# 循環(huán)
for i in range(10):
print(i ** i)

from multiprocessing.dummy import Pool

# 平方函數(shù)
def calc_power2(num):
return num * num

# 定義三個(gè)線程池
pool = Pool(3)
# 定義循環(huán)數(shù)
origin_num = [x for x in range(10)]
# 利用map讓線程池中的所有線程‘同時(shí)'執(zhí)行calc_power2函數(shù)
result = pool.map(calc_power2, origin_num)
print(f'計(jì)算1-10的平方分別為：{result}')

import time
import requests
from multiprocessing.dummy import Pool

# 自定義函數(shù)
def query(url):
requests.get(url)

start = time.time()
for i in range(100):
query('https://www.csdn.net/')
end = time.time()
print(f'單線程循環(huán)訪問100次CSDN，耗時(shí)：{end - start}')

start = time.time()
url_list = []
for i in range(100):
url_list.append('https://www.csdn.net/')
pool = Pool(5)
pool.map(query, url_list)
end = time.time()
print(f'5線程訪問100次CSDN，耗時(shí)：{end - start}')

import re
import os
import requests
from multiprocessing.dummy import Pool

# 爬取的主網(wǎng)站地址
start_url = 'https://www.kanunu8.com/book2/11138/'
"""
獲取網(wǎng)頁源代碼
:param url: 網(wǎng)址
:return: 網(wǎng)頁源代碼
"""
def get_source(url):
html = requests.get(url)
return html.content.decode('gbk') # 這個(gè)網(wǎng)頁需要使用gbk方式解碼才能讓中文正常顯示

"""
獲取每一章鏈接，儲存到一個(gè)列表中并返回
:param html: 目錄頁源代碼
:return: 每章鏈接
"""
def get_article_url(html):
article_url_list = []
article_block = re.findall('正文(.*?)<div class="clear">', html, re.S)[0]
article_url = re.findall('<a href="(\d*.html)" rel="external nofollow"  rel="external nofollow" >', article_block, re.S)
for url in article_url:
article_url_list.append(start_url + url)
return article_url_list

"""
獲取每一章的正文并返回章節(jié)名和正文
:param html: 正文源代碼
:return: 章節(jié)名，正文
"""
def get_article(html):
chapter_name = re.findall('<h1>(.*?)<br>', html, re.S)[0]
text_block = re.search('<p>(.*?)</p>', html, re.S).group(1)
text_block = text_block.replace('?', '') # 替換 ? 網(wǎng)頁空格符
text_block = text_block.replace('<p>', '') # 替換 <p></p> 中的嵌入的 <p></p> 中的 <p>
return chapter_name, text_block

"""
將每一章保存到本地
:param chapter: 章節(jié)名, 第X章
:param article: 正文內(nèi)容
:return: None
"""
def save(chapter, article):
os.makedirs('北歐眾神', exist_ok=True) # 如果沒有"北歐眾神"文件夾，就創(chuàng)建一個(gè)，如果有，則什么都不做"
with open(os.path.join('北歐眾神', chapter + '.txt'), 'w', encoding='utf-8') as f:
f.write(article)

"""
根據(jù)正文網(wǎng)址獲取正文源代碼，并調(diào)用get_article函數(shù)獲得正文內(nèi)容最后保存到本地
:param url: 正文網(wǎng)址
:return: None
"""
def query_article(url):
article_html = get_source(url)
chapter_name, article_text = get_article(article_html)
# print(chapter_name)
# print(article_text)
save(chapter_name, article_text)

if __name__ == '__main__':
toc_html = get_source(start_url)
toc_list = get_article_url(toc_html)
pool = Pool(4)
pool.map(query_article, toc_list)

# 爬取的主網(wǎng)站地址
start_url = 'https://www.kanunu8.com/book2/11138/'
def get_source(url):
html = requests.get(url)
return html.content.decode('gbk') # 這個(gè)網(wǎng)頁需要使用gbk方式解碼才能讓中文正常顯示

def get_article_url(html):
article_url_list = []
# 根據(jù)正文鎖定每一章節(jié)的鏈接區(qū)域
article_block = re.findall('正文(.*?)<div class="clear">', html, re.S)[0]
# 獲取到每一章的鏈接
article_url = re.findall('<a href="(\d*.html)" rel="external nofollow"  rel="external nofollow" >', article_block, re.S)
for url in article_url:
article_url_list.append(start_url + url)
return

def get_article(html):
chapter_name = re.findall('<h1>(.*?)<br>', html, re.S)[0]
text_block = re.search('<p>(.*?)</p>', html, re.S).group(1)
text_block = text_block.replace('?', '') # 替換 ? 網(wǎng)頁空格符
text_block = text_block.replace('<p>', '') # 替換 <p></p> 中的嵌入的 <p></p> 中的 <p>
return chapter_name,

"""
將每一章保存到本地
:param chapter: 章節(jié)名, 第X章
:param article: 正文內(nèi)容
:return: None
"""
def save(chapter, article):
os.makedirs('北歐眾神', exist_ok=True) # 如果沒有"北歐眾神"文件夾，就創(chuàng)建一個(gè)，如果有，則什么都不做"
with open(os.path.join('北歐眾神', chapter + '.txt'), 'w', encoding='utf-8') as f:
f.write(article)

"""
根據(jù)正文網(wǎng)址獲取正文源代碼，并調(diào)用get_article函數(shù)獲得正文內(nèi)容最后保存到本地
:param url: 正文網(wǎng)址
:return: None
"""
def query_article(url):
article_html = get_source(url)
chapter_name, article_text = get_article(article_html)
# print(chapter_name)
# print(article_text)
save(chapter_name, article_text)

if __name__ == '__main__':
toc_html = get_source(start_url)
toc_list = get_article_url(toc_html)
pool = Pool(4)
pool.map(query_article, toc_list)