python爬虫抓取小说--练习

 

思路：

1、抓取解析获取整个网站的所有小说

2、抓取解析小说的所有章节路径

3、抓取解析小说所有章节的内容生成TXT

  1 import threading
  2 import time
  3 import urllib.request
  4 from bs4 import BeautifulSoup
  5 import re
  6 import socket
  7 
  8 #设置超时时间
  9 socket.setdefaulttimeout(10) 
 10 
 11 def getHTMLData(strURL):
 12     try:
 13         data = urllib.request.urlopen(strURL).read()
 14         return data
 15     except:
 16         print('i get the error')
 17         data = urllib.request.urlopen(strURL).read()
 18         return data
 19 
 20 def getDataOnMatch(data, name, att, match):
 21     soup = BeautifulSoup(data,"html.parser")
 22     result = soup.find_all(name, att)
 23     if match !="":
 24         re_pat = re.compile(match)
 25         list = re_pat.findall(str(result))
 26         return list 
 27     return result
 28 
 29 #保存小说信息
 30 class ListBookInfo:
 31     def __init__(self):
 32         self.lock = threading.Lock()
 33         self.nLsBookCnt = 0
 34         self.lsBookInfo = []
 35       
 36     def AddBookInfo(self, strBookName, strBookURL):
 37         self.lock.acquire()
 38         obj = []
 39         obj.append(strBookName)
 40         obj.append(strBookURL)
 41         self.lsBookInfo.append(obj)
 42         self.nLsBookCnt += 1
 43         self.lock.release()
 44         
 45     def GetHeadBookInfo(self):
 46         self.lock.acquire()
 47         if self.nLsBookCnt > 0:
 48             bookInfo = self.lsBookInfo[0]
 49             del self.lsBookInfo[0]
 50             self.nLsBookCnt -= 1
 51             self.lock.release()
 52             return bookInfo
 53         else:
 54             self.lock.release()
 55             return 0
 56         
 57     def GetSize(self):
 58         self.lock.acquire()
 59         nSize = self.nLsBookCnt
 60         self.lock.release()
 61         return nSize
 62         
 63     def ClearLsBook(self):
 64         self.lock.acquire()
 65         self.lsBookInfo.clear()
 66         self.nLsBookCnt = 0
 67         self.lock.release()
 68 
 69 #保存小说名、小说章节信息（章节名、章节URL）        
 70 class BookPageInfo:
 71     def __init__(self):
 72         self.lock = threading.Lock()
 73         self.nBookPageCnt = 0
 74         self.lsBookPageInfo = []
 75       
 76     def AddBookPageInfo(self, strBookName, lsBookPageURL):
 77         self.lock.acquire()
 78         obj = []
 79         obj.append(strBookName)
 80         obj.append(lsBookPageURL)
 81         self.lsBookPageInfo.append(obj)
 82         self.nBookPageCnt += 1
 83         self.lock.release()
 84         
 85     def GetHeadBookPageInfo(self):
 86         self.lock.acquire()
 87         if self.nBookPageCnt > 0:
 88             bookInfo = self.lsBookPageInfo[0]
 89             del self.lsBookPageInfo[0]
 90             self.nBookPageCnt -= 1
 91             self.lock.release()
 92             return bookInfo
 93         else:
 94             self.lock.release()
 95             return 0
 96     
 97     def GetSize(self):
 98         self.lock.acquire()
 99         nSize = self.nBookPageCnt
100         self.lock.release()
101         return nSize
102         
103     def ClearLsBookPage(self):
104         self.lock.acquire()
105         self.lsBookPageInfo.clear()
106         self.nBookPageCnt = 0
107         self.lock.release()
108         
109 def getArticleType(data):
110     soup = BeautifulSoup(data)
111     data_ul = soup.find_all("ul", "channel-nav-list")
112     print(data_ul)
113     re_pat = re.compile('\(.*)\<\/a\>') 
114     list = re_pat.findall(str(data_ul))
115     print(list)
116     for i in list:
117         print("%s-->%s" % (i[1], i[0]))
118     return list
119 
120 def getArticle(strURL):
121     data = getHTMLData(strURL)
122     print(data)
123     ll = getDataOnMatch(data, "ul", "seeWell cf", "\(.*?)href=\"(.*?)\"(.*?)\<\/li\>")
124     list = []
125     for i in ll:
126         obj = []
127         listReData = getDataOnMatch(getHTMLData(i[1]),"section","main b-detail", "(.*?)href=\"(.*?)\"(.*?)")
128         obj.append(listReData[0][1])
129         lf = re.findall("(.*?)alt=\"(.*?)\"(.*?)", i[2])    
130         obj.append(lf[0][1])
131         list.append(obj)
132     return list
133 
134 def getArticlePageContent(strURL):
135     data = getHTMLData(strURL)
136     InfoList = getDataOnMatch(data, "div", "clearfix dirconone", "\(.*?)href=\"(.*?)\" title=\"(.*?)\"(.*?)\<\/li\>")
137     pageInfoList = []
138     for i  in InfoList:
139         obj = []
140         obj.append(strURL + '/' + i[1])
141         obj.append(i[2])
142         pageInfoList.append(obj)
143     return pageInfoList
144 
145 def getArticleContent(strURL):
146     try:
147         data = getHTMLData(strURL)
148         ll = getDataOnMatch(data, "div", "mainContenr", "")
149         return ll
150     except:
151         print('i get the error')
152         data = getHTMLData(strURL)
153         ll = getDataOnMatch(data, "div", "mainContenr", "")
154         return ll
155 
156 class CleverBookSys:
157     
158     def __init__(self):
159         self.bExit = 0
160         self.eventBook = threading.Event()
161         self.eventPage = threading.Event()
162         self.lsBookInfo = ListBookInfo()
163         self.lsBookPageInfo = BookPageInfo()
164         self.thrParseBook = ThreadForParseAllBook(self, "ThreadForParseAllBook")
165         self.thrParseBookPage = ThreadForParseBookPage(self, "ThreadForParseBookPage")
166         nCount = 0
167         self.thrDownLoad = []
168         #开十个线程用于下载，视网速而定
169         while nCount < 10:         
170             thread = ThreadForDownloadTxt(self,"ThreadForDownloadTxt",nCount)
171             thread.start()
172             self.thrDownLoad.append(thread)
173             nCount += 1
174         self.thrParseBook.start()
175         self.thrParseBookPage.start()
176         
177 #用与抓取整个网站的小说名及URL（没写完、大概写了一些）
178 class ThreadForParseAllBook(threading.Thread):
179     
180     def __init__(self, parent, strThrName):
181         threading.Thread.__init__(self) 
182         self.parent = parent
183         self.strThrName = strThrName
184         #这里只针对这个网站的解析
185         self.lsArticle = getArticleType(getHTMLData("http://www.quanshuwang.com/"))
186         
187     def run(self):
188         print("Thread %s is Start!!!" % (self.strThrName))
189         for art in self.lsArticle:
190             bookInfoList = getArticle(art[0])
191             #【0】：小说路径，[1]：小说名
192             for bookInfo in bookInfoList:
193                 self.parent.lsBookInfo.AddBookInfo(bookInfo[1], bookInfo[0])
194             self.parent.eventBook.set()
195             
196 #用于抓取单本小说的所以章节名及URL                
197 class ThreadForParseBookPage(threading.Thread):
198     
199     def __init__(self, parent, strThrName):
200         threading.Thread.__init__(self) 
201         self.parent = parent
202         self.strThrName = strThrName
203         
204     def run(self):
205         print("Thread %s is Start!!!" % (self.strThrName))
206         while self.parent.bExit == 0:
207             nSize = self.parent.lsBookInfo.GetSize() 
208             print("ThreadForParseBookPage-->%d" % nSize)
209             if (nSize > 0):
210                 bookInfo = self.parent.lsBookInfo.GetHeadBookInfo()
211                 print("ThreadForParseBookPage->%s" % bookInfo)
212                 PageInfo = getArticlePageContent(bookInfo[1])
213                 print("ThreadForParseBookPage2->%s" % PageInfo)
214                 self.parent.lsBookPageInfo.AddBookPageInfo(bookInfo[0], PageInfo)
215                 self.parent.eventPage.set()
216             else:
217                 print("self.parent.eventBook.wait()")
218                 self.parent.eventBook.wait()
219                 if(nSize <= 0):
220                     self.parent.eventBook.clear()
221                 print("self.parent.eventBook.run()")
222                 
223 #用于抓取单小说的所有章节内容并生成TXT文档保存                
224 class ThreadForDownloadTxt(threading.Thread):
225     
226     def __init__(self, parent, strThrName, nThrNO):
227         threading.Thread.__init__(self) 
228         self.parent = parent
229         self.strThrName = strThrName
230         self.nThrNO = nThrNO
231         
232     def run(self):
233         print("Thread %s%d is Start!!!" % (self.strThrName,self.nThrNO))
234         while self.parent.bExit == 0:
235             nSize = self.parent.lsBookPageInfo.GetSize()
236             print("ThreadForDownloadTxt-->%d" % nSize)
237             if (nSize > 0):
238                 bookPageInfoList = self.parent.lsBookPageInfo.GetHeadBookPageInfo()
239                 print("ThreadForDownloadTxt%d-->%s" % (self.nThrNO,bookPageInfoList))
240                 fileName = 'D:\\txt\\' + bookPageInfoList[0] + '.txt'
241                 file_object = open(fileName, 'w',encoding='utf-8')
242                 for pageInfo in bookPageInfoList[1]:
243                         print("ThreadForDownloadTxt%d-->%s" % (self.nThrNO,pageInfo))
244                         content = getArticleContent(pageInfo[0])
245                         print(content)
246                         file_object.write(pageInfo[1])
247                         file_object.write(str(content))
248                         file_object.flush()
249                 file_object.close()
250             else:
251                 print("self.parent.eventPage.wait()")
252                 self.parent.eventPage.wait()
253                 if(nSize <= 0):
254                     self.parent.eventPage.clear()
255                 print("self.parent.eventPage.run()")
256 
257 cleverBook =  CleverBookSys()              
258         
259         
260         
261         
262         
263         
264         
265         

 

缺点：

1、学习PYTHON两天很多语法以及基础的细节不明白

2、对于不同网站的抓取解析有变动

 

转载于:https://www.cnblogs.com/zbs337650377/p/7110202.html