原文來自: https://blog.csdn.net/u012717715/article/details/92811743
本人說明:其實嚴格地這不是轉載,實際上更應該算是原創!原文代碼不能正常運作(我推測準确說應該是:原系統是在MAC中開發的,但在win中有若幹問題),是以才有本文,但是實際上就算在windows中還是有問題沒有完全解決:就是如果儲存資料的檔案夾和檔案已經存在則會有錯誤發生,是以大家使用時如果碰到請手工删除他們。本來是想發在原文的評論中,但是評論篇幅有限,隻能發40行代碼!沒辦法才單獨發的
程式的原理那些請看原文
環境:win10 20h2 19042.804,64位簡體中文版,python-3.9.2,VScode x64 1.53.2
一、要pip install lxml和pip install requests
二、完整代碼修改後如下
# -*- coding:UTF-8 -*-
from bs4 import BeautifulSoup
import requests, sys, threading , os , shutil
"""
類說明:下載下傳《筆趣看》網小說《一念永恒》
Parameters:
無
Returns:
無
Modify:
2017-09-13
"""
class downloader(object):
def __init__(self):
self.server = 'http://www.biqukan.com/'
self.target = 'http://www.biqukan.com/1_1094/'
self.names = [] #存放章節名
self.urls = [] #存放章節連結
self.nums = 0 #章節數
"""
函數說明:擷取章節清單以及對應的下載下傳連結清單
Parameters:
無
Returns:
無
Modify:
2017-09-13
"""
def get_download_url(self):
req = requests.get(url = self.target)
html = req.text
div_bf = BeautifulSoup(req.content,'lxml')
div = div_bf.find_all('div', class_ = 'listmain')
a_bf = BeautifulSoup(str(div[0]),'lxml')
a = a_bf.find_all('a')
self.nums = len(a[13:]) #剔除不必要的章節,并統計章節數
for each in a[13:]:
self.names.append(each.string)
self.urls.append(self.server + each.get('href'))
"""
函數說明:擷取對應章節的内容
Parameters:
target - 下載下傳連接配接(string)
Returns:
texts - 章節内容(string)
Modify:
2017-09-13
"""
def get_contents(self, target):
req = requests.get(url = target)
html = req.text
bf = BeautifulSoup(req.content, 'lxml')
texts = bf.find_all('div', class_ = 'showtxt')
texts = texts[0].text.replace('\xa0'*8,'\n\n')
return texts
"""
函數說明:将爬取的文章内容寫入檔案
Parameters:
name - 章節名稱(string)
path - 目前路徑下,小說儲存名稱(string)
text - 章節内容(string)
Returns:
無
Modify:
2017-09-13
"""
def writer(self, name, path, text):
write_flag = True
with open(path, 'a', encoding='utf-8') as f:
'''
f.write(name + '\n')
f.writelines(text)
'''
tmpstr=name+ '\n'+text
f.write(tmpstr)
f.write('\n\n')
class myThread (threading.Thread): #繼承父類threading.Thread
def __init__(self, name,temdl,startNum,endNum):
threading.Thread.__init__(self)
self.runlist = list()
self.name = name
self.temdl = temdl
self.startNum = startNum
self.endNum = endNum
def run(self): #把要執行的代碼寫到run函數裡面 線程在建立後會直接運作run函數
print ("Starting " + self.name)
startDownloadTxt(self.temdl,self.startNum,self.endNum)
print ("Exiting " + self.name)
def mkdir(path):
'''
判斷路徑是否存在
存在 True
不存在 False
'''
isExists=os.path.exists(path)
if not isExists:
os.makedirs(path)
return True
else:
return False
def subFile(path):
#特定目錄下的檔案清單
docList = os.listdir(path)
# 顯示目前檔案夾下所有檔案并進行排序
'''
key = lambda x:int(x[:-4])
忽略檔案名開始到倒數第四個字元為止
docList.remove(i)
删除數組中點開頭的系統隐藏檔案,因為會影響排序
'''
for i in docList:
if(i[0]=='.'):
docList.remove(i)
break
docList.sort(key = lambda x: int(x[:-4]))
#建立一個以書籍名字命名的檔案
fnamepath = path+'/一念永恒.txt'
fname = open(fnamepath, "w", encoding='utf-8')
#打開你之前命名的下載下傳檔案
for i in docList:
tempath = path+'/'+i
x = open (tempath, "r", encoding='utf-8') #打開清單中的檔案,讀取檔案内容
fname.write(x.read()) #寫入建立的檔案中
x.close() #關閉清單檔案
fname.close()
#移動最後的完成檔案到桌面,在删除download檔案夾(windows環境下根據情況自己修改路徑)
shutil.move(fnamepath, 'c:/Users/lps/Desktop')
shutil.rmtree(path)
'''
temdl:downloader類
startNum,endNum開始和結束的rang
'''
def startDownloadTxt(temdl,startNum,endNum):
mkdir('download')
for i in range(startNum,endNum):
temPath = './download/'+str(i)+'.txt'
tem=temdl.get_contents(temdl.urls[i])
temdl.writer(temdl.names[i], temPath, temdl.get_contents(temdl.urls[i]))
print(temdl.names[i]+'done')
if __name__ == "__main__":
dl = downloader()
#擷取章節清單以及對應的下載下傳連結清單
dl.get_download_url()
print('《一年永恒》開始下載下傳:')
# 建立二十個線程(太多的話,會卡)
threads = []
threadNum = 40
for p in range(threadNum):
threadname = '"Thread'+str(p)
stepNum = dl.nums//threadNum
if(p==threadNum-1):
thread = myThread(threadname,dl,p*stepNum,dl.nums)
else:
thread = myThread(threadname,dl,p*stepNum,(p+1)*stepNum)
threads.append(thread)
try:
# 開啟線程
for t in threads:
t.start()
for t in threads:
t.join()
except:
print ("Error: unable to start thread")
subFile('./download')
print('一念永恒下載下傳完成')