当前位置 博文首页 > li5672的专栏:使用python下载一部小说
# -*- coding:UTF-8-*-
from bs4 import BeautifulSoup
import requests
import os
def mkdir(path):
path = path.strip()
isExists = os.path.exists(path)
if not isExists:
os.makedirs(path)
print(path + ' 创建成功')
return True
else:
print(path + ' 目录已存在')
return False
def writer(name, text):
file_name = 'D:\\MySpace\\github\\py-demo\\book\\' + name+'.txt'
with open(file_name, 'a', encoding='utf-8') as f:
f.write(file_name + '\n')
f.writelines(str(text).replace('\xa0'*8, '\n\n').replace('<br/>', ''))
f.write('\n\n')
def download_text(obj):
target = 'http://www.biqukan.com'
req = requests.get(target+obj['url'])
html = req.text
bf = BeautifulSoup(html)
texts = bf.find_all('div', class_='showtxt')
writer(obj['name'], texts)
if __name__ == "__main__":
target = 'https://www.biqukan.com/1_1094/'
req = requests.get(url=target)
req.encoding = 'gb18030'
html = req.text
div_bf = BeautifulSoup(html)
div = div_bf.find_all('div', class_='listmain')
a_bf = BeautifulSoup(str(div[0]))
a = a_bf.find_all('a')
for each in a:
obj = {}
obj['name'] = each.string
obj['url'] = each.get('href')
download_text(obj)
cs