4.动态HTML处理和机器图像识别

# IPython2 测试代码

# 导入 webdriver
from selenium import webdriver

# 要想调用键盘按键操作需要引入keys包
from selenium.webdriver.common.keys import Keys

# 调用环境变量指定的PhantomJS浏览器创建浏览器对象
driver = webdriver.PhantomJS()

# 如果没有在环境变量指定PhantomJS位置
# driver = webdriver.PhantomJS(executable_path="./phantomjs"))

# get方法会一直等到页面被完全加载，然后才会继续程序，通常测试会在这里选择 time.sleep(2)
driver.get("http://www.baidu.com/")

# 获取页面名为 wrapper的id标签的文本内容
data = driver.find_element_by_id("wrapper").text

# 打印数据内容
print data

# 打印页面标题 "百度一下，你就知道"
print driver.title

# 生成当前页面快照并保存
driver.save_screenshot("baidu.png")

# id="kw"是百度搜索输入框，输入字符串"长城"
driver.find_element_by_id("kw").send_keys(u"长城")

# id="su"是百度搜索按钮，click() 是模拟点击
driver.find_element_by_id("su").click()

# 获取新的页面快照
driver.save_screenshot("长城.png")

# 打印网页渲染后的源代码
print driver.page_source

# 获取当前页面Cookie
print driver.get_cookies()

# ctrl+a 全选输入框内容
driver.find_element_by_id("kw").send_keys(Keys.CONTROL,'a')

# ctrl+x 剪切输入框内容
driver.find_element_by_id("kw").send_keys(Keys.CONTROL,'x')

# 输入框重新输入内容
driver.find_element_by_id("kw").send_keys("itcast")

# 模拟Enter回车键
driver.find_element_by_id("su").send_keys(Keys.RETURN)

# 清除输入框内容
driver.find_element_by_id("kw").clear()

# 生成新的页面快照
driver.save_screenshot("itcast.png")

# 获取当前url
print driver.current_url

# 关闭当前页面，如果只有一个页面，会关闭浏览器
# driver.close()

# 关闭浏览器
driver.quit()

By ID

<div id="coolestWidgetEvah">...</div>
实现

element = driver.find_element_by_id("coolestWidgetEvah")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
element = driver.find_element(by=By.ID, value="coolestWidgetEvah")
By Class Name

<div class="cheese"><span>Cheddar</span></div><div class="cheese"><span>Gouda</span></div>
实现

cheeses = driver.find_elements_by_class_name("cheese")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
cheeses = driver.find_elements(By.CLASS_NAME, "cheese")
By Tag Name

<iframe src="..."></iframe>
实现

frame = driver.find_element_by_tag_name("iframe")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
frame = driver.find_element(By.TAG_NAME, "iframe")
By Name

<input name="cheese" type="text"/>
实现

cheese = driver.find_element_by_name("cheese")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
cheese = driver.find_element(By.NAME, "cheese")
By Link Text

<a href="http://www.google.com/search?q=cheese">cheese</a>
实现

cheese = driver.find_element_by_link_text("cheese")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
cheese = driver.find_element(By.LINK_TEXT, "cheese")
By Partial Link Text

<a href="http://www.google.com/search?q=cheese">search for cheese</a>>
实现

cheese = driver.find_element_by_partial_link_text("cheese")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
cheese = driver.find_element(By.PARTIAL_LINK_TEXT, "cheese")
By CSS

<div id="food"><span class="dairy">milk</span><span class="dairy aged">cheese</span></div>
实现

cheese = driver.find_element_by_css_selector("#food span.dairy.aged")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
cheese = driver.find_element(By.CSS_SELECTOR, "#food span.dairy.aged")
By XPath

<input type="text" name="example" />
<INPUT type="text" name="other" />
实现

inputs = driver.find_elements_by_xpath("//input")
------------------------ or -------------------------
from selenium.webdriver.common.by import By
inputs = driver.find_elements(By.XPATH, "//input")

#导入 ActionChains 类
from selenium.webdriver import ActionChains

# 鼠标移动到 ac 位置
ac = driver.find_element_by_xpath('element')
ActionChains(driver).move_to_element(ac).perform()


# 在 ac 位置单击
ac = driver.find_element_by_xpath("elementA")
ActionChains(driver).move_to_element(ac).click(ac).perform()

# 在 ac 位置双击
ac = driver.find_element_by_xpath("elementB")
ActionChains(driver).move_to_element(ac).double_click(ac).perform()

# 在 ac 位置右击
ac = driver.find_element_by_xpath("elementC")
ActionChains(driver).move_to_element(ac).context_click(ac).perform()

# 在 ac 位置左键单击hold住
ac = driver.find_element_by_xpath('elementF')
ActionChains(driver).move_to_element(ac).click_and_hold(ac).perform()

# 将 ac1 拖拽到 ac2 位置
ac1 = driver.find_element_by_xpath('elementD')
ac2 = driver.find_element_by_xpath('elementE')
ActionChains(driver).drag_and_drop(ac1, ac2).perform()

<select id="status" class="form-control valid" onchange="" name="status">
    <option value=""></option>
    <option value="0">未审核</option>
    <option value="1">初审通过</option>
    <option value="2">复审通过</option>
    <option value="3">审核不通过</option>
</select>

# 导入 Select 类
from selenium.webdriver.support.ui import Select

# 找到 name 的选项卡
select = Select(driver.find_element_by_name('status'))

# 
select.select_by_index(1)
select.select_by_value("0")
select.select_by_visible_text(u"未审核")

from selenium import webdriver
from selenium.webdriver.common.by import By
# WebDriverWait 库，负责循环等待
from selenium.webdriver.support.ui import WebDriverWait
# expected_conditions 类，负责条件出发
from selenium.webdriver.support import expected_conditions as EC

driver = webdriver.Chrome()
driver.get("http://www.xxxxx.com/loading")
try:
    # 页面一直循环，直到 id="myDynamicElement" 出现
    element = WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.ID, "myDynamicElement"))
    )
finally:
    driver.quit()

title_is
title_contains
presence_of_element_located
visibility_of_element_located
visibility_of
presence_of_all_elements_located
text_to_be_present_in_element
text_to_be_present_in_element_value
frame_to_be_available_and_switch_to_it
invisibility_of_element_located
element_to_be_clickable – it is Displayed and Enabled.
staleness_of
element_to_be_selected
element_located_to_be_selected
element_selection_state_to_be
element_located_selection_state_to_be
alert_is_present

from selenium import webdriver

driver = webdriver.Chrome()
driver.implicitly_wait(10) # seconds
driver.get("http://www.xxxxx.com/loading")
myDynamicElement = driver.find_element_by_id("myDynamicElement")

# douban.py

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time

driver = webdriver.PhantomJS()
driver.get("http://www.douban.com")

# 输入账号密码
driver.find_element_by_name("form_email").send_keys("xxxxx@xxxx.com")
driver.find_element_by_name("form_password").send_keys("xxxxxxxx")

# 模拟点击登录
driver.find_element_by_xpath("//input[@class='bn-submit']").click()

# 等待3秒
time.sleep(3)

# 生成登陆后快照
driver.save_screenshot("douban.png")

with open("douban.html", "w") as file:
    file.write(driver.page_source)

driver.quit()

#!/usr/bin/env python
# -*- coding:utf-8 -*-

# python的测试模块
import unittest
from selenium import webdriver
from bs4 import BeautifulSoup


class douyuSelenium(unittest.TestCase):
    # 初始化方法
    def setUp(self):
        self.driver = webdriver.PhantomJS()

    #具体的测试用例方法，一定要以test开头
    def testDouyu(self):
        self.driver.get('http://www.douyu.com/directory/all')
        while True:
            # 指定xml解析
            soup = BeautifulSoup(driver.page_source, 'xml')
            # 返回当前页面所有房间标题列表 和 观众人数列表
            titles = soup.find_all('h3', {'class': 'ellipsis'})
            nums = soup.find_all('span', {'class': 'dy-num fr'})

            # 使用zip()函数来可以把列表合并，并创建一个元组对的列表[(1,2), (3,4)]
            for title, num in zip(nums, titles):
                print u"观众人数:" + num.get_text().strip(), u"	房间标题: " + title.get_text().strip()
            # page_source.find()未找到内容则返回-1
            if driver.page_source.find('shark-pager-disable-next') != -1:
                break
            # 模拟下一页点击
            self.driver.find_element_by_class_name('shark-pager-next').click()

    # 退出时的清理方法
    def tearDown(self):
        print '加载完成...'
        self.driver.quit()

if __name__ == "__main__":
    unittest.main()

from selenium import webdriver

driver = webdriver.PhantomJS()
driver.get("https://www.baidu.com/")

# 给搜索输入框标红的javascript脚本
js = "var q=document.getElementById("kw");q.style.border="2px solid red";"

# 调用给搜索输入框标红js脚本
driver.execute_script(js)

#查看页面快照
driver.save_screenshot("redbaidu.png")

#js隐藏元素，将获取的图片元素隐藏
img = driver.find_element_by_xpath("//*[@id='lg']/img")
driver.execute_script('$(arguments[0]).fadeOut()',img)

# 向下滚动到页面底部
driver.execute_script("$('.scroll_top').click(function(){$('html,body').animate({scrollTop: '0px'}, 800);});")

#查看页面快照
driver.save_screenshot("nullbaidu.png")

driver.quit()

# 
from selenium import webdriver
import time

driver = webdriver.PhantomJS()
driver.get("https://movie.douban.com/typerank?type_name=剧情&type=11&interval_id=100:90&action=")

# 向下滚动10000像素
js = "document.body.scrollTop=10000"
#js="var q=document.documentElement.scrollTop=10000"
time.sleep(3)

#查看页面快照
driver.save_screenshot("douban.png")

# 执行JS语句
driver.execute_script(js)
time.sleep(10)

#查看页面快照
driver.save_screenshot("newdouban.png")

driver.quit()

import pytesseract
from PIL import Image

image = Image.open('test.jpg')
text = pytesseract.image_to_string(image)
print text

This is some text, written in Arial, that will be read by
Tesseract. Here are some symbols: !@#$%"&*()

from PIL import Image 
import subprocess

def cleanFile(filePath, newFilePath): 
    image = Image.open(filePath)

    # 对图片进行阈值过滤,然后保存
    image = image.point(lambda x: 0 if x<143 else 255)     
    image.save(newFilePath)

    # 调用系统的tesseract命令对图片进行OCR识别     
    subprocess.call(["tesseract", newFilePath, "output"])

    # 打开文件读取结果
    file = open("output.txt", 'r')     
    print(file.read()) 
    file.close()

cleanFile("text2.jpg", "text2clean.png")

import time
from urllib.request import urlretrieve 
import subprocess
from selenium import webdriver
#创建新的Selenium driver
driver = webdriver.PhantomJS()

# 用Selenium试试Firefox浏览器:
# driver = webdriver.Firefox()

driver.get("http://www.amazon.com/War-Peace-Leo-Nikolayevich-Tolstoy/dp/1427030200")
# 单击图书预览按钮 driver.find_element_by_id("sitbLogoImg").click() imageList = set()
# 等待页面加载完成
time.sleep(5)
# 当向右箭头可以点击时,开始翻页
while "pointer" in driver.find_element_by_id("sitbReaderRightPageTurner").get_attribute("style"):
    driver.find_element_by_id("sitbReaderRightPageTurner").click()
    time.sleep(2)
    # 获取已加载的新页面(一次可以加载多个页面,但是重复的页面不能加载到集合中) 
    pages = driver.find_elements_by_xpath("//div[@class='pageImage']/div/img") 
    for page in pages:
        image = page.get_attribute("src")
        imageList.add(image)
driver.quit()

# 用Tesseract处理我们收集的图片URL链接 
for image in sorted(imageList):
    # 保存图片
    urlretrieve(image, "page.jpg")
    p = subprocess.Popen(["tesseract", "page.jpg", "page"], stdout=subprocess.PIPE,stderr=subprocess.PIPE)
    f = open("page.txt", "r")
    p.wait() print(f.read())

 "A word of friendly advice, mon
     cher. Be off as soon as you can,
     that's all I have to tell you. Happy
     he who has ears to hear. Good-by,
     my dear fellow. Oh, by the by!" he
     shouted through the doorway after
     Pierre, "is it true that the countess
     has fallen into the clutches of the
     holy fathers of the Society of je-
     sus?"

     Pierre did not answer and left Ros-
     topchin's room more sullen and an-
     gry than he had ever before shown
     himself.

   WEI' nrrd Peace
   Len Nlkelayevldu Iolfluy
   Readmg shmdd be ax
   wlnvame asnossxble Wenfler
   an mm m our cram: Llhvary
    - Leo Tmsloy was a Russian rwovelwst
    I and moval phflmopher med lur
    A ms Ideas 01 nonviolenx reswslance m 5 We range     0, "and"

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import requests
import time
import pytesseract
from PIL import Image
from bs4 import BeautifulSoup

def captcha(data):
    with open('captcha.jpg','wb') as fp:
        fp.write(data)
    time.sleep(1)
    image = Image.open("captcha.jpg")
    text = pytesseract.image_to_string(image)
    print "机器识别后的验证码为：" + text
    command = raw_input("请输入Y表示同意使用，按其他键自行重新输入：")
    if (command == "Y" or command == "y"):
        return text
    else:
        return raw_input('输入验证码：')

def zhihuLogin(username,password):

    # 构建一个保存Cookie值的session对象
    sessiona = requests.Session()
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0'}

    # 先获取页面信息，找到需要POST的数据（并且已记录当前页面的Cookie）
    html = sessiona.get('https://www.zhihu.com/#signin', headers=headers).content

    # 找到 name 属性值为 _xsrf 的input标签，取出value里的值
    _xsrf = BeautifulSoup(html ,'lxml').find('input', attrs={'name':'_xsrf'}).get('value')

    # 取出验证码，r后面的值是Unix时间戳,time.time()
    captcha_url = 'https://www.zhihu.com/captcha.gif?r=%d&type=login' % (time.time() * 1000)
    response = sessiona.get(captcha_url, headers = headers)


    data = {
        "_xsrf":_xsrf,
        "email":username,
        "password":password,
        "remember_me":True,
        "captcha": captcha(response.content)
    }

    response = sessiona.post('https://www.zhihu.com/login/email', data = data, headers=headers)
    print response.text

    response = sessiona.get('https://www.zhihu.com/people/maozhaojun/activities', headers=headers)
    print response.text


if __name__ == "__main__":
    #username = raw_input("username")
    #password = raw_input("password")
    zhihuLogin('xxxx@qq.com','ALAxxxxIME')