Python爬虫——实战三：爬取苏宁易购的商品价格

苏宁易购的商品价格请求URL为

https://pas.suning.com/nspcsale_0_000000000152709847_000000000152709847_0000000000_10_010_0100101_20268_1000000_9017_10106_Z001___R0104002_46.5_0_.html?callback=pcData&_=1503023077300

价格在返回的数据中结构为：pcData[0]–>data–>price–>saleInfo–>0–>promotionPrice。

但是上面的URL很难看出是什么结构，并且也不知道需要的信息应该从哪里获得。所以直接访问URL这种方法不具备通用性。

"""
from PySide.QtGui import *
from PySide.QtWebKit import *
from PySide.QtCore import *
"""
from PySide import *
import time

class BrowserRender(QWebView):
    def __init__(self, show=True):
        self.app = QApplication(sys.argv)
        QWebView.__init__(self)
        if show:
            self.show()

    def download(self, url, timeout=60):
        loop = QEventLoop()
        timer = QTimer()
        timer.setSingleShot(True)
        timer.timeout.connect(loop.quit)
        self.loadFinished.connect(loop.quit)
        self.load(QUrl(url))
        timer.start(timeout * 1000)
        loop.exec_()
        if timer.isActive():
            timer.stop()
            return self.html()
        else:
            print "Request time out: " + url

    def html(self):
        return self.page().mainFrame().toHtml()

    def find(self, pattern):
        return self.page().mainFrame().findAllElements(pattern)

    def attr(self, pattern, name, value):
        for e in self.find(pattern):
            e.setAttribute(name, value)

    def text(self, pattern, value):
        for e in self.find(pattern):
            e.setPlainText(value)

    def click(self, pattern):
        for e in self.find(patter):
            e.evaluateJavaScript("this.click()")

    """
    def wait_load(self, pattern, timeout=60):
        deadline = time.time() + timeout
        while time.time() < deadline:
            self.app.processEvents()
            matches = self.find(pattern)
            if matches:
                return matches
        print "wait load time out"
    """
    9
if __name__=="__main__":
    br = BrowserRender()
    br.download("https://product.suning.com/0000000000/152709847.html?srcpoint=index3_homepage1_32618213038_prod02")
    price = br.find("span.mainprice" )  
    print price[0].toPlainText().strip()