10分钟用python实现给定电影英文名，在猫眼上爬到中文名和票

&

[root@xxn maoyan]# cat cat.py
#!/usr/bin/env python
#coding:utf-8

import requests
from bs4 import BeautifulSoup

def movieurl(url):
    """
    用来获取电影的单页url地址
    """
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36",
    }
    response = requests.get(url,headers=headers,timeout=10)
    soup= BeautifulSoup(response.text,'lxml')
    href = soup.find_all('div',class_="channel-detail movie-item-title")[0]
    movieurl = "http://maoyan.com%s" % href.find('a')['href']
    return movieurl

def moveinfo(url):
    """
    得到电影的中文名,票房单位。
    如果票房单位没数据，说明票房"暂无"。
    """
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3964.2 Safari/537.36",
    }
    response = requests.get(url, headers=headers,timeout=5)
    soup = BeautifulSoup(response.text, 'lxml')
    Chinesename = soup.find('div',class_="movie-brief-container").h3.string
    try:
        boxofficeunit = soup.find_all('div',class_="movie-index-content box")[0].find('span',class_='unit').string
    except:
        boxofficeunit = 0
    return Chinesename,boxofficeunit

if __name__ == '__main__':
    Moviename = input("请输入电影的英文名字：")
    Moviename = Moviename.replace(' ','+')
    url = "http://maoyan.com/query?kw=%s&type=0" % Moviename
    Chinesename, boxofficeunit = moveinfo(movieurl(url))
    print Chinesename,boxofficeunit

&

[root@xxn maoyan]# cat maoyan.py
#!/usr/bin/env python
# coding=utf-8
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import random
from PIL import Image
import pytesseract
import os
import cat

def imagedownlod(url):
    """
    把电影单页做个截图保存,因为我们要取票房数据，所以不进行图片载入，加快速度
    """
    dcap = dict(DesiredCapabilities.PHANTOMJS)
    USER_AGENTS=[
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4882.400 QQBrowser/9.7.13059.400'
    ]
    #从USER_AGENTS列表中随机选一个浏览器头，伪装浏览器
    dcap["phantomjs.page.settings.userAgent"] = (random.choice(USER_AGENTS))
    driver = webdriver.PhantomJS(desired_capabilities=dcap)
    # 不载入图片，爬页面速度会快很多
    dcap["phantomjs.page.settings.loadImages"] = False # 禁止加载图片
    driver = webdriver.PhantomJS(desired_capabilities=dcap)
    driver.set_window_size(1366, 3245)
    driver.get(url)
    driver.save_screenshot("maoyan.png")

def crop_image(image_path,crop_path):
    """
    本来想利用webdriver来得到票房元素的位置,然后根据位置和元素大小做数字运算求出来4个参数，位置可以正常得到，但是图片大小不一，所以抠图会有问题
    所以换种方式：我把每个页面截图修改成统一大小，因为票房的位置是固定的，所以这样可以使爬虫更强健。
    """
    # 计算抠取区域的绝对坐标
    left = 668
    top = 388
    right = 668+158
    bottom = 388+54
    # 打开图片，抠取相应区域并存储
    img = Image.open(image_path)
    out = img.resize((1366, 3245),Image.ANTIALIAS) #resize image with high-quality
    out.save('maoyannew.png')
    im = Image.open('maoyannew.png')
    im = im.crop((left, top, right, bottom))
    im.save(crop_path)
    os.remove('maoyannew.png')

def words(image):
    """
    因为我们对不同大小的图片进行归一化处理，所以有些图片pytesseract不能识别数字
    所以我首先进行灰度处理，然后使用config="-psm 8 -c tessedit_char_whitelist=1234567890"这个参数
    """
    im = Image.open(image).convert('L')
    im.save(image)
    number =  pytesseract.image_to_string(Image.open(image),config="-psm 8 -c tessedit_char_whitelist=1234567890")
    os.remove(image)
    return number

if __name__ == '__main__':
    Moviename = input("请输入电影的英文名字：")
    Moviename = Moviename.replace(' ','+')
    url = "http://maoyan.com/query?kw=%s&type=0" % Moviename
    Chinesename,boxofficeunit = cat.moveinfo(cat.movieurl(url))
    imagedownlod(cat.movieurl(url))
    crop_image('maoyan.png','piaofang.png')
    print words('piaofang.png')
    os.remove('maoyan.png')

&

[root@xxn maoyan]# cat catseye.py 
#!/usr/bin/env python
# coding=utf-8
import cat
import maoyan
import sys
import os
reload(sys)
sys.setdefaultencoding('utf8')
def main():
    moviename = input("请输入电影的英文名字：")
    Moviename = moviename.replace(' ','+')
    Moviename = moviename.replace(':','%3A')
    url = "http://maoyan.com/query?kw=%s&type=0" % Moviename
    Chinesename,boxofficeunit = cat.moveinfo(cat.movieurl(url))
    if boxofficeunit == 0:
        """
        如果票房单位为0也就是不存在，那么电影票房也就是暂无，所以我们就不需要抠图识别数字了
        """
        print "您搜索的电影英文名字:" + moviename
        print "您搜索的电影中文名字:" +  Chinesename
        print "你搜索的电影票房:" + '暂无'
    else:
        maoyan.imagedownlod(cat.movieurl(url))
        maoyan.crop_image('maoyan.png','piaofang.png')
        number = maoyan.words('piaofang.png')
        print "您搜索的电影英文名字:" + moviename
        print "您搜索的电影中文名字:" +  Chinesename
        print "你搜索的电影票房:" + str(number2) + str(boxofficeunit)
        os.remove('maoyan.png')
if __name__ == '__main__':
    main()

测试：

如果你依然在编程的世界里迷茫，可以加入我们的Python学习扣qun：784758214，看看前辈们是如何学习的！交流经验！自己是一名高级python开发工程师，从基础的python脚本到web开发、爬虫、django、数据挖掘等，零基础到项目实战的资料都有整理。送给每一位python的小伙伴！分享一些学习的方法和需要注意的小细节，点击加入我们的 python学习者聚集地