# -*- coding:utf-8 -*-
"""
作者：wyt
日期：2022年04月21日
"""
import threading
import requests
import time
urls = [
    f'https://www.cnblogs.com/#p{page}' # 待爬地址
    for page in range(1, 10)  # 爬取1-10頁(yè)
]
def craw(url):
    r = requests.get(url)
    num = len(r.text)  # 爬取博客園當(dāng)頁(yè)的文字?jǐn)?shù)
    return num  # 返回當(dāng)頁(yè)文字?jǐn)?shù)
 
def sigle():  # 單線程
    res = []
    for i in urls:
        res.append(craw(i))
    return res
class MyThread(threading.Thread):  # 重寫threading.Thread類，加入獲取返回值的函數(shù)
    def __init__(self, url):
        threading.Thread.__init__(self)
        self.url = url                # 初始化傳入的url
    def run(self):                    # 新加入的函數(shù)，該函數(shù)目的：
        self.result = craw(self.url)  # ①。調(diào)craw(arg)函數(shù)，并將初試化的url以參數(shù)傳遞——實(shí)現(xiàn)爬蟲功能
                                      # ②。并獲取craw(arg)函數(shù)的返回值存入本類的定義的值result中
    def get_result(self):  #新加入函數(shù)，該函數(shù)目的：返回run()函數(shù)得到的result
        return self.result
def multi_thread():
    print("start")
    threads = []           # 定義一個(gè)線程組
    for url in urls:
        threads.append(    # 線程組中加入賦值后的MyThread類
            MyThread(url)  # 將每一個(gè)url傳到重寫的MyThread類中
        )
    for thread in threads: # 每個(gè)線程組start
        thread.start()
    for thread in threads: # 每個(gè)線程組join
        thread.join()
    list = []
    for thread in threads:
        list.append(thread.get_result())  # 每個(gè)線程返回結(jié)果(result)加入列表中
    print("end")
    return list  # 返回多線程返回的結(jié)果組成的列表
if __name__ == '__main__':
    start_time = time.time()
    result_multi = multi_thread()
    print(result_multi)  # 輸出返回值-列表
    # result_sig = sigle()
    # print(result_sig)
    end_time = time.time()
    print('用時(shí)：', end_time - start_time)

import threading
import requests
import time
urls = [
    f'https://www.cnblogs.com/#p{page}' # 待爬地址
    for page in range(1, 10)  # 爬取1-10頁(yè)
]
def craw(url):
    r = requests.get(url)
    num = len(r.text)  # 爬取博客園當(dāng)頁(yè)的文字?jǐn)?shù)
    print(num)
def sigle():  # 單線程
    res = []
    for i in urls:
        res.append(craw(i))
    return res
def multi_thread():
    print("start")
    threads = []           # 定義一個(gè)線程組
    for url in urls:
        threads.append(
            threading.Thread(target=craw,args=(url,))  # 注意args=(url,)，元組
        )
    for thread in threads: # 每個(gè)線程組start
        thread.start()
    for thread in threads: # 每個(gè)線程組join
        thread.join()
    print("end")
if __name__ == '__main__':
    start_time = time.time()
    result_multi = multi_thread()
    # result_sig = sigle()
    # print(result_sig)
    end_time = time.time()
    print('用時(shí)：', end_time - start_time)

import time
from threading import Thread
def foo(number):
    time.sleep(1)
    return number
class MyThread(Thread):
    def __init__(self, number):
        Thread.__init__(self)
        self.number = number
    def run(self):
        self.result = foo(self.number)
    def get_result(self):
        return self.result
if __name__ == '__main__':
    thd1 = MyThread(3)
    thd2 = MyThread(5)
    thd1.start()
    thd2.start()
    thd1.join()
    thd2.join()
    print(thd1.get_result())
    print(thd2.get_result())

threading.Thread(target=craw,args=(url,))  # 注意args=(url,)，元組

import threading
import requests
from bs4 import BeautifulSoup
from static.plugs.headers import get_ua
#https://cn.bing.com/search?q=site%3Abaidu.com&go=Search&qs=ds&first=20&FORM=PERE
def search_1(url):
    Subdomain = []
    html = requests.get(url, stream=True, headers=get_ua())
    soup = BeautifulSoup(html.content, 'html.parser')
    job_bt = soup.findAll('h2')
    for i in job_bt:
        link = i.a.get('href')
        # print(link)
        if link not in Subdomain:
            Subdomain.append(link)
    return Subdomain
class MyThread(threading.Thread):
    def __init__(self, url):
        threading.Thread.__init__(self)
        self.url = url
    def run(self):
        self.result = search_1(self.url)
    def get_result(self):
        return self.result
def Bing_multi_thread(site):
    print("start")
    threads = []
    for i in range(1, 30):
        url = "https://cn.bing.com/search?q=site%3A" + site + "&go=Search&qs=ds&first=" + str(
            (int(i) - 1) * 10) + "&FORM=PERE"
        threads.append(
            MyThread(url)
        )
    for thread in threads:
        thread.start()
    for thread in threads:
        thread.join()
    res_list = []
    for thread in threads:
        res_list.extend(thread.get_result())
    res_list = list(set(res_list)) #列表去重
    number = 1
    for i in res_list:
        number += 1
    number_list = list(range(1, number + 1))
    dict_res = dict(zip(number_list, res_list))
    print("end")
    return dict_res
if __name__ == '__main__':
    print(Bing_multi_thread("qq.com"))