马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
采集小说到本地生成txt文件,采集网站https://www.xbiquge.la,菜鸟写作,欢迎大家交流学习 QQ:343266695import requests
import os
from lxml import etree
import random
import time
import pymysql
def get_html(url):
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
res = requests.get(url,headers=headers,timeout=600)
res.encoding = res.apparent_encoding
#res.encoding = 'UTF-8'
#res.encoding='gb2312'
htmlmu = res.text
#print(html)
return htmlmu
#获取页面
def get_book(url):
html = get_html(url)
selector = etree.HTML(html)
nov_name = selector.xpath('//*[@id="info"]/h1/text()') #标题
all_urls = selector.xpath('//*[@id="list"]/dl/dd/a/@href') #连接
nov_name = ' '.join(nov_name) # 去除前后[]字符
print(nov_name)
print("匹配到小说共%d章节" % len(all_urls))
k=0
for part_url in all_urls:
k += 1
part_url = f'{www}{part_url}'
booktxt=get_html(part_url)
# print(booktxt.status_code)
selector = etree.HTML(booktxt)
title = selector.xpath('//*[@id="wrapper"]//div//h1/text()') # 标题
content = selector.xpath('//*[@id="content"]/text()') # 作者
content = str(content)
title = ' '.join(title) # 去除前后[]字符
title = title.replace("正文卷", "")
content = content.replace("\\xa0\\xa0\\xa0\\xa0", " ")
content = content.replace("\\r', '\\r', '", "\n\n")
content = content.replace("['", "\n\n")
content = content.replace("………………']", "")
content = content.replace("']", "\n\n")
content = content.replace("<br/>\\ufeff", "\n\n")
content = content.replace("新书就是幼苗,需要大家的呵护才能成长,求推荐票,求收藏,求大家的支持!)", "")
content = content.replace("<br/>【接近6000字的大章,因为里面有不少设定,所以就不断章了,不想看设定可以跳过去,反正也不重要(认真脸)】<br/> ……<br/>",
"<br/>")
new = []
new.append(title)
new.append(content)
down = "./txt/"
if os.path.exists(down) != True:
os.makedirs(down)
print("正在写入第%d章" % k)
with open("./txt/" + nov_name + ".txt", 'a+', encoding='utf-8')as p:
p.writelines(new)
m = random.randint(3,6)
time.sleep(m)
if __name__ == '__main__': #主函数
url="https://www.xbiquge.la/28/28564/"
www="https://www.xbiquge.la"
#url="http://www.shuquge.com/txt/139403/index.html"
# url=input("请输入采集目录地址:")
get_html(url)
get_book(url)
|