python爬虫笔记（八） 实例3：用Python批量爬取全站小说【以书趣阁为例】

1. 用Python批量爬取全站小说

爬取这个网站小说：http://www.shuquge.com/txt/89644/index.html

2. 爬取一本书

# -*- coding: utf-8 -*-
"""
Created on Sat Feb  8 20:31:43 2020

@author: douzi
"""

import requests
from parsel import Selector
import re
import time
    

def main():
    index_url = 'http://www.shuquge.com/txt/89644/index.html'  # 想要爬取的小说
    tpl = 'http://www.shuquge.com/txt/89644/'   
    
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36"}
    
    # 获取小说目录页
    urllist = requests.get(index_url, headers=headers)
    index_sel = Selector(urllist.text)
    # 
 
《九星毒奶》最新章节
1040 养龙皮？
    index = index_sel.css('.listmain a::attr(href)').getall()
    # 保存10章节
    for n in index:
        url = tpl + n
        
        # 第 n 章
        response = requests.get(url, headers=headers, timeout=30)
        response.encoding = response.apparent_encoding
        
        print(response.request.url)
        # xpath css 选择器 提取网页数据结构（html） 
        # lxml pyquery parsel
        sel = Selector(response.text)
        title = sel.css('h1::text').get()
        print(title)
        match = re.search(r'[0-9]*', title.split()[0])
        if match:
            with open("./jiuxin/" + match.group(0) + '.txt', 'w', encoding = 'utf-8') as f:
                f.writelines(title)
                # 

                for line in sel.css('#content::text').getall():
                    f.writelines(line)
        time.sleep(0.5)
    
if __name__ == '__main__':
    main()   

 

3. 爬取一个分类

# -*- coding: utf-8 -*-
"""
Created on Sat Feb  8 20:31:43 2020

@author: douzi
"""

import requests
from parsel import Selector
import re
import time
import os


headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36"}

# 下载一章节
def download_one_chapter(url, book_name):
    # 第 n 章
    response = requests.get(url, headers=headers, timeout=30)
    response.encoding = response.apparent_encoding
    
    print(response.request.url)
    # xpath css 选择器 提取网页数据结构（html） 
    # lxml pyquery parsel
    sel = Selector(response.text)
    title = sel.css('h1::text').get()
    print(title)
    with open('./'+book_name+'/'+title+'.txt','a+', encoding = 'utf-8') as f:
        f.writelines(title)
        # 

        for line in sel.css('#content::text').getall():
            f.writelines(line)
        f.write('\n\0')
        
    time.sleep(0.5)

# 下载一本书
def download_one_book(index_url, bname):
#    index_url = 'http://www.shuquge.com/txt/89644/index.html'  # 想要爬取的小说:例，九星毒奶
    book_name = re.split('/', index_url)[-2]  # 例: 89644
    tpl = 'http://www.shuquge.com/txt/' + book_name + '/'
    
    # 获取小说目录页
    urllist = requests.get(index_url, headers=headers)
    urllist.encoding = urllist.apparent_encoding
    
    index_sel = Selector(urllist.text)
    # 
 
《九星毒奶》最新章节
1040 养龙皮？
    index = index_sel.css('.listmain a::attr(href)').getall()
    
    for n in index:
        url = tpl + n
        download_one_chapter(url, bname)
        
# 下载一类别
def download_one_category():
    tpl = 'http://www.shuquge.com/category/7_{}.html'  # 想要爬取的类别
    
    # 3页
    for page in range(1, 4):
        category_url = tpl.format(page)
        print(category_url)
        # 获取小说类别页
        cate_list = requests.get(category_url, headers=headers)
        cate_list.encoding = cate_list.apparent_encoding
        
        index_sel = Selector(cate_list.text)
       
        books_url = index_sel.css('span.s2 a::attr(href)').getall()
        books_name = index_sel.css('span.s2 a::text').getall()
       
        for book_url in books_url:
            # 如：变成随身老奶奶 http://www.shuquge.com/txt/109203/index.html
            book_name = books_name[books_url.index(book_url)]
            print(book_name, book_url)
            if os.path.isdir('./' + book_name):
                os.removedirs(book_name)
            else:
                os.mkdir('./' + book_name)
            # 下载一本书
            download_one_book(book_url, book_name)
    
if __name__ == '__main__':
#    download_one_book('asd')
    download_one_category()