python实践项目（十一）

1、从图像网站下载

       编写一个程序，访问图像共享网站，如 Flickr 或 Imgur，查找一个类型的照片，然后下载所有查询结果的图像。可以编写一个程序，访问任何具有查找功能的图像网站。 

#-*-coding:utf-8-*-
import os
import requests
import bs4

baseUrl = 'http://imgur.com'
dirName = 'image'
os.makedirs(dirName, exist_ok=True)
# 搜索参数
url = baseUrl + '/search/score?q=' + 'movie'
response = requests.get(url)
response.raise_for_status()
soup = bs4.BeautifulSoup(response.text, "html.parser")
imageUrls = soup.select(".image-list-link img")
if not imageUrls:
    print('Could not find image.')
else:
    for imageUrl in imageUrls:
        downloadUrl = imageUrl.get('src')
        print("Download image %s..." % downloadUrl)
        split = downloadUrl.split('/')
        fileName = os.path.basename(split[len(split) - 1])
        filePath = os.path.join(dirName, fileName)
        print("FilePath is  %s..." % filePath)
        if not os.path.exists(filePath):
            imageStream = requests.get('http:' + downloadUrl)
            imageStream.raise_for_status()
            imageFile = open(filePath, 'wb')
            for chunk in imageStream.iter_content(100000):
                imageFile.write(chunk)

2、2048游戏

      2048 是一个简单的游戏，通过箭头向上、下、左、右移动滑块，让滑块合并。实际上，你可以通过一遍一遍的重复“上、右、下、左”模式，获得相当高的分数。编写一个程序，打开 https://gabrielecirulli.github.io/2048/上的游戏，不断发送上、右、下、左按键，自动玩游戏。

#-*-coding:utf-8-*-
from selenium import webdriver
from selenium.webdriver.common.keys import Keys

browser = webdriver.Firefox()
url = 'https://gabrielecirulli.github.io/2048/'
browser.get(url)
game_elem = browser.find_element_by_class_name('game-container')
while True:
    retry_elem = browser.find_element_by_class_name('retry-button')
    # new game
    if retry_elem.text == 'Try again':
        retry_elem.click()
        game_elem = browser.find_element_by_class_name('game-container')
    game_elem.send_keys(Keys.UP)
    game_elem.send_keys(Keys.RIGHT)
    game_elem.send_keys(Keys.DOWN)
    game_elem.send_keys(Keys.LEFT)

3、链接验证

      编写一个程序，对给定的网页 URL，下载该页面所有链接的页面。程序应该标记出所有具有 404“Not Found”状态码的页面，将它们作为坏链接输出。

#-*-coding:utf-8-*-
import requests
import bs4

url = 'http://ifeve.com/'
response = requests.get(url)
soup = bs4.BeautifulSoup(response.text, "html.parser")
a_list = soup.select('a')
for a in a_list:
    a_url = a.get('href')
    try:
        response = requests.get(a_url)
        if response.status_code == requests.codes.not_found:
            print("Page %s is broken link" % a_url)
        else:
            print("Page %s is other type link" % a_url)
        response.raise_for_status()
    except:
        print("Page %s is Error" % a_url)