問題描述

python 隊列 queue在傳遞數(shù)據(jù)的時候編碼問題

可以看到 單線程的可以下載

多線程的 使用queue就。。

問題出現(xiàn)的環(huán)境背景及自己嘗試過哪些方法

python

相關(guān)代碼

// 請把代碼文本粘貼到下方（請勿用圖片代替代碼）

# -*- coding:utf-8 -*-

import re
import os
import Queue
import urllib
import requests
import threading
from lxml import etree

class Procuder(threading.Thread):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'
    }

    #*args,**kwargs  任意未知參數(shù)，任意關(guān)鍵字參數(shù)
    def __init__(self,page_queue,img_queue,*args,**kwargs):
        super(Procuder, self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.img_queue = img_queue

    def run(self):
        while True:
            if self.page_queue.empty():
                break
            url = self.page_queue.get()
            self.parse_page(url)

    def parse_page(self,url):
        response = requests.get(url,headers=self.headers)
        text = response.text
        html = etree.HTML(text)
        imgs = html.xpath("http://div[@class='page-content text-center']//img[@class!='gif']")
        for img in imgs:
            img_url = img.get('data-original')
            alt = img.get('alt')
            alt = re.sub(r'[\?？\.，。！!]','',alt)
            suffix = os.path.splitext(img_url)[1]
            filename = alt+suffix
            self.img_queue.put((img_url,filename))

class Consumer(threading.Thread):
    def __init__(self,page_queue,img_queue,*args,**kwargs):
        super(Consumer, self).__init__(*args,**kwargs)
        self.page_queue = page_queue
        self.img_queue = img_queue
    def run(self):
        while True:
            if self.page_queue.empty() and self.img_queue.empty():
                break
            img_url,filename = self.img_queue.get()
            urllib.urlretrieve(img_url,'imagess/'+filename)
            print filename+"     下載完成！"


def main():
    page_queue = Queue.Queue(100)
    img_queue = Queue.Queue(1000)
    for x in range(1,101):
        url = "http://www.doutula.com/photo/list/?page=%d" % x
        page_queue.put(url)

    for x in range(5):
        t = Procuder(page_queue,img_queue)
        t.start()
    for x in range(5):
        t = Consumer(page_queue,img_queue)
        t.start()



if __name__ == '__main__':
    main()

你期待的結(jié)果是什么？實(shí)際看到的錯誤信息又是什么？

這里的filename亂碼編碼問題怎么解決