcwd(), 'downloads/fan_group/' + m[0][0]), 'wb' )
            f.write( image.read() )
            f.close()
        except:
            print("{} cant't be read".format(m[0][0]))