运行下面代码，运行结果没有保存文件，请帮我找出原因 # -- coding: utf-8 -- import urllib.request import re def getNovertContent(): url = 'http://www.quannovel.com/read/640/' req = urllib.request.Request(url) req.add_header('User-Agent', ' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36') data = urllib.request.urlopen(req).read().decode('gbk') str1 = str(data) # 将网页数据转换为字符串 reg = r'<li><a href="(.?)" title=".?">(.?)</a><li>' reg = re.compile(reg) urls = reg.findall(str1) for url in urls: novel_url = url[0] novel_title = url[1] chapt = urllib.request.urlopen(novel_url).read() chapt_html = chapt.decode('gbk') reg = r'</script> (.?)</script type="text/javascript">' reg = re.compile(reg, re.S) chapt_content = reg.findall(chapt_html) chapt_content = chapt_content[0].replace( " ", "") chapt_content = chapt_content.replace("<br />", "") print("正在保存 %s" % novel_title) with open("{}.txt".format(novel_title), 'w', encoding='utf-8') as f: f.write(chapt_content) getNovertContent()

在这段代码中，正则表达式的模式字符串存在错误。具体来说，第17行的正则表达式模式字符串r'</script> (.?)</script type="text/javascript">' 需要修改为r'</script>&nbsp;&nbsp;&nbsp;&nbsp;(.*?)</script type="text/javascript">'，因为小说网站中的章节正文内容前面有四个空格，而不是一个空格。另外，正则表达式中的点号也需要修改为点号加上一个问号，以适配所有可能的字符。修改后的代码如下：

# -- coding: utf-8 -- 

import urllib.request 
import re 

def getNovertContent(): 
    url = 'http://www.quannovel.com/read/640/' 
    req = urllib.request.Request(url) 
    req.add_header('User-Agent', ' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36') 
    data = urllib.request.urlopen(req).read().decode('gbk') 
    str1 = str(data) # 将网页数据转换为字符串 
    reg = r'<li><a href="(.?)" title=".?">(.?)</a><li>' 
    reg = re.compile(reg) 
    urls = reg.findall(str1) 
    for url in urls: 
        novel_url = url[0] 
        novel_title = url[1] 
        chapt = urllib.request.urlopen(novel_url).read() 
        chapt_html = chapt.decode('gbk') 
        reg = r'</script>&nbsp;&nbsp;&nbsp;&nbsp;(.*?)</script type="text/javascript">' 
        reg = re.compile(reg, re.S) 
        chapt_content = reg.findall(chapt_html) 
        chapt_content = chapt_content[0].replace("&nbsp;&nbsp;&nbsp;&nbsp;", "") 
        chapt_content = chapt_content.replace("<br />", "") 
        print("正在保存 %s" % novel_title) 
        with open("{}.txt".format(novel_title), 'w', encoding='utf-8') as f: 
            f.write(chapt_content) 
            
getNovertContent()

这样就可以正常保存爬取到的小说内容了。