Last active
July 21, 2017 02:47
-
-
Save jason-xuan/094a6049ebe6cb1f2f99be5b7fbb8035 to your computer and use it in GitHub Desktop.
下载某小说网站的小说的简单代码(单线程)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from re import compile | |
from tqdm import tqdm | |
from bs4 import BeautifulSoup | |
root_url = 'http://www.biquzi.com' | |
def get_urls_from_main_page(url) -> list: | |
result = requests.get(url) | |
result.encoding = 'gbk' | |
text = result.text | |
soup = BeautifulSoup(text, 'lxml') | |
urls = [a['href'] for a in soup.find_all('a')] | |
number = [x for x in url.split('/') if x != ''][-1] | |
model = compile(f'/{number}/') | |
urls = [ root_url + url for url in urls if model.match(url)] | |
return urls | |
def process_page(url) -> str: | |
result = requests.get(url) | |
result.encoding = 'gbk' | |
text = result.text | |
soup = BeautifulSoup(text, 'lxml') | |
title = soup.find('div', 'bookname').h1.text | |
strings = [string.replace('\xa0', '') for string in soup.find(id='content').strings] | |
content = "".join(strings) | |
result = title + '\n' + content + '\n' | |
return result | |
def download(url, path): | |
urls = get_urls_from_main_page(url) | |
with open(path ,'w') as f: | |
for url in tqdm(urls): | |
# keep trying | |
while True: | |
try: | |
text = process_page(url) | |
f.write(text) | |
break | |
except Exception as e: | |
print(e) | |
if __name__ == '__main__': | |
url = 'http://www.biquzi.com/0_32/' | |
path = '全职高手.txt' | |
download(url, path) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment