Selenium&EmguCV实现爬虫图片识别
概述
爬虫需要抓取网站价格，与一般抓取网页区别的是抓取内容是通过AJAX加载，并且价格是通过CSS背景图片显示的。
每一个数字对应一个样式，如'p_h57_5'
.p_h57_5 {
background: url('http://pic.c-ctrip.com/priceblur/h57/3713de5c594648529f39d031243966dd.gif') no-repeat -590px;
padding: 0 6px;
font-size: 18px;
}
数字对应的样式和对应的backgroundimg都是动态改变的，需要获取到每一个房型的房价。虽然后来有了其它渠道获取房价，这里记录一下用Selenium&Emgu抓取的方式。
流程：
1.Selenium访问网址
2.全屏截图
3.Selenium选择器获取房型等信息
4.Selenium选择器获取价格DOM元素，计算出价格元素的相对位置，截取价格图片，使用Emgu识别价格并且输出
实现
static void Main(string[] args)
{
//访问网址
ChromeOptions options = new ChromeOptions();
options.AddArguments("--start-maximized --disable-popup-blocking");
var driver = new ChromeDriver(options);
driver.Navigate().GoToUrl("http://hotels.ctrip.com/hotel/992765.html");
try
{
new WebDriverWait(driver, TimeSpan.FromSeconds(1)).Until(
ExpectedConditions.ElementExists((By.ClassName("htl_room_table")))); //表示已加载完毕
}
finally
{
}
//删除价格的¥符号
ReadOnlyCollection<IWebElement> elementsList = driver.FindElementsByCssSelector("tr[expand]");
driver.ExecuteScript(@"
var arr = document.getElementsByTagName('dfn');
for(var i=0;i<arr.length;i++){
arr[i].style.display = 'none';
}
");
//全屏截图
var image2 = GetEntereScreenshot(driver);
image2.Save(@"Z:\111.jpg");
//输出
Console.WriteLine("{0,-20}{1,-20}{2,-20}", "房型", "类型", "房价");
foreach (IWebElement _ in elementsList)
{
//var image = _.Snapshot();
//image.Save(@"Z:\" + Guid.NewGuid() + ".jpg");
//var str = ORC_((Bitmap)image);
var roomType = "";
try
{
roomType = _.FindElement(By.CssSelector(".room_unfold")).Text;
}
catch (Exception)
{
}
var roomTypeText = regRoomType.Match(roomType);
var roomTypeName = _.FindElement(By.CssSelector("span.room_type_name")).Text;
//价格元素生成图片
var image = _.FindElement(By.CssSelector("span.base_price")).SnapshotV2(image2);
//识别
var price = ORC_((Bitmap)image);
Console.WriteLine("{0,-20}{1,-20}{2,-20}", roomTypeText.Value, roomTypeName, price);
}
Console.Read();
}
图片识别方法
static Program()
{
_ocr.SetVariable("tessedit_char_whitelist", "0123456789");
}
private static Tesseract _ocr = new Tesseract(@"C:\Emgu\emgucv-windows-universal-cuda 2.9.0.1922\bin\tessdata", "eng", Tesseract.OcrEngineMode.OEM_TESSERACT_CUBE_COMBINED);
//传入图片进行识别
public static string ORC_(Bitmap img)
{
//""标示OCR识别调用失败
string re = "";
if (img == null)
return re;
else
{
Bgr drawColor = new Bgr(Color.Blue);
try
{
Image<Bgr, Byte> image = new Image<Bgr, byte>(img);
using (Image<Gray, byte> gray = image.Convert<Gray, Byte>())
{
_ocr.Recognize(gray);
Tesseract.Charactor[] charactors = _ocr.GetCharactors();
foreach (Tesseract.Charactor c in charactors)
{
image.Draw(c.Region, drawColor, 1);
}
re = _ocr.GetText();
}
return re;
}
catch (Exception ex)
{
return re;
}
}
}
Selenium内置了截图方法，只能截取浏览器中显示的内容，找到一个全屏截图的方式（内置截图+控制滚动条,图片拼接）
public static Bitmap GetEntereScreenshot(IWebDriver _driver)
{
Bitmap stitchedImage = null;
try
{
long totalwidth1 = (long)((IJavaScriptExecutor)_driver).ExecuteScript("return document.body.offsetWidth");//documentElement.scrollWidth");
long totalHeight1 = (long)((IJavaScriptExecutor)_driver).ExecuteScript("return document.body.parentNode.scrollHeight");
int totalWidth = (int)totalwidth1;
int totalHeight = (int)totalHeight1;
// Get the Size of the Viewport
long viewportWidth1 = (long)((IJavaScriptExecutor)_driver).ExecuteScript("return document.body.clientWidth");//documentElement.scrollWidth");
long viewportHeight1 = (long)((IJavaScriptExecutor)_driver).ExecuteScript("return window.innerHeight");//documentElement.scrollWidth");
int viewportWidth = (int)viewportWidth1;
int viewportHeight = (int)viewportHeight1;
// Split the Screen in multiple Rectangles
List<Rectangle> rectangles = new List<Rectangle>();
// Loop until the Total Height is reached
for (int i = 0; i < totalHeight; i += viewportHeight)
{
int newHeight = viewportHeight;
// Fix if the Height of the Element is too big
if (i + viewportHeight > totalHeight)
{
newHeight = totalHeight - i;
}
// Loop until the Total Width is reached
for (int ii = 0; ii < totalWidth; ii += viewportWidth)
{
int newWidth = viewportWidth;
// Fix if the Width of the Element is too big
if (ii + viewportWidth > totalWidth)
{
newWidth = totalWidth - ii;
}
// Create and add the Rectangle
Rectangle currRect = new Rectangle(ii, i, newWidth, newHeight);
rectangles.Add(currRect);
}
}
// Build the Image
stitchedImage = new Bitmap(totalWidth, totalHeight);
// Get all Screenshots and stitch them together
Rectangle previous = Rectangle.Empty;
foreach (var rectangle in rectangles)
{
// Calculate the Scrolling (if needed)
if (previous != Rectangle.Empty)
{
int xDiff = rectangle.Right - previous.Right;
int yDiff = rectangle.Bottom - previous.Bottom;
// Scroll
//selenium.RunScript(String.Format("window.scrollBy({0}, {1})", xDiff, yDiff));
((IJavaScriptExecutor)_driver).ExecuteScript(String.Format("window.scrollBy({0}, {1})", xDiff, yDiff));
System.Threading.Thread.Sleep(200);
}
// Take Screenshot
var screenshot = ((ITakesScreenshot)_driver).GetScreenshot();
// Build an Image out of the Screenshot
Image screenshotImage;
using (MemoryStream memStream = new MemoryStream(screenshot.AsByteArray))
{
screenshotImage = Image.FromStream(memStream);
}
// Calculate the Source Rectangle
Rectangle sourceRectangle = new Rectangle(viewportWidth - rectangle.Width, viewportHeight - rectangle.Height, rectangle.Width, rectangle.Height);
// Copy the Image
using (Graphics g = Graphics.FromImage(stitchedImage))
{
g.DrawImage(screenshotImage, rectangle, sourceRectangle, GraphicsUnit.Pixel);
}
// Set the Previous Rectangle
previous = rectangle;
}
}
catch (Exception ex)
{
// handle
}
return stitchedImage;
}
最后的是根据传入的元素和全屏截图，获取到价格元素的图片
public static Image SnapshotV2(this IWebElement element, Bitmap bitmap)
{
Size size = new Size(
Math.Min(element.Size.Width, bitmap.Width),
Math.Min(element.Size.Height, bitmap.Height));
Rectangle crop = new Rectangle(element.Location, size);
return bitmap.Clone(crop, bitmap.PixelFormat);
}
运行效果如下
