1 def CreatFile(filename):
2     with open(filename +".txt",'w',encoding='utf-8',errors='ignore') as f:
3         f.writelines("           " + filename + "        " + '\r\n')
4 def appointchapter(filename, context):
5     with open(filename +".txt",'a',encoding='utf-8',errors='ignore') as f:
6         f.writelines(context + '\r\n')

 1 import re
 2 # 获取小说名字
 3 reName = re.compile(r'<h1>.+?(?:</h1>)',re.DOTALL)
 4 #获取小说章节目录
 5 rechapterLi = re.compile(r'<table.+?(?:</table>)',re.DOTALL)
 6 #获取小说单个章节目录
 7 rePage = re.compile(r'<a.+?(?:</a>)',re.MULTILINE)
 8 #获取小说单个章节链接
 9 rePageUrl = re.compile(r'[\d]+.+?(?:html)',re.DOTALL)
10 #获取小说章节名字
11 reTitle = re.compile(r'<dd><h1>.+?(?:</h1></dd>)',re.DOTALL)
12 #获取原始的章节内容
13 reContent =re.compile(r'<dd id="contents".+?(?:</dd>)',re.DOTALL)
14
15 def DoHtmlToTxt(htmlstr):
16     txt = re.sub('&nbsp;',' ',htmlstr)
17     txt = re.sub('<br />','\r\n',txt)
18     txt = re.sub(r'<.+?(?:>)','',txt)
19     return txt
20 def DelHtmlCoding(htmlstr):
21     txt = re.sub(r'<.+?(?:>)','',htmlstr)
22     txt = re.sub(r'最新.+?(?:列表)','',txt)
23     txt = re.sub(' ','',txt)
24     return txt

 1 import urllib
 2 import urllib.request
 3 def GetHtmlContent(html,endcoding):
 4     try:
 5         request =  urllib.request.Request(html)
 6         response = urllib.request.urlopen(request)
 7         data = response.read()
 8         data = data.decode(endcoding)
 9         return data
10     except Exception as e:
11         with open('erro.txt','a',encoding='utf-8') as f:
12             f.writelines('抓取报错' + html)
13             f.writelines('报错原因' + e)
14             return '0'
15     except URLError as e:
16         with open('erro.txt','a',encoding='utf-8') as f:
17             f.writelines('抓取报错' + html)
18             f.writelines('报错原因' + e)
19             return '0'
20     

 1 import RegularExpression.Regular
 2 import FileManager.FileWrite
 3 import WebManager.HttpContext
 4 #htmlurl = 'https://www.x23us.com/html/69/69720/'
 5 htmlurl = 'https://www.23us.cc/html/173/173244/'
 6 htmltxt = WebManager.HttpContext.GetHtmlContent(htmlurl,'gbk')
 7 if htmltxt != '0':
 8     titlehtml = RegularExpression.Regular.reName.search(htmltxt).group()
 9     title =  RegularExpression.Regular.DelHtmlCoding(titlehtml)
10     FileManager.FileWrite.CreatFile(title)
11     chaptercontent = RegularExpression.Regular.rechapterLi.search(htmltxt).group()
12     if chaptercontent:
13         chapterli = RegularExpression.Regular.rePage.finditer(chaptercontent)
14         if chapterli:
15             for m in chapterli:
16                 pageurl = RegularExpression.Regular.rePageUrl.search(m.group()).group()
17                 htmlpagetxt =  WebManager.HttpContext.GetHtmlContent(htmlurl + pageurl,'gbk')
18                 if htmlpagetxt != '0':
19                     pageName = RegularExpression.Regular.reTitle.search(htmlpagetxt).group()
20                     pageContent = RegularExpression.Regular.reContent.search(htmlpagetxt).group()
21                     pageName = RegularExpression.Regular.DelHtmlCoding(pageName)
22                     pageContent = RegularExpression.Regular.DoHtmlToTxt(pageContent)
23                     txt = '\r\n'+ pageName +'\r\n' + pageContent
24                     FileManager.FileWrite.appointchapter(title,txt)
25                 else:
26                     continue
27             print('下载成功!')