2019新年爬本小说看看

标签：blog   sts   tail   pen   内容   return   cti   wrap   ace   

#_author_=‘LaoHan‘;
#date:  2019/2/11
# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup
import requests
import codecs
def get_url_list(url):
    begin_html = requests.get(url)
    soup = BeautifulSoup(begin_html.content, ‘lxml‘)
    #begin_html.content如果换成begin_html.text会有乱码
    #后来查了下为什么，可以参考下面这个链接
    # https://blog.csdn.net/qq_38900441/article/details/79946377
    url_list = []
    list = soup.select("#list > dl > dd > a")
    #访问主页返回信息中的所有a标签中的内容
    for i in list:
        i = i.get("href")
        #print(i)
        i = ‘http://www.biqugecom.com‘ + i
        url_list.append(i)
    url_list = url_list[9:-1]
    print (url_list)
    return url_list
def get_data(url):
    html = requests.get(url)
    soup = BeautifulSoup(html.content, ‘lxml‘)
    book = codecs.open(‘output.txt‘, ‘a+‘, ‘utf-8‘);
    # 以二进制写入章节题目 需要转换为utf-8编码，否则会出现乱码
    section_name = soup.select("#wrapper > div.content_read > div > div.bookname > h1")[0].text
    print (section_name)
    book.write((‘\r\n‘ + section_name + ‘\r\n‘))
    section_text = soup.select("#content")
    for page in section_text:
        a = page.text.replace(‘readx();‘, ‘‘).replace(‘www.biqugecom.com/20/20341/‘, ‘‘)
        book.write((a)+ ‘\r\n‘)
    # 以二进制写入章节内容
    book.close()  # 关闭小说文件
if ‘__main__‘ == __name__:
    url = ‘http://www.biqugecom.com/34/34055/‘
    url_list = get_url_list(url)
    for n in url_list:
        get_data (n)

2019新年爬本小说看看

标签：blog   sts   tail   pen   内容   return   cti   wrap   ace   

原文地址：https://www.cnblogs.com/pytest/p/10362342.html