最近一直在找横练加点升级流小说发现有一本《武侠:开局横练童子功》的小说看起来还不错,但是找遍全网大部分都是飞卢的,所以你懂的0.0 ,后便找了能看书的网站自己爬~~~。话不多说上代码:
from urllib import request
from urllib import request
from fake_useragent import FakeUserAgent
from bs4 import BeautifulSoup
from urllib.request import urlopen#用于获取网页
from bs4 import BeautifulSoup#用于解析网页
html = urlopen('https://www.56bok.com/list/190/190727.html')
bsObj = BeautifulSoup(html, 'html.parser')
t1 = bsObj.find_all('a')
for t2 in t1:
t3 = t2.get('onclick')
t4=str(t3)
t5=t4[13:46]
server = 'https://www.56bok.com'
t6=server +t5
from urllib import request
from fake_useragent import FakeUserAgent
if __name__ == '__main__':
url=t6
headers = {
'user-agent': FakeUserAgent().random
}
# 1、创建请求对象,包装ua信息
req = request.Request(url,headers=headers)
# 2、发送请求,获取响应对象
res = request.urlopen(req)
# 3、提取响应内容
html = res.read().decode('gb18030')
bs = BeautifulSoup(html, 'html.parser')
# br1=bs.find('div',class_ = 'back_r190727')
for element1 in bs.select("div[class='Al63OkVPyD']"):
aa=str(element1)
for element2 in bs.select("div[class='back_r190727']"):
# print( element)
ab=str(element2)
ac=aa+ab
# print(ac)
# for string in bs.stripped_strings:
with open("武侠:开局横练童子功.txt","a",encoding='UTF-8') as f:
f.write(ac)
备注:若是想怕网站别的小说要把"div[class='back_r190727']"标签地址换一下就ok了。