获取贴吧帖子的总页数

获取贴吧http://tieba.baidu.com/p/2314539885帖子的总页数，并获取里面的邮箱。

from urllib import request
import re
url = 'http://tieba.baidu.com/p/2314539885'
def get_content(url):
    with request.urlopen(url) as f:
        content = f.read().decode('utf-8')
        return content
def get_page(url):
        content = get_content(url)
        # < a href = "/p/2314539885?pn=31" >尾页 < / a >
        pattern = r'<a href="/p/.*?pn=(.*)">尾页</a>'
        return int(re.findall(pattern, content)[0])
def create_url(url, page):
    url_li = []
    for i in range(page):
        print("第%s页" %(i+1))
        new_url = url+'?pn=%d' %(i+1)
        url_li.append(new_url)
    return url_li
def get_email(url):
    content = get_content(url)
    pattern = r"[a-zA-Z0-9_]+@\w+\.com"
    return re.findall(pattern, content)
page = get_page(url)
print("贴吧总共有%d页, 正在爬取中.......")
url_li = create_url(url,page)
for url in url_li:

    print(get_email(url))

import re
from asyncio import as_completed
from concurrent.futures import ThreadPoolExecutor
from urllib import request
from mytime import timeit
url = 'http://tieba.baidu.com/p/2314539885'
def get_content(url):
    with request.urlopen(url, timeout=60) as urlObj:
        content = urlObj.read().decode('utf-8')
        return content
def get_page(url):
    content = get_content(url)
    pattern = r'<a href="/p/.*pn=(\d+)">尾页</a>'
    page = re.findall(pattern, content)[0]
    return int(page)
def get_all_url(url, page):
    url_li = []
    for i in range(page):
        new_url = url +'?pn=%d' %(i+1)
        url_li.append(new_url)
    return url_li
def get_email(content):
    pattern = r'[a-zA-Z0-9]+@\w+\.com'
    return re.findall(pattern, content)
@timeit
def useThreadMain():
    page = get_page(url)
    url_li = get_all_url(url, page)
    with ThreadPoolExecutor(max_workers=4) as pool:
        pool.map(get_email, url_li)
def useNoThreadMain():
    page = get_page(url)
    url_li = get_all_url(url, page)
    for urlItem in url_li:
        get_email(urlItem)
def main():
    page = get_page(url)
    url_li = get_all_url(url, page)
    for urlItem in url_li:
        content = get_content(urlItem)
        print(get_email(content))

main()