import requests
from bs4 import BeautifulSoup
import lxml #解析器
url = "https://www.biqukan.com/0_790/67139352.html"
#访问网页
req = requests.get(url = url)
#更改字符级设定,避免出现乱码
req.encoding = "gbk"
#查看相应码 200成功
print(req.status_code)
#获取内容
html = req.text
print(html)
#解析网站
bf = BeautifulSoup(html, "lxml")
#解析需要的div
div = bf.find_all("div", class_ = "showtxt")
print(div)
#存储
txt = div[0].text
i = 0
#修改文本格式
txt = txt.replace(" ", '\n\n')
# while txt[i]:
# if i % 80 == 0:
# txt.insert(i + 1, '\n')
# i = i + 1
# i += 1
print(txt)
with open("小说.text", "w", encoding="utf-8") as file:
file.write(txt)
file.close()
python3 爬取单章节小说并存取
猜你喜欢
转载自blog.csdn.net/AK47red/article/details/103748857
今日推荐
周排行