简单优化这段代码import requests from bs4 import BeautifulSoup from threading import Thread def crawl_books(start, end): for i in range(start, end): url = 'http://search.dangdang.com/?key=%BC%C6%CB%E3%BB%FA&act=input&page_index={}'.format(i) response = requests.get(url) page = response.text soup = BeautifulSoup(page, 'lxml') books = soup.find('ul', class_='bigimg') for book in books.find_all('li'): title = book.find('a', class_='pic').get('title') author = book.find('p', class_='search_book_author').text price = book.find('p', class_='price').find('span', class_='search_now_price').text book_link = 'https:' + book.find('a', class_='pic').get('href') response = requests.get(book_link) page = response.text soup = BeautifulSoup(page, 'lxml') comment_num_tag = soup.find('a', class_='review_num') if comment_num_tag: comment_num = comment_num_tag.text else: comment_num = '0' print(title, author, price, comment_num) threads = [] for i in range(1, 101, 10): t = Thread(target=crawl_books, args=(i, i+10)) threads.append(t) t.start() for t in threads: t.join()

这段代码已经很简洁了，但是可以对程序进行一些小的优化，如下：

1. 由于书籍详情页有可能没有评论数量，因此可以在获取评论数量时添加判断。

2. 为了提高爬取效率，可以使用 `Session` 对象来复用连接，避免多次建立连接。

3. 在爬取时可以设置超时时间，防止程序长时间等待而阻塞。

优化后的代码如下：

import requests
from bs4 import BeautifulSoup
from threading import Thread

def crawl_books(start, end):
    session = requests.Session()
    for i in range(start, end):
        url = 'http://search.dangdang.com/?key=%BC%C6%CB%E3%BB%FA&act=input&page_index={}'.format(i)
        try:
            response = session.get(url, timeout=10)
        except requests.exceptions.Timeout:
            print('Timeout occurred when accessing: ' + url)
            continue
        page = response.text
        soup = BeautifulSoup(page, 'lxml')
        books = soup.find('ul', class_='bigimg')
        for book in books.find_all('li'):
            title = book.find('a', class_='pic').get('title')
            author = book.find('p', class_='search_book_author').text
            price = book.find('p', class_='price').find('span', class_='search_now_price').text
            book_link = 'https:' + book.find('a', class_='pic').get('href')
            try:
                response = session.get(book_link, timeout=10)
            except requests.exceptions.Timeout:
                print('Timeout occurred when accessing: ' + book_link)
                continue
            page = response.text
            soup = BeautifulSoup(page, 'lxml')
            comment_num_tag = soup.find('a', class_='review_num')
            if comment_num_tag:
                comment_num = comment_num_tag.text
            else:
                comment_num = '0'
            print(title, author, price, comment_num)

threads = []
for i in range(1, 101, 10):
    t = Thread(target=crawl_books, args=(i, i+10))
    threads.append(t)
    t.start()

for t in threads:
    t.join()

这样，我们对程序进行了一些小的优化，代码更加健壮和高效。