本文為使用python3通過豆瓣演員id下載演員圖片

1. 該類為讀取Excel表格數(shù)據(jù)

"""
-------------------------------------------------
   File Name：     Do_Excel
   Description :
   Author :       小魚
   date：          2018/3/19
-------------------------------------------------
   Change Activity:
                   2018/3/19:
-------------------------------------------------
"""
__author__ = '小魚'

from openpyxl import load_workbook

class DoExcel:

    def __init__(self,excelpath):
        self.wb = load_workbook(excelpath)
        self.excelpath = excelpath
        self.sh_id = self.wb.get_sheet_by_name("id")
        self.sh_move = self.wb.get_sheet_by_name("move")

    def get_id(self):
        l=[]
        for i in range(1,self.sh_id.max_row+1):
            id = self.sh_id.cell(row=i,column=1).value
            l.append(id)
        return l

"""
-------------------------------------------------
   File Name：     douban_spider2
   Description :
   Author :       小魚
   date：          2018/3/20
-------------------------------------------------
   Change Activity:
                   2018/3/20:
-------------------------------------------------
"""
import urllib

__author__ = '小魚'
from Do_Excel import DoExcel
import requests
import re
import time
from urllib.request import urlretrieve, urlcleanup
import os

class DouBan_Spider():
    def auto_down(self,url, filename):
        try:
            urlretrieve(url, filename)
        except :
            print("重新下載")
            urlcleanup()
            return self.auto_down(url,filename)
    def judge_ban(self, id):
        move_url = "https://movie.douban.com/celebrity/%s" % id
        try:
            response = requests.get(url=move_url, timeout=30)
        except:
                time.sleep(10)
                print('請求多次仍然超時，請檢查')
                return self.judge_ban(id)
        html = response.text
        if html.find(r'檢測到有異常請求從你的') != -1:
            print("被ban了，需要等待10s繼續(xù)請求")
            time.sleep(10)
            return self.judge_ban(id)
        else:
            picture = r'''title="點擊看大圖"
                src="(.*?)">'''
            imgre = re.compile(picture)
            imgrelist = imgre.findall(html)
        if imgrelist!=[]:
            self.auto_down(imgrelist[0],os.getcwd()+'/picture/%s.jpg'%id)
            print("當(dāng)前演員id為:" + str(id))
            print('.......................')
        else:
            print("該演員沒有頭像")
            print('.......................')
if __name__ == '__main__':
    m = DouBan_Spider()
    do_excel = DoExcel('move_id.xlsx')
    id_list = do_excel.get_id()
    count = 0
    for m_id in id_list:
        count += 1
        print('當(dāng)前下載了' + str(count) + '張')
        m.judge_ban(m_id)

備注：

• 該腳本實現(xiàn)了通過演員id下載演員頭像的功能，如果被ban，則過10秒重新請求
• 讀取Excel表格最大行數(shù)max_row，應(yīng)該+1，不然無法取到最后一行

2.結(jié)果如圖

image.png