用Python爬取小说《一念永恒》

　　我们首先选定从笔趣看网站爬取这本小说。

 

　　然后开始分析网页构造，这些与以前的分析过程大同小异，就不再多叙述了，只需要找到几个关键的标签和user-agent基本上就可以了。

　　那么下面，我们直接来看代码。

from urllib import request
from bs4 import BeautifulSoup
import re
import sys

if __name__ == "__main__":
    #创建txt文件
    file = open('一念永恒.txt', 'w', encoding='utf-8')
    #一念永恒小说目录地址
    target_url = 'http://www.biqukan.com/1_1094/'
    head = {}
    head['User-Agent'] = 'Mozilla/5.0 (Linux; Android 4.1.1; Nexus 7 Build/JRO03D) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166  Safari/535.19'
    target_req = request.Request(url = target_url, headers = head)
    target_response = request.urlopen(target_req)
    target_html = target_response.read().decode('gbk','ignore')
    listmain_soup = BeautifulSoup(target_html)
    #找出div标签中class为listmain的所有子标签
    chapters = listmain_soup.find_all('div',class_ = 'listmain')
    download_soup = BeautifulSoup(str(chapters))
    #计算章节个数
    numbers = (len(download_soup.dl.contents) - 1) / 2 - 8
    index = 1
    begin_flag = False
    for child in download_soup.dl.children:
        if child != '\n':
            #找到《一念永恒》正文卷
            if child.string == u"《一念永恒》正文卷":
                begin_flag = True
            #爬取链接并下载链接内容
            if begin_flag == True and child.a != None:
                download_url = "http://www.biqukan.com" + child.a.get('href')
                download_req = request.Request(url = download_url, headers = head)
                download_response = request.urlopen(download_req)
                download_html = download_response.read().decode('gbk','ignore')
                download_name = child.string
                soup_texts = BeautifulSoup(download_html)
                texts = soup_texts.find_all(id = 'content', class_ = 'showtxt')
                soup_text = BeautifulSoup(str(texts))
                write_flag = True
                file.write(download_name + '\n\n')
                #将爬取内容写入文件
                for each in soup_text.div.text.replace('\xa0',''):

                    if each == 'h':
                        write_flag = False
                    if write_flag == True and each != ' ':
                        file.write(each)
                    if write_flag == True and each == '\r':
                        file.write('\n')
                    print('正在写入第{0}小节'.format(index))
                    index+=1
                file.write('\n\n')
                #打印爬取进度
                sys.stdout.write("已下载:%.3f%%" % float(index/numbers) + '\r')
                sys.stdout.flush()
                index += 1
    file.close()

 　　这个代码可能还存在着一些小问题，但是并不影响我们爬取小说，下面来看看我们的运行结果。