元尊 python

直接上源码

// An highlighted block
import requests
import sys
from bs4 import BeautifulSoup

"""
下载笔趣阁小说元尊


"""





class Downloader(object):

    def __init__(self):
        self.server = 'http://www.biqu.ge/'
        self.target = 'http://www.biqu.ge/0/214/'
        self.names = []  # 存放章节名
        self.url = []  # 存放章节链接
        self.nums = 0  # 章节数

    def get_download_url(self):
        req = requests.get(url=self.target).content.decode('utf-8')
        html = req
        div_bf = BeautifulSoup(html, 'lxml')
        div = div_bf.find_all('div', id="list")
        a_bf = BeautifulSoup(str(div[0]), 'lxml')
        a = a_bf.find_all('a')
        self.nums = len(a[10:])  # 删除不必要的章节
        for each in a[10:]:
            self.names.append(each.string)
            self.url.append(self.server + str(each.get('href')))

    def get_contents(self,target):
        req = requests.get(url=target)
        html = req
        bf = BeautifulSoup(html.content, features='lxml')
        texts = bf.find_all('div', class_="acontent")
        texts = texts[0].text.replace('<br/>', '\n\n')
        return texts

    def writer(self,name, path, text):
        writer_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("元尊开始下载")
    for i in range(dl.nums):
        for i in range(dl.nums):
            dl.writer(dl.names[i], '元尊.txt', dl.get_contents(dl.url[i]))
            sys.stdout.write("  已下载:%.3f%%" % float(i / dl.nums) + '\r')
            sys.stdout.flush()

    print('下载完成')

本文地址：https://blog.csdn.net/csdnzhaozhao/article/details/107648585