import requests
from bs4 import BeautifulSoup
from urllib import parse
import time
class bqg(object):
def bqg_search(self):
keyword = input("请输入你想搜索的小说关键字或者小说的名字：")
data = {
# 'searchtype':'articlename',
'searchkey': keyword
# 'action':'login',
# 'submit':' 搜 索 '
}
self.data=parse.urlencode(data,encoding='ansi')
res = requests.get(url=self.bqg_search_url, headers=self.headers, params=self.data)
res.encoding = 'gbk'
soup = BeautifulSoup(res.text, 'lxml')
refer_link = soup.find('link')['href'] #获取小说的refer网址
if(soup.find('div',id='list')!=None): #这部分表示只能找到一本小说
lists=soup.find('div',id='list')
list = lists.find('dl')
title=str(list.find('dt').string).replace('正文','') #获取小说的名字
dd = list.find('dd')
first_link=refer_link+dd.find('a')['href']
# print(first_link)
fp=self.creat_file(title)
print("您搜索的小说："+title+" 已找到")
return fp,first_link
elif(soup.find('div',class_='novelslistss').find('li')!=None):
page = soup.find('div', class_='pagelink')
page_count = str(page.find('em').string).split('/')[1].strip()
page_link = page.find('a')['href']
name_list=[]
link_list=[]
for i in range(1, int(page_count) + 1):
listl,listn=self.many_pageparse('https://www.52bqg.com/' + str(page_link).replace('1', str(i)))
for link in listl:
link_list.append(link)
for name in listn:
name_list.append(name)
count=1
for name in name_list:
print((str(count)+'.'+name).ljust(15))
count+=1
novel_index=int(input("请输入你想要下载的小说编号"))
print("你选择的是"+' '+str(novel_index)+name_list[novel_index-1])
print(name_list[novel_index-1]+" 即将开始下载")
res=requests.get(link_list[novel_index-1],headers=self.headers)
res.encoding='gbk'
soup = BeautifulSoup(res.text, 'lxml')
refer_link = soup.find('link')['href']
lists = soup.find('div', id='list')
list = lists.find('dl')
title = str(list.find('dt').string).replace('正文', '') # 获取小说的名字
dd = list.find('dd')
first_link = refer_link + dd.find('a')['href']
# print(first_link)
fp = self.creat_file(title)
return fp, first_link
elif(soup.find('div',class_='novelslistss').find('li')==None and soup.find('div',id='list')==None):
print("对不起，您搜索的关键字："+keyword+" 没有找到，请换一个试试吧")
answer=input("是否取消搜索，并转用其他接口进行搜索 输入Y/N(忽略大小写)")
if answer.startswith('Y') or answer.startswith('y'):
# print("系统将跳转到其他网站进行下载")
return None
else:
print("该网站没有找到您想看的小说，可以尝试换一部哦")
return 1
def many_pageparse(self,url):
res=requests.get(url=url,headers=self.headers)
res.encoding='gbk'
soup=BeautifulSoup(res.text,'lxml')
novelslistss = soup.find('div', class_='novelslistss')
result_name = novelslistss.find('h2').string
lis = novelslistss.find_all('li')
link_list = []
name_list = []
for li in lis:
span2 = li.find('span', class_='s2')
a = span2.find('a')
novel_title = a.string
href = a['href']
name_list.append(novel_title)
link_list.append(href)
return link_list,name_list
# count = 1
# for name in link_list:
# print(str(count) + ' ' + name, end='')
# if (count % 4 == 0):
# print('n')
# count += 1
def get_content(self,url):
res=requests.get(url=url,headers=self.headers)
res.encoding='gbk'
soup=BeautifulSoup(res.text,'lxml')
book_name=soup.find('div',class_="bookname")
bookname=book_name.find('h1').string #获取章节名
# print(bookname)
bookname='rr'+bookname+'n'
list_novel=[]
contents=soup.find('div',attrs={'id':'content','name':'content'})
novel_content=contents.strings
for content in novel_content:
list_novel.append(str(content))
list_novel.insert(1,bookname.replace('《','').replace('》',''))
novel_list=[]
for line in list_novel:
novel_list.append(str(line).rstrip())
# print(novel_list[1:])
return novel_list[1:]
def get_next_url(self,url):
res=requests.get(url=url,headers=self.headers)
res.encoding='gbk'
soup=BeautifulSoup(res.text,'lxml')
bottem=soup.find('div',class_='bottem')
next_link=list(bottem.find_all('a'))[3]['href']
return next_link
def down_load(self):
try:
fp, first_link = self.bqg_search()
except:
# if(fp==None or first_link==None):
print("系统操作异常，请稍后重试")
return 0
while(1):
try:
conten_list = self.get_content(first_link)
fp.writelines(conten_list)
link = first_link
print("正在下载"+' '+conten_list[0].strip())
first_link = self.get_next_url(first_link)
except:
fp.write("最后一次下载链接：n" + link)
break
print(fp.name+"已经下载完毕")
time.sleep(5000)
return 0
def creat_file(self,file_name):
fp=open(r'D:/novels/'+file_name+'.txt','a+',encoding='utf-8')
return fp
def main(self):
while 1:
self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.163 Safari/537.36'}
self.bqg_search_url = 'https://www.52bqg.com/modules/article/search.php?searchkey='
try:
self.down_load()
except:
print("系统发生异常，请重试")
finally:
flage = input("您是否要继续下载小说？ 请输入Y/N(忽略大小写)")
if flage.startswith('N') or flage.startswith('n'):
print("欢迎下次使用")
break
else:
self.main()
# self.get_content('https://www.52bqg.com/book_80265/23413578.html')
if __name__ == '__main__':
try:
novel = bqg()
novel.main()
except:
print("系统将跳转到其他网站进行下载")
