add Chapter10

xxg1413 · xxg1413 · commit 4b83e9f137ac · 2016-10-13T11:31:34.000+08:00
diff --git a/Web Scraping with Python/Chapter10/javascript-redirect.py b/Web Scraping with Python/Chapter10/javascript-redirect.py
@@ -0,0 +1,30 @@
+from selenium import webdriver
+import time
+from selenium.webdriver.remote.webelement import WebElement
+from selenium.common.exceptions import StaleElementReferenceException
+
+
+'''
+我们可以用一种智能的方法来检测客户端重定向是否完成,首先从页面开始加载 时就“监视”DOM 中的一个元素,
+然后重复调用这个元素直到 Selenium
+抛出一个 StaleElementReferenceException 异常;
+也就是说,元素不在页面的 DOM 里了,说明这时 网站已经跳转:
+'''
+def waitForLoad(driver):
+    elem = driver.find_element_by_tag_name("html")
+    count = 0
+    while True:
+        count += 1
+        if count > 20:
+            print("Timing out after 10 seconds and returning")
+            return
+        time.sleep(.5)
+        try:
+            elem == driver.find_element_by_tag_name("html")
+        except StaleElementReferenceException:
+            return
+
+driver = webdriver.PhantomJS(executable_path='<Path to Phantom JS>')
+driver.get("http://pythonscraping.com/pages/javascript/redirectDemo1.html")
+waitForLoad(driver)
+print(driver.page_source)
diff --git a/Web Scraping with Python/Chapter10/selenium-basic.py b/Web Scraping with Python/Chapter10/selenium-basic.py
@@ -0,0 +1,18 @@
+from selenium import webdriver
+import time
+
+
+'''
+那些使用了 Ajax 或 DHTML 技术改变 / 加载内容的页面,可能有一些采集手段,但是用 Python 解决这个问题只有两种途径:
+直接从 JavaScript 代码里采集内容,或者用 Python 的 第三方库运行 JavaScript,直接采集你在浏览器里看到的页面
+
+PhantomJS 无头浏览器
+
+把 Selenium 和 PhantomJS 结合在一 起,就可以运行一个非常强大的网络爬虫了,
+可以处理 cookie、JavaScrip、header,以及 任何你需要做的事情。
+'''
+driver = webdriver.PhantomJS(executable_path='')
+driver.get("http://pythonscraping.com/pages/javascript/ajaxDemo.html")
+time.sleep(3)
+print(driver.find_element_by_id("content").text)
+driver.close()
diff --git a/Web Scraping with Python/Chapter10/wait-for-load.py b/Web Scraping with Python/Chapter10/wait-for-load.py
@@ -0,0 +1,11 @@
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+
+driver = webdriver.PhantomJS(executable_path='')
+driver.get("http://pythonscraping.com/pages/javascript/ajaxDemo.html")
+try:
+    element = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, "loadedButton")))
+finally:
+    print(driver.find_element_by_id("content").text)
+    driver.close()
