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

import os
import re
import urllib
import json
import socket
import urllib.request
import urllib.parse
import urllib.error
# 設置超時
import time

timeout = 5
socket.setdefaulttimeout(timeout)


class Crawler:
    # 睡眠時長
    __time_sleep = 0.1
    __amount = 0
    
 
__start_amount = 0
    __counter = 0

    # 獲取圖片url內容等
    # t 下載圖片時間間隔
    def __init__(self, t=0.1):
        self.time_sleep = t

    # 開始獲取
    def __getImages(self, word=‘美女‘):
        search = urllib.parse.quote(word)
        # pn int 圖片數
        pn = self.__start_amount
        while pn < self.__amount
 
:

            headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0‘}
            url = ‘http://image.baidu.com/search/avatarjson?tn=resultjsonavatarnew&ie=utf-8&word=‘ + search + ‘&cg=girl&pn=‘ + str(
                pn) + ‘&rn=60&itg=0&z=0&fr=&width=&height=&lm=-1&ic=0&s=0&st=-1&gsm=1e0000001e
 
‘
            # 設置header防ban
            try:
                time.sleep(self.time_sleep)
                req = urllib.request.Request(url=url, headers=headers)
                page = urllib.request.urlopen(req)
                data = page.read().decode(‘utf8‘)
            except UnicodeDecodeError as e:
                print(‘-----UnicodeDecodeErrorurl:‘, url)
            except urllib.error.URLError as e:
                print("-----urlErrorurl:", url)
            except socket.timeout as e:
                print("-----socket timout:", url)
            else:
                # 解析json
                json_data = json.loads(data)
                self.__saveImage(json_data, word)
                # 讀取下一頁
                print("下載下一頁")
                pn += 60
            finally:
                page.close()
        print("下載任務結束")
        return

    # 保存圖片
    def __saveImage(self, json, word):

        if not os.path.exists("./" + word):
            os.mkdir("./" + word)
        # 判斷名字是否重復，獲取圖片長度
        self.__counter = len(os.listdir(‘./‘ + word)) + 1
        for info in json[‘imgs‘]:
            try:
                if self.__downloadImage(info, word) == False:
                    self.__counter -= 1
            except urllib.error.HTTPError as urllib_err:
                print(urllib_err)
                pass
            except Exception as err:
                time.sleep(1)
                print(err);
                print("產生未知錯誤，放棄保存")
                continue
            finally:
                print("小黃圖+1,已有" + str(self.__counter) + "張小黃圖")
                self.__counter += 1
        return

    # 下載圖片
    def __downloadImage(self, info, word):
        time.sleep(self.time_sleep)
        fix = self.__getFix(info[‘objURL‘])
        urllib.request.urlretrieve(info[‘objURL‘], ‘./‘ + word + ‘/‘ + str(self.__counter) + str(fix))

    # 獲取後綴名
    def __getFix(self, name):
        m = re.search(r‘\.[^\.]*$‘, name)
        if m.group(0) and len(m.group(0)) <= 5:
            return m.group(0)
        else:
            return ‘.jpeg‘

    # 獲取前綴
    def __getPrefix(self, name):
        return name[:name.find(‘.‘)]

    # page_number 需要抓取數據頁數 總抓取圖片數量為 頁數x60
    # start_page 起始頁數
    def start(self, word, spider_page_num=1, start_page=1):
        self.__start_amount = (start_page - 1) * 60
        self.__amount = spider_page_num * 60 + self.__start_amount
        self.__getImages(word)


crawler = Crawler(0.05)
crawler.start(‘科幻‘, 1, 5)
#crawler.start(‘二次元 性感‘, 3, 3)
# crawler.start(‘帥哥‘, 5)

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from time import sleep
userid=input(‘username‘)
passid=input(‘password‘)
sendtxt="hello"#郵件內容
sendto=input(‘sendto‘)
#打開Firefox
driver = webdriver.Firefox()
driver.get(‘http://mail.10086.cn/‘)#郵箱網址
#填寫用戶名
emailElem = driver.find_element_by_id(‘txtUser‘)
emailElem.send_keys(userid)#用戶名
#填寫密碼
passwordElem = driver.find_element_by_id(‘txtPass‘)
passwordElem.send_keys(passid)#密碼
passwordElem.submit()
#寫郵件
sleep(10)
write=driver.find_element_by_id(‘btn_compose‘)
write.click()
sleep(10)
iframe_xpath = "//iframe[contains(@id,‘compose_‘)]"
#寫信頁所在的iframe的xpath路徑，通過火狐瀏覽器的firebug插件可以查看到是在一個iframe的頁面內
iframe = driver.find_element_by_xpath(iframe_xpath)
driver.switch_to_frame(iframe)
sleep(5)
driver.find_element_by_id(‘toContaine‘).send_keys(sendto)
driver.find_element_by_id(‘txtSubject‘).send_keys(sendtxt)
driver.find_element_by_id(‘topSend‘).click()

python編程快速上手之第10章實踐項目參考答案(11.11.2)