通过python爬取笔趣阁小说，获取图片保存本地，数据保存mysql

通过python爬取小说图片、小说名称、作者、章节、内容。直接上代码

import requests
import time
from bs4 import BeautifulSoup
from queue import Queue
import threading
import pymysql
from DBUtils.PooledDB import PooledDBproxy='124.243.226.18:8888'#如果代理需要验证，只需要在前面加上用户名密码，如下所示# proxy='username:password@124.243.226.18:8888'
proxies={'http':'http://119.140.186.17:894','http':'http://27.24.20.22:766','http':'http://114.98.189.158:766','http':'http://114.101.246.185:23564'
}pool = PooledDB(creator=pymysql,maxconnections=0,  # 连接池允许的最大连接数，0和None表示不限制连接数mincached=10,  # 初始化时，链接池中至少创建的空闲的链接，0表示不创建maxcached=0,  # 链接池中最多闲置的链接，0和None不限制blocking=True,  # 连接池中如果没有可用连接后，是否阻塞等待。True，等待；False，不等待然后报错host='47.106.122.177',  # 数据库ip地址port=3306,user='root',passwd='123456',db='zskxt',use_unicode=True,charset='utf8')send_headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36","Connection": "keep-alive","Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8","Accept-Language": "zh-CN,zh;q=0.8"
}  # 伪装成浏览器#获取小说URL列表
def huoquxiaoshuo():search_real_url = 'http://www.xbiquge.la/xiaoshuodaquan/'try:html = requests.get(search_real_url).texthtmlTree = BeautifulSoup(html, 'html.parser')url_list=htmlTree.find(id='main').find_all('a')print(url_list[0]);urlreutrn = []for url in url_list:urlreutrn.append(url.attrs['href'])return urlreutrnexcept Exception as e:print(e)class Producer(threading.Thread):def __init__(self, url_queue , *args, **kwargs):super(Producer, self).__init__(*args, **kwargs)self.url_queue = url_queuedef run(self):# 获取小说目录try:while True:if self.url_queue.empty():breakurl=self.url_queue.get()while True:try:text = requests.get(url,send_headers)except Exception as e:print(e)continuetext.encoding = 'utf-8'novel_source=text.texthtmlTree = BeautifulSoup(novel_source, 'html.parser')print(htmlTree.title);if str(htmlTree.title).find('503')==-1:breakelse :time.sleep(1)img = htmlTree.find(id='fmimg').find_all('img')#print(img)#保存图片while True:try:response = requests.get(img[0].get('src'),send_headers)except Exception as e:print(e)continue# 获取的文本实际上是图片的二进制文本imgxr = response.contentif len(imgxr) <300:time.sleep(1)else :break# 将他拷贝到本地文件 w 写  b 二进制  wb代表写入二进制文本imgxrlist=[]imgxrlist=img[0].get('src').split("/")bookmsimg=imgxrlist[len(imgxrlist) - 1]with open('d:\\img\\'+bookmsimg, 'wb') as f:f.write(imgxr)id=url.split("/")bookid=id[len(id) - 2]bookname=htmlTree.find(id='info').find('h1').stringbookzz = htmlTree.find(id='info').find_all('p')[0].string.replace('作    者：','')bookms = htmlTree.find(id='intro').find_all('p')[1].stringbookms=bookms.replace("'","\'")sql="insert into zsk_book_sm (bookid,bookname,zz,zhgxsj,msnr,tp) values ('xbqg"+bookid+"','"+bookname+"','"+bookzz+"',now(),'"+bookms+"','"+bookmsimg+"')"db = pool.connection()  # 连接数据池cursor = db.cursor()  # 获取游标try:cursor.execute(sql)db.commit()except Exception as e:print("SQL ERROR！", e)db.rollback()#finally:#cursor.close()#db.close()bookzjlisturl=[]bookzjlist=htmlTree.find(id='list').find_all('a')for url in bookzjlist:urlzj=str(url.get('href'))zjid=urlzj.split("/")[3].replace(".html", "")#获取章节内容while True:try:time.sleep(1)#nrtext = requests.get('http://www.xbiquge.la/2/2210/1744317.html', send_headers)nrtext = requests.get('http://www.xbiquge.la'+urlzj, send_headers)#nrtext = requests.get('http://www.xbiquge.la' + urlzj, send_headers, proxies=proxies)except Exception as e:print(e)continuenrtext.encoding = 'utf-8'nrnovel_source = nrtext.textnrhtmlTree = BeautifulSoup(nrnovel_source, 'html.parser')print(nrhtmlTree.title);if str(nrhtmlTree.title).find('503') == -1:breakelse:time.sleep(1)content=nrhtmlTree.find(id='content')#if str(content).index("</p>")!=-1:#   nrhtmlTree.find('p').decompose()a=str(content).replace("<div id=\"content\">","").replace("</div>","")a=a.replace("'","")nrsql = "INSERT INTO `zsk_book_content` (`id`, `content`) VALUES ('" +zjid + "', '" + a + "')"zjsql ="INSERT INTO zsk_book_ml (mlid, zjmc, bookid, content_id, is_delete, words) VALUES ('"+ zjid + "', '" + url.text + "', '" +bookid+ "', '" + urlzj.split("/")[3].replace(".html", "") + "', 0, 1)";try:cursor.execute(zjsql)cursor.execute(nrsql)db.commit()except Exception as e:print("SQL ERROR！", e)db.rollback()#finally:#cursor.close()#db.close()except Exception as e:print(e)if __name__ == '__main__':url_list=huoquxiaoshuo();print(url_list[0]);url_queue = Queue(len(url_list))for url in url_list:url_queue.put(url)for x in range(3):t = Producer(url_queue)t.start()# book_name = input('请输入你要下载的小说名字(确保输入的小说名字正确)：')# novel_url, novel_name = download(book_name)# chapter_list = get_chapter(novel_url)# get_content(chapter_list, novel_name)

数据库结构如下

Target Server Type    : MYSQL
Target Server Version : 50562
File Encoding         : 65001Date: 2020-03-28 12:32:08
*/SET FOREIGN_KEY_CHECKS=0;
-- ----------------------------
-- Table structure for `zsk_book_content`
-- ----------------------------
DROP TABLE IF EXISTS `zsk_book_content`;
CREATE TABLE `zsk_book_content` (
`id`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL DEFAULT '' COMMENT '内容id' ,
`content`  text CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '章节内容' ,
PRIMARY KEY (`id`)
)
ENGINE=InnoDB
DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;-- ----------------------------
-- Table structure for `zsk_book_ml`
-- ----------------------------
DROP TABLE IF EXISTS `zsk_book_ml`;
CREATE TABLE `zsk_book_ml` (
`mlid`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL COMMENT '目录id' ,
`zjmc`  varchar(200) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '目录章节名称' ,
`bookid`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL DEFAULT '' COMMENT '书id' ,
`content_id`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '文章内容id' ,
`is_delete`  int(11) NULL DEFAULT NULL COMMENT '删除标识' ,
`words`  int(11) NULL DEFAULT NULL COMMENT '字数' ,
`ctime`  timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP COMMENT '创建时间' ,
`mtime`  timestamp NOT NULL DEFAULT '0000-00-00 00:00:00' COMMENT '修改时间' ,
PRIMARY KEY (`mlid`, `bookid`)
)
ENGINE=InnoDB
DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;-- ----------------------------
-- Table structure for `zsk_book_sm`
-- ----------------------------
DROP TABLE IF EXISTS `zsk_book_sm`;
CREATE TABLE `zsk_book_sm` (
`bookid`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NOT NULL COMMENT '书id' ,
`bookname`  varchar(100) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '书名' ,
`zz`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '作者' ,
`zhgxsj`  timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP COMMENT '最后更新时间' ,
`tp`  varchar(500) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '封面' ,
`zxzj`  varchar(100) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '最新章节' ,
`zxzjid`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '最新章节id' ,
`msnr`  varchar(500) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '描述内容' ,
`lb`  varchar(50) CHARACTER SET utf8 COLLATE utf8_general_ci NULL DEFAULT NULL COMMENT '类别' ,
PRIMARY KEY (`bookid`)
)
ENGINE=InnoDB
DEFAULT CHARACTER SET=utf8 COLLATE=utf8_general_ci;

通过python爬取笔趣阁小说，获取图片保存本地，数据保存mysql相关推荐

python爬取笔趣阁小说（附源码）
python爬取笔趣阁小说文章目录 python爬取笔趣阁小说前言一.获取小说目录结构获取目录连接请求代码解析目录 XPath tqdm 解析二.获取小说章节结构请求代码解析章节代 ...
python爬取小说爬取_用python爬取笔趣阁小说
原标题:用python爬取笔趣阁小说首先打开笔趣阁网址,链接,搜索自己想要的小说. 在网站内单击右键,点击检查,会出现如下界面! 我们需要的章节信息就在我划的这块, 可以将每个标签点一下,它对应的内 ...
1.python爬取笔趣阁小说
前一阵无聊想学习python,就有了以下代码,选取了笔趣阁这个大众化的网站,百度发现以笔趣阁为名的小说网站很多,本段代码只在百度结果里选取前五条,并选取了三个叫笔趣阁的网站,前五条里包含笔趣阁的任意一 ...
Python爬取笔趣阁小说，有趣又实用！
上班想摸鱼?为了摸鱼方便,今天自己写了个爬取笔阁小说的程序.好吧,其实就是找个目的学习python,分享一下. 1. 首先导入相关的模块 import os import requests from ...
用python爬取笔趣阁小说并分章节保存到本地
在宿舍无聊时想做点小程序,刚好又看到笔趣阁的广告,就想着爬一下小说看看,通过网上的爬取教程整理的使用beautifulsoup解析request获取的HTML http://beautifulsou ...
Python爬取笔趣阁小说2.0版
之前的爬虫文章中,我们只可以爬取某本特定的小说,小波大叔一般喜欢看玄幻和修真类的,那么想把这一类小说全部爬下来该怎么操作呢,2.0版本来了,依然还是笔趣阁网站,初学者而言,这个没有反扒机制,比较方便. ...
BeautifulSoup爬取笔趣阁小说并下载到本地
首先打开笔趣阁网址随便选一篇小说先请求网址拿到网页的数据代码如下: def __init__(self):#http://www.biquyun.com/14_14055/9195936.html# ...
1-4 python爬取笔趣阁小说（附带完整代码）
笔趣看是一个盗版小说网站,这里有很多起点中文网的小说,该网站小说的更新速度稍滞后于起点中文网正版小说的更新速度.并且该网站只支持在线浏览,不支持小说打包下载.所以可以通过python爬取文本信息保存, ...
python爬取笔趣阁小说的代码微小调整修改
原文来自: https://blog.csdn.net/u012717715/article/details/92811743 本人说明:其实严格地这不是转载,实际上更应该算是原创!原文代码不能正常 ...

通过python爬取笔趣阁小说，获取图片保存本地，数据保存mysql

通过python爬取笔趣阁小说，获取图片保存本地，数据保存mysql相关推荐

最新文章

热门文章