from bs4 import BeautifulSoup
import requests
import sys
import re
class downloader(object):
def __init__(self):
self.server = 'http://www.biqukan.com/'
self.target = 'http://book.zongheng.com/showchapter/881459.html'
self.names = [] #存放章節名
self.urls = [] #存放章節鏈接
self.nums = 0
# 獲取下載鏈接
def get_download_url(self):
req = requests.get(url=self.target) #獲取網頁
bf = BeautifulSoup(req.content, 'lxml') #決議網頁
texts = bf.find('div', class_="container")#查找網頁
all_a = texts.find_all('a')
del all_a[0:5]
self.nums = len(all_a)
for x in all_a:
self.names.append(x.string)
self.urls.append(x.get('href'))
# print(x.string, x.get('href'))
# 下載章節內容
def get_contents(self, target):
req = requests.get(url = self.target)
bf = BeautifulSoup(req.content, 'lxml')
texts = bf.find('div', class_="content")
return texts
# 寫入檔案
def writer(self, name, path, text):
write_flag = True
with open(path, 'a', encoding='utf-8') as f:
f.write(name + '\n')
f.writelines(text)
f.write('\n\n')
if __name__ == "__main__":
dl = downloader()
dl.get_download_url()
print('《星際超級獵人》開始下載：')
path = r'D:\\星級超級獵人.txt'
for i in range(dl.nums):
dl.writer(dl.names[i], path, dl.get_contents(dl.urls[i]))
sys.stdout.write(" 已下載:%.3f%%" % float(i/dl.nums) + '\r')
sys.stdout.flush()
print('《星際超級獵人》下載完成')
*********************************************************
《星際超級獵人》開始下載：
Traceback (most recent call last):
File "D:\A_python_work\test.py", line 49, in <module>
dl.writer(dl.names[i], path, dl.get_contents(dl.urls[i]))
File "D:\A_python_work\test.py", line 39, in writer
f.writelines(text)
TypeError: 'NoneType' object is not iterable
**********************************************************
源代碼與結果如上，提示型別錯誤，希望哪位朋友指點下？
uj5u.com熱心網友回復：
自問自答，型別錯誤是text格式有問題，改為text=str(text)即可轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/82706.html