第七色在线视频,2021少妇久久久久久久久久,亚洲欧洲精品成人久久av18,亚洲国产精品特色大片观看完整版,孙宇晨将参加特朗普的晚宴

為了賬號安全，請及時綁定郵箱和手機立即綁定

代碼出現問題

import?requests,time,random
from?lxml?import?etree
from?multiprocessing?import?Pool
from?threading?import?Thread
from?urllib?import?request
user_agent?=?[
???????"Mozilla/5.0?(compatible;?Baiduspider/2.0;?+http://www.baidu.com/search/spider.html)",
???????"Mozilla/4.0?(compatible;?MSIE?6.0;?Windows?NT?5.1;?SV1;?AcooBrowser;?.NET?CLR?1.1.4322;?.NET?CLR?2.0.50727)",
???????"Mozilla/4.0?(compatible;?MSIE?7.0;?Windows?NT?6.0;?Acoo?Browser;?SLCC1;?.NET?CLR?2.0.50727;?Media?Center?PC?5.0;?.NET?CLR?3.0.04506)",
???????"Mozilla/4.0?(compatible;?MSIE?7.0;?AOL?9.5;?AOLBuild?4337.35;?Windows?NT?5.1;?.NET?CLR?1.1.4322;?.NET?CLR?2.0.50727)",
???????"Mozilla/5.0?(Windows;?U;?MSIE?9.0;?Windows?NT?9.0;?en-US)",
???????"Mozilla/5.0?(compatible;?MSIE?9.0;?Windows?NT?6.1;?Win64;?x64;?Trident/5.0;?.NET?CLR?3.5.30729;?.NET?CLR?3.0.30729;?.NET?CLR?2.0.50727;?Media?Center?PC?6.0)",
]
headers={"User-Agent":?random.choice(user_agent)}
filk=r'C:\Users\25063\Desktop\音樂'
class?jiuku(Thread):
????url='http://www.9ku.com/x1/music/by_new.php?act=t_m_hits&page='
????def?__init__(self,star_page,end_page):
????????super(jiuku,self).__init__()
????????self.star_page=star_page
????????self.end_page=end_page
????????self.music_list=[]
????def?get_one_html(self,page):
????????'''獲取一個頁面的html'''
????????now_url=self.url+str(page)
????????print(now_url)
????????r=requests.get(now_url,headers=headers)
????????return?r.text
????def?get_many_url(self,html):
????????'''根據html解析得到音樂的url'''
????????xml=etree.HTML(html)
????????music_url=xml.xpath('//ol/li/a/@href')
????????for?urls?in?music_url:
????????????url='http://www.9ku.com'+urls
????????????self.music_list.append(url)
????????return?self.music_list
????def?down_one_music(self,url):
????????r=requests.get(url,headers=headers)
????????xml=etree.HTML(r.text)
????????title=xml.xpath('//div[@class="playingTit"]/h1/text()')[0]
????????singer=xml.xpath('//div[@class="playingTit"]/h2/a/text()')[0]
????????music=title+'-'+singer
????????music_id=url.split('/')[-1].split('.')[0]#獲取音樂的id
????????print('正在下載:{}'.format(music))
????????music_url='http://mp3.9ku.com/m4a/{}.m4a'.format(music_id)
????????request.urlretrieve(music_url,filk+music+'.mp3')
????def?run(self):
????????for?page?in?range(self.star_page,self.end_page):
????????????time.sleep(1)
????????????html=self.get_one_html(page)
????????????music_list=self.get_many_url(html)
????????????pool=Pool()
????????????'''使用多進程進行下載，但是出錯'''
????????????pool.map(self.down_one_music,[url?for?url?in?music_list])
????????????#?for?i?in?music_list:
????????????#?????self.down_one_music(i)
def?main():
????number?=?int(input('請輸入要爬取的頁數:'))
????if?number?<=?4:
????????a?=?[i?for?i?in?range(0,?number+1)]
????????a1_min?=?min(a)
????????a1_max?=?max(a)
????????down?=?jiuku(a1_min,?a1_max)
????????down.start()
????else:
????????a?=?[i?for?i?in?range(0,?number)]
????????d?=?number?/?4??#?得到的數是一個浮點數
????????e?=?int(d)??#?這一步是對浮點數變?yōu)檎麛?，程序會將整數后面的小數全部清理這是的e就會小于d
????????if?d?>?e:??#?判斷如果e小于b則就需要將每個小列表中的數量為e+1
????????????step?=?e?+?1
????????????b?=?[a[i:i?+?step]?for?i?in?range(0,?len(a),?step)]
????????else:
????????????step?=?e
????????????b?=?[a[i:i?+?step]?for?i?in?range(0,?len(a),?step)]
????????a1_max?=?max(b[0])
????????a1_min?=?min(b[0])
????????a2_max?=?max(b[1])
????????a2_min?=?min(b[1])
????????a3_max?=?max(b[2])
????????a3_min?=?min(b[2])
????????a4_max?=?max(b[3])
????????a4_min?=?min(b[3])
????????down?=?jiuku(a1_min,?a1_max)
????????down.start()
????????down1?=?jiuku(a2_min,?a2_max)
????????down1.start()
????????down2?=?jiuku(a3_min,?a3_max)
????????down2.start()
????????down3?=?jiuku(a4_min,?a4_max)
????????down3.start()
if?__name__?==?'__main__':
????main()
#?def?main():
#?????a=int(input('da:'))
#?????d=int(input('agd:'))
#?????down=jiuku(a,d)
#?????down.run()
#?if?__name__?==?'__main__':
#?????main()

上面的代碼 我是打算使用多進程家多線程進行下載但是出錯 為什么?

正在回答

4 回答

1、線程如果使用Thread，在子線程中再用進程池Pool?就會報錯，原理不太清楚，可能需要老師來回答了，換用Process?就沒問題了；

2、這個音樂的頁面應該是從page=1開始的，所以我稍微改了一下入參。你可以看一下。

0 回復 有任何疑惑可以回復我~ 
import?requests,?time,?random
from?lxml?import?etree
from?multiprocessing?import?Pool
from?multiprocessing?import?Process
from?urllib?import?request
from?urllib?import?error

user_agent?=?[
????"Mozilla/5.0?(compatible;?Baiduspider/2.0;?+http://www.baidu.com/search/spider.html)",
????"Mozilla/4.0?(compatible;?MSIE?6.0;?Windows?NT?5.1;?SV1;?AcooBrowser;?.NET?CLR?1.1.4322;?.NET?CLR?2.0.50727)",
????"Mozilla/4.0?(compatible;?MSIE?7.0;?Windows?NT?6.0;?Acoo?Browser;?SLCC1;?.NET?CLR?2.0.50727;?Media?Center?PC?5.0;?.NET?CLR?3.0.04506)",
????"Mozilla/4.0?(compatible;?MSIE?7.0;?AOL?9.5;?AOLBuild?4337.35;?Windows?NT?5.1;?.NET?CLR?1.1.4322;?.NET?CLR?2.0.50727)",
????"Mozilla/5.0?(Windows;?U;?MSIE?9.0;?Windows?NT?9.0;?en-US)",
????"Mozilla/5.0?(compatible;?MSIE?9.0;?Windows?NT?6.1;?Win64;?x64;?Trident/5.0;?.NET?CLR?3.5.30729;?.NET?CLR?3.0.30729;?.NET?CLR?2.0.50727;?Media?Center?PC?6.0)",
]
headers?=?{"User-Agent":?random.choice(user_agent)}
filk?=?r'D:\Users\zgl\Music\\'


class?Jiuku(Process):
????url?=?'http://www.9ku.com/x1/music/by_new.php?act=t_m_hits&page='

????def?__init__(self,?threadID,?star_page,?end_page):
????????super().__init__()
????????self.threadID?=?threadID
????????self.star_page?=?star_page
????????self.end_page?=?end_page
????????self.music_list?=?[]

????def?get_one_html(self,?page):
????????"""獲取一個頁面的html"""
????????now_url?=?self.url?+?str(page)
????????print("線程：{},頁面鏈接：{}".format(self.threadID,?now_url))
????????r?=?requests.get(now_url,?headers=headers)
????????return?r.text

????def?get_many_url(self,?html):
????????"""根據html解析得到音樂的url"""
????????try:
????????????xml?=?etree.HTML(html)
????????????music_url?=?xml.xpath('//ol/li/a/@href')
????????????for?urls?in?music_url:
????????????????url?=?'http://www.9ku.com'?+?urls
????????????????self.music_list.append(url)
????????except?AttributeError:
????????????print("當前頁面無音樂鏈接")
????????return?self.music_list

????def?run(self):
????????#?print("線程：{},開始頁:{},結束頁：{}".format(self.threadID,?self.star_page,?self.end_page))
????????for?page?in?range(self.star_page,?self.end_page?+?1):
????????????time.sleep(1)
????????????#?print("當前頁數：{}".format(page))
????????????html?=?self.get_one_html(page)
????????????self.get_many_url(html)
????????????pool?=?Pool(10)
????????????pool.map(down_one_music,?self.music_list,?10)
????????????#?print("線程：{},音樂鏈接列表：{}".format(self.threadID,?self.music_list))
????????????#?for?i?in?self.music_list:
????????????#????print("音樂鏈接：{}".format(i))
????????????#????down_one_music(i)
????????????self.music_list.clear()


def?down_one_music(url):
????if?url:
????????#?print("音樂鏈接：{}".format(url))
????????try:
????????????r?=?requests.get(url,?headers=headers)
????????????xml?=?etree.HTML(r.text)
????????????title?=?xml.xpath('//div[@class="playingTit"]/h1/text()')[0]
????????????singer?=?xml.xpath('//div[@class="playingTit"]/h2/a/text()')[0]
????????????music?=?title?+?'-'?+?singer
????????????music_id?=?url.split('/')[-1].split('.')[0]??#?獲取音樂的id
????????????print('正在下載:{}'.format(music))
????????????music_url?=?'http://mp3.9ku.com/m4a/{}.m4a'.format(music_id)
????????????request.urlretrieve(music_url,?filk?+?music?+?'.mp3')
????????except?error.HTTPError:
????????????print("{}已下線".format(music))


def?main():
????number?=?int(input('請輸入要爬取的頁數:'))
????if?number?<=?4:
????????a?=?[i?for?i?in?range(1,?number?+?1)]
????????a_min?=?min(a)
????????a_max?=?max(a)
????????down?=?Jiuku("Thread-1",?a_min,?a_max)
????????down.start()
????else:
????????a?=?[i?for?i?in?range(1,?number?+?1)]
????????d?=?number?/?4??#?得到的數是一個浮點數
????????e?=?int(d)??#?這一步是對浮點數變?yōu)檎麛?，程序會將整數后面的小數全部清理這是的e就會小于d
????????if?d?>?e:??#?判斷如果e小于b則就需要將每個小列表中的數量為e+1
????????????step?=?e?+?1
????????????b?=?[a[i:i?+?step]?for?i?in?range(0,?len(a),?step)]
????????else:
????????????step?=?e
????????????b?=?[a[i:i?+?step]?for?i?in?range(0,?len(a),?step)]

????????for?index?in?range(len(b)):
????????????a_max?=?max(b[index])
????????????a_min?=?min(b[index])
????????????down?=?Jiuku("Thread-"?+?str(index),?a_min,?a_max)
????????????down.start()


if?__name__?==?'__main__':
????main()


0 回復 有任何疑惑可以回復我~ 
import?requests,?time,?random
from?lxml?import?etree
from?multiprocessing?import?Pool
from?multiprocessing?import?Process
from?urllib?import?request
from?urllib?import?error

user_agent?=?[
????"Mozilla/5.0?(compatible;?Baiduspider/2.0;?+http://www.baidu.com/search/spider.html)",
????"Mozilla/4.0?(compatible;?MSIE?6.0;?Windows?NT?5.1;?SV1;?AcooBrowser;?.NET?CLR?1.1.4322;?.NET?CLR?2.0.50727)",
????"Mozilla/4.0?(compatible;?MSIE?7.0;?Windows?NT?6.0;?Acoo?Browser;?SLCC1;?.NET?CLR?2.0.50727;?Media?Center?PC?5.0;?.NET?CLR?3.0.04506)",
????"Mozilla/4.0?(compatible;?MSIE?7.0;?AOL?9.5;?AOLBuild?4337.35;?Windows?NT?5.1;?.NET?CLR?1.1.4322;?.NET?CLR?2.0.50727)",
????"Mozilla/5.0?(Windows;?U;?MSIE?9.0;?Windows?NT?9.0;?en-US)",
????"Mozilla/5.0?(compatible;?MSIE?9.0;?Windows?NT?6.1;?Win64;?x64;?Trident/5.0;?.NET?CLR?3.5.30729;?.NET?CLR?3.0.30729;?.NET?CLR?2.0.50727;?Media?Center?PC?6.0)",
]
headers?=?{"User-Agent":?random.choice(user_agent)}
filk?=?r'D:\Users\zgl\Music\\'


class?Jiuku(Process):
????url?=?'http://www.9ku.com/x1/music/by_new.php?act=t_m_hits&page='

????def?__init__(self,?threadID,?star_page,?end_page):
????????super().__init__()
????????self.threadID?=?threadID
????????self.star_page?=?star_page
????????self.end_page?=?end_page
????????self.music_list?=?[]

????def?get_one_html(self,?page):
????????"""獲取一個頁面的html"""
????????now_url?=?self.url?+?str(page)
????????print("線程：{},頁面鏈接：{}".format(self.threadID,?now_url))
????????r?=?requests.get(now_url,?headers=headers)
????????return?r.text

????def?get_many_url(self,?html):
????????"""根據html解析得到音樂的url"""
????????try:
????????????xml?=?etree.HTML(html)
????????????music_url?=?xml.xpath('//ol/li/a/@href')
????????????for?urls?in?music_url:
????????????????url?=?'http://www.9ku.com'?+?urls
????????????????self.music_list.append(url)
????????except?AttributeError:
????????????print("當前頁面無音樂鏈接")
????????return?self.music_list

????def?run(self):
????????#?print("線程：{},開始頁:{},結束頁：{}".format(self.threadID,?self.star_page,?self.end_page))
????????for?page?in?range(self.star_page,?self.end_page?+?1):
????????????time.sleep(1)
????????????#?print("當前頁數：{}".format(page))
????????????html?=?self.get_one_html(page)
????????????self.get_many_url(html)
????????????pool?=?Pool(10)
????????????pool.map(down_one_music,?self.music_list,?10)
????????????#?print("線程：{},音樂鏈接列表：{}".format(self.threadID,?self.music_list))
????????????#?for?i?in?self.music_list:
????????????#????print("音樂鏈接：{}".format(i))
????????????#????down_one_music(i)
????????????self.music_list.clear()


def?down_one_music(url):
????if?url:
????????#?print("音樂鏈接：{}".format(url))
????????try:
????????????r?=?requests.get(url,?headers=headers)
????????????xml?=?etree.HTML(r.text)
????????????title?=?xml.xpath('//div[@class="playingTit"]/h1/text()')[0]
????????????singer?=?xml.xpath('//div[@class="playingTit"]/h2/a/text()')[0]
????????????music?=?title?+?'-'?+?singer
????????????music_id?=?url.split('/')[-1].split('.')[0]??#?獲取音樂的id
????????????print('正在下載:{}'.format(music))
????????????music_url?=?'http://mp3.9ku.com/m4a/{}.m4a'.format(music_id)
????????????request.urlretrieve(music_url,?filk?+?music?+?'.mp3')
????????except?error.HTTPError:
????????????print("{}已下線".format(music))


def?main():
????number?=?int(input('請輸入要爬取的頁數:'))
????if?number?<=?4:
????????a?=?[i?for?i?in?range(1,?number?+?1)]
????????a_min?=?min(a)
????????a_max?=?max(a)
????????down?=?Jiuku("Thread-1",?a_min,?a_max)
????????down.start()
????else:
????????a?=?[i?for?i?in?range(1,?number?+?1)]
????????d?=?number?/?4??#?得到的數是一個浮點數
????????e?=?int(d)??#?這一步是對浮點數變?yōu)檎麛担绦驎⒄麛岛竺娴男等壳謇磉@是的e就會小于d
????????if?d?>?e:??#?判斷如果e小于b則就需要將每個小列表中的數量為e+1
????????????step?=?e?+?1
????????????b?=?[a[i:i?+?step]?for?i?in?range(0,?len(a),?step)]
????????else:
????????????step?=?e
????????????b?=?[a[i:i?+?step]?for?i?in?range(0,?len(a),?step)]

????????for?index?in?range(len(b)):
????????????a_max?=?max(b[index])
????????????a_min?=?min(b[index])
????????????down?=?Jiuku("Thread-"?+?str(index),?a_min,?a_max)
????????????down.start()


if?__name__?==?'__main__':
????main()

回復居然不能編輯，上面的格式不知道怎么回事，重新上傳一下代碼

0 回復 有任何疑惑可以回復我~ 
import requests, time, random
from lxml import etree
from multiprocessing import Pool
from multiprocessing import Process
from urllib import request
from urllib import error

user_agent = [
 ? ?"Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)",
 ? ?"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
 ? ?"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
 ? ?"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
 ? ?"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
 ? ?"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
]
headers = {"User-Agent": random.choice(user_agent)}
filk = r'D:\Users\zgl\Music\\'


class Jiuku(Process):
 ? ?url = 'http://www.9ku.com/x1/music/by_new.php?act=t_m_hits&page='

 ? ?def __init__(self, threadID, star_page, end_page):
 ? ? ? ?super().__init__()
 ? ? ? ?self.threadID = threadID
 ? ? ? ?self.star_page = star_page
 ? ? ? ?self.end_page = end_page
 ? ? ? ?self.music_list = []

 ? ?def get_one_html(self, page):
 ? ? ? ?"""獲取一個頁面的html"""
 ? ? ? ?now_url = self.url + str(page)
 ? ? ? ?print("線程：{},頁面鏈接：{}".format(self.threadID, now_url))
 ? ? ? ?r = requests.get(now_url, headers=headers)
 ? ? ? ?return r.text

 ? ?def get_many_url(self, html):
 ? ? ? ?"""根據html解析得到音樂的url"""
 ? ? ? ?try:
 ? ? ? ? ? ?xml = etree.HTML(html)
 ? ? ? ? ? ?music_url = xml.xpath('//ol/li/a/@href')
 ? ? ? ? ? ?for urls in music_url:
 ? ? ? ? ? ? ? ?url = 'http://www.9ku.com' + urls
 ? ? ? ? ? ? ? ?self.music_list.append(url)
 ? ? ? ?except AttributeError:
 ? ? ? ? ? ?print("當前頁面無音樂鏈接")
 ? ? ? ?return self.music_list

 ? ?def run(self):
 ? ? ? ?# print("線程：{},開始頁:{},結束頁：{}".format(self.threadID, self.star_page, self.end_page))
 ? ? ? ?for page in range(self.star_page, self.end_page + 1):
 ? ? ? ? ? ?time.sleep(1)
 ? ? ? ? ? ?# print("當前頁數：{}".format(page))
 ? ? ? ? ? ?html = self.get_one_html(page)
 ? ? ? ? ? ?self.get_many_url(html)
 ? ? ? ? ? ?pool = Pool(10)
 ? ? ? ? ? ?pool.map(down_one_music, self.music_list, 10)
 ? ? ? ? ? ?# print("線程：{},音樂鏈接列表：{}".format(self.threadID, self.music_list))
 ? ? ? ? ? ?# for i in self.music_list:
 ? ? ? ? ? ?# ? ?print("音樂鏈接：{}".format(i))
 ? ? ? ? ? ?# ? ?down_one_music(i)
 ? ? ? ? ? ?self.music_list.clear()


def down_one_music(url):
 ? ?if url:
 ? ? ? ?# print("音樂鏈接：{}".format(url))
 ? ? ? ?try:
 ? ? ? ? ? ?r = requests.get(url, headers=headers)
 ? ? ? ? ? ?xml = etree.HTML(r.text)
 ? ? ? ? ? ?title = xml.xpath('//div[@class="playingTit"]/h1/text()')[0]
 ? ? ? ? ? ?singer = xml.xpath('//div[@class="playingTit"]/h2/a/text()')[0]
 ? ? ? ? ? ?music = title + '-' + singer
 ? ? ? ? ? ?music_id = url.split('/')[-1].split('.')[0] ?# 獲取音樂的id
 ? ? ? ? ? ?print('正在下載:{}'.format(music))
 ? ? ? ? ? ?music_url = 'http://mp3.9ku.com/m4a/{}.m4a'.format(music_id)
 ? ? ? ? ? ?request.urlretrieve(music_url, filk + music + '.mp3')
 ? ? ? ?except error.HTTPError:
 ? ? ? ? ? ?print("{}已下線".format(music))


def main():
 ? ?number = int(input('請輸入要爬取的頁數:'))
 ? ?if number <= 4:
 ? ? ? ?a = [i for i in range(1, number + 1)]
 ? ? ? ?a_min = min(a)
 ? ? ? ?a_max = max(a)
 ? ? ? ?down = Jiuku("Thread-1", a_min, a_max)
 ? ? ? ?down.start()
 ? ?else:
 ? ? ? ?a = [i for i in range(1, number + 1)]
 ? ? ? ?d = number / 4 ?# 得到的數是一個浮點數
 ? ? ? ?e = int(d) ?# 這一步是對浮點數變?yōu)檎麛?，程序會將整數后面的小數全部清理這是的e就會小于d
 ? ? ? ?if d > e: ?# 判斷如果e小于b則就需要將每個小列表中的數量為e+1
 ? ? ? ? ? ?step = e + 1
 ? ? ? ? ? ?b = [a[i:i + step] for i in range(0, len(a), step)]
 ? ? ? ?else:
 ? ? ? ? ? ?step = e
 ? ? ? ? ? ?b = [a[i:i + step] for i in range(0, len(a), step)]

 ? ? ? ?for index in range(len(b)):
 ? ? ? ? ? ?a_max = max(b[index])
 ? ? ? ? ? ?a_min = min(b[index])
 ? ? ? ? ? ?down = Jiuku("Thread-" + str(index), a_min, a_max)
 ? ? ? ? ? ?down.start()


if __name__ == '__main__':
 ? ?main()


我將你的程序根據我的理解優(yōu)化了一下，目前運行正常?？梢詤⒖家幌隆?/p>

http://img1.sycdn.imooc.com//5dbd940800017f8816910931.jpg


0 回復 有任何疑惑可以回復我~

舉報

0/150
提交
取消
Python開發(fā)簡單爬蟲
  • 參與學習       227603    人
  • 解答問題       1282    個

本教程帶您解開python爬蟲這門神奇技術的面紗

進入課程

代碼出現問題

我要回答 關注問題
微信客服

購課補貼
聯系客服咨詢優(yōu)惠詳情

 幫助反饋 APP下載

慕課網APP
您的移動學習伙伴

 公眾號

掃描二維碼
關注慕課網微信公眾號