python爬取小说（四）代码优化

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/MTbaby/article/details/82557442

为方便后续做前端展示，本次主要优化章节字段根据爬取顺序入库，各功能函数模块化。

# -*- coding: utf-8 -*-
import urllib.request
import bs4
import re
import sqlite3
import time
print ('连接数据库……')
cx = sqlite3.connect('PaChong.db')
# 在该数据库下创建表

# cx.execute('''CREATE TABLE book_info(
#        id INTEGER PRIMARY KEY   AUTOINCREMENT,
#        title             verchar(128)     not null,
#        img             verchar(512)      null,
#        auther         verchar(64)      null,
#        type             verchar(128)      null,
#        status             verchar(64)      null,
#        num             int      null,
#        updatatime             datetime      null,
#        newchapter             verchar(512)      null,
#        authsummery             verchar(1024)      null,
#        summery            verchar(1024)      null,
#        notipurl             verchar(512)      null);
#        ''')
# cx.execute('''CREATE TABLE book_chapter(
#        id INTEGER PRIMARY KEY   AUTOINCREMENT,
#        book_id         int      null ,
#        chapter_no         int      null ,
#        chapter_name             verchar(128)      null,
#        chapter_url             verchar(512)      null,
#        chapter_content         text      null);
#        ''')

print("Table created successfully")
print("数据库连接完成")

def getHtml(url):
    user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36"
    headers = {"User-Agent":user_agent}
    request = urllib.request.Request(url,headers=headers)
    response = urllib.request.urlopen(request)
    html = response.read()
    return html


# 爬取整个网页
def parse(url):
    html_doc = getHtml(url)
    sp = bs4.BeautifulSoup(html_doc, 'html.parser', from_encoding="utf-8")
    return sp
# 爬取书籍基本信息
def get_book_baseinfo(url):
    # class = "info"信息获取
    info = parse(url).find('div', class_='info')
    book_info = {}  # 存储书籍所有基本信息
    pre_small = []  # 存储处理前的信息
    aft_small = []  # 存储使用分号切割后的信息
    pre_intro = []  # 存储简介开始之后的信息

    if info:
        # print(info)
        book_info['title'] = ''
        book_info['img'] = ''
        # 标题
        book_info['title'] = info.find('h2').string

        # 图片链接
        img = info.find('div',class_ = 'cover')
        for im in img.children:
            # 图片地址想要访问，显然需要拼接
            book_info['img'] = 'http://www.biqukan.com' + im.attrs['src']

        # 作者，分类，状态，字数，更新时间，最新章节
        ifo = info.find('div',class_ = 'small')
        for b in ifo:
            for v in b.children:
                t = v.string
                if t:
                    pre_small.append(''.join(t))

        # 将：后面的信息连起来
        cv = ''
        for v in pre_small:
            if v.find('：') >= 0:
                if cv:
                    aft_small.append(cv)
                cv = v
            else:
                cv += v
        aft_small.append(cv)

        # 基本信息转成字典
        for element in aft_small:
            its = [v.strip() for v in element.split('：')]
            if len(its) != 2:
                continue
            nm = its[0].lower()  # 统一成小写
            if type(nm).__name__ == 'unicode':
                nm = nm.encode('utf-8')
            vu = its[1]
            book_info[nm] = vu
        # 发现这里获取到的字典键与后面将要获取的键重复了，所以这里改一下
        book_info['auther'] = book_info.pop('作者')

        # 简介获取()
        intro = info.find('div',class_ = 'intro')
        for b in intro:
            t = b.string
            if t:
                pre_intro.append(''.join(t))
    ext_info = extract_book_ext_info(''.join(pre_intro))
    # 使用笨办法将字典的key转成英文状态，这样方便数据库存储
    book_info['type'] = book_info.pop('分类')
    book_info['status'] = book_info.pop('状态')
    book_info['num'] = book_info.pop('字数')
    book_info['updatatime'] = book_info.pop('更新时间')
    book_info['newchapter'] = book_info.pop('最新章节')
    # 注意，以下三个是extract_book_ext_info函数返回
    book_info['authsummery'] = ext_info['作者']
    book_info['summery'] = ext_info['简介']
    book_info['notipurl'] = ext_info['无弹窗推荐地址']
    print("正在获取书籍【{}】".format(book_info['title']))
    return book_info

# 简介、作者介绍、无弹窗地址获取
def extract_book_ext_info(ext_text):
    tag = ['简介：', '作者：', '无弹窗推荐地址：']

    # 查找分片位置
    pos = []
    cur_pos = 0
    for t in tag:
        tpos = ext_text.find(t, cur_pos)
        pos.append(tpos)

    # 分片
    cur_pos = 0
    items = []
    for i in range(len(tag)):
        items.append(ext_text[cur_pos:pos[i]])
        cur_pos = pos[i]
    items.append(ext_text[pos[-1]:])

    ext_info = {}
    for v in items:
        txt = v.strip()
        if not txt:
            continue

        dim_pos = txt.find('：')
        if dim_pos < 0:
            continue
        ext_info[txt[:dim_pos].strip()] = txt[dim_pos+1:].strip()
    return ext_info

# 获取书籍目录
def get_book_dir(url):
    books_dir = []
    name = parse(url).find('div', class_='listmain')
    if name:
        dd_items = name.find('dl')
        dt_num = 0
        for n in dd_items.children:
            ename = str(n.name).strip()
            if ename == 'dt':
                dt_num += 1
            if ename != 'dd':
                continue
            Catalog_info = {}
            if dt_num == 2:
                durls = n.find_all('a')[0]
                Catalog_info['chapter_name'] = (durls.get_text())
                Catalog_info['chapter_url'] = 'http://www.biqukan.com' + durls.get('href')
                books_dir.append(Catalog_info)
    # print(books_dir)
    return books_dir


# 获取章节内容
def get_charpter_text(curl):
    text = parse(curl).find('div', class_='showtxt')
    if text:
        cont = text.get_text()
        cont = [str(cont).strip().replace('\r \xa0\xa0\xa0\xa0\xa0\xa0\xa0\xa0', '').replace('\u3000\u3000', '')]
        c = " ".join(cont)
        ctext = ' '.join(re.findall(r'^.*?html', c))
        return ctext
    else:
        return ''

#数据存储
def SqlExec(conn,sql):
    try:
        cur = conn.cursor()
        cur.execute(sql)
        conn.commit()
    except Exception as e:
        print('exec sql error[%s]' % sql)
        print(Exception, e)
        cur = None
    return cur

# 获取书籍章节内容
def get_book(burl):
    # 目录
    book = get_book_dir(burl)
    if not book:
        print('获取数据目录失败:', burl)
        return book
    for cno, d in enumerate(book):
        curl = d['chapter_url']
        d['chapter_no'] = str(cno)
        try:
            print('正在获取....【{}】'.format(d['chapter_name']))
            ctext = get_charpter_text(curl)
            d['chapter_content'] = ctext
        except Exception as err:
            d['chapter_content'] = 'get failed'
            continue
    return book

# 插入书籍章节内容
def insert_chapter(dic):
    if not dic:
        print("获取基本信息失败")
        return dic
    sql = 'insert into book_chapter(' + ','.join(dic.keys()) + ') '
    sql += "values('" + "','".join(dic.values()) + "');"
    # 调用数据库函数
    if SqlExec(cx, sql):
        print('正在插入...【{}】'.format(dic['chapter_name']))
    else:
        print(sql)


# 书籍基本信息入库
def insert_baseinfo(burl):
    baseinfo = get_book_baseinfo(burl)
    if not baseinfo:
        print("获取基本信息失败")
        return baseinfo

    sql = 'insert into book_info(' + ','.join(baseinfo.keys()) + ')'
    sql += " values('" + "','".join(baseinfo.values()) + "');"
    # 调用数据库函数
    if SqlExec(cx, sql):
        print('正在插入...书籍【{}】的基本信息'.format(baseinfo['title']))
    else:
        print(sql)

if __name__ == '__main__':
    url = 'http://www.biqukan.com/1_1093/'
    insert_baseinfo(url)  # 获取书籍基本信息并入库
    books = get_book(url)  # 获取书籍章节目录
    for i in books:  # 插入每章内容
        insert_chapter(i)

结果显示：

同样，要获取更多书籍信息，可以加个循环

if __name__ == '__main__':
    for i in range(1090,1100):
        url = 'http://www.biqukan.com/1_' + str(i) + '/'
        insert_baseinfo(url)  # 获取书籍基本信息并入库
        books = get_book(url)  # 获取书籍章节目录
        for per_ch in books:  # 插入每章内容
            insert_chapter(per_ch)

数据库展示：