自己在论坛上面找了一份python3爬虫的代码,但是比照着写就出现了上面的问题,求助大家帮我看一下。
import requests
from bs4 import BeautifulSoup
"""
说明:下载《笔趣阁》小说《一念永恒》
parameter:
无
Return:
无
Modify:
2019-06-27
"""
class downloader(object):
def init(self):
self.server='https://www.biqukan.com/'
self.url='https://www.biqukan.com/1_1094/'
self.name=[]
self.urls=[]
self.nums=0
"""
函数说明:获取下载链接
Parameters:
无
Returns:
无
Modify:
2019-06-27
"""
def get_download_url(self):
resp = requests.get(url)
html=resp.text
resp.encoding=resp.apparent_encoding
if html:
with open('test.html',mode='a+',encoding=resp.apparent_encoding) as file:
file.write(html)
div_bf = BeautifulSoup(html)
div=div_bf.find_all('div', class_ = 'listmain')
a_bf = BeautifulSoup(str(div[0]))
a = a_bf.find_all('a')
self.nums=len(a[15:])
for each in a[15:]:
self.names.append(each.string)
self.urls.append(self.server+each.get('href')
"""
函数说明:获取章节内容
Parameters:
url - 下载连接(string)
Returns:
texts - 章节内容(string)
Modify:
2019-6-27
"""
def get_contents(self, url):
req = requests.get(url)
html = resp.text
bf = BeautifulSoup(html)
texts = bf.find_all('div', class_ = 'showtxt')
texts = texts[0].text.replace('\xa0'*8,'\n\n')
return texts
"""
函数说明:将爬取的文章内容写入文件
Parameters:
name - 章节名称(string)
path - 当前路径下,小说保存名称(string)
text - 章节内容(string)
Returns:
无
Modify:
2019-06-27
"""
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')
dl = downloader()
dl.get_download_url()
print('《一年永恒》开始下载:')
for i in range(dl.nums):
dl.writer(dl.names[i], '一念永恒.txt', dl.get_contents(dl.urls[i]))
sys.stdout.write("已下载:%.3f%%" % float(i/dl.nums) + '\r')
sys.stdout.flush()
print('《一年永恒》下载完成')