盗墓笔记小说爬取

1. 普通方式编写

from lxml import html
import requests
import os


url_first = "http://www.daomubiji.com/"


def get_text(url):
    response = requests.request('get', url)
    return response.text


# 获取所有部 书
text = get_text(url_first)
etree = html.etree.HTML(text)
#　所有书的名字
book_name = etree.xpath("//ul[@class='sub-menu']/li/a/text()")
#　所有书的链接
book_link  = etree.xpath("//ul[@class='sub-menu']/li/a/@href")


try:
    for i in range(len(book_link)):
        second = get_text(book_link[i])
        etree_second = html.etree.HTML(second)
        link = etree_second.xpath("//article[@class='excerpt excerpt-c3']/a/@href")
        book_title = etree_second.xpath("//article[@class='excerpt excerpt-c3']/a/text()")
        print(book_name[i])
        if os.path.exists(book_name[i]):
            pass
        else:
            os.mkdir(book_name[i])

        for j in range(len(link)):
            book_content = get_text(link[j])
            content_etree = html.etree.HTML(book_content)
            book_p = content_etree.xpath('//article[@class="article-content"]/p/text()')
            print(book_p)
            try:
                with open('{}/{}.txt'.format(book_name[i],book_title[j]), 'w+') as f:
                    for data in book_p:
                        # print(book_p)
                        f.write(data + "\n")
            except Exception:
                    print("编写出现异常")
        print(link, len(link))
        print(book_title, len(book_title))
except Exception:
    print("未知错误")

2. 面向对象方式编写

from lxml import html
import requests
import os


class DaoMuNote:

    def __init__(self, url=None):
        self.url = url

    # 获取相应文本
    def get_response_text(self, url):
        response = requests.request('get', url=url)
        return response.text

    # 创建 etree 对象
    def create_etree(self, text):
        etree = html.etree.HTML(text)
        return etree

    # 创建文件夹
    def create_files(self, file_name):
        self.file_name = file_name
        if os.path.exists(file_name):
            return file_name
        else:
            os.mkdir(file_name)
            return file_name

    #　写文本
    def writr_text(self, file_name, files, text):
        try:
            with open('{}/{}.txt'.format(file_name, files), 'a+') as f:
                f.write(text+'\n')
        except Exception:
            print("编写出现错误")


url = "http://www.daomubiji.com/"

# 初始化 DaoMuNote 对象
note = DaoMuNote(url=url)
# 第一页的所有标签
first_content = note.get_response_text(note.url)
first_etree = note.create_etree(first_content)
first_links = first_etree.xpath("//ul[@class='sub-menu']/li/a/@href")
first_title = first_etree.xpath("//ul[@class='sub-menu']/li/a/text()")

# 异常处理
try:
    # 第一页遍历 访问各个集数的链接 并进行xpath解析
    for i in range(len(first_links)):
        print(first_links[i])
        second_content = note.get_response_text(first_links[i])
        second_etree = note.create_etree(second_content)
        second_links = second_etree.xpath("//article[@class='excerpt excerpt-c3']/a/@href")
        second_titles = second_etree.xpath("//article[@class='excerpt excerpt-c3']/a/text()")
        # 创建文件夹 书的集数作为标题
        file_name = note.create_files(first_title[i])
        for j in range(len(second_links)):
            third_content = note.get_response_text(second_links[j])
            third_etree = note.create_etree(third_content)
            book_content = third_etree.xpath('//article[@class="article-content"]/p/text()')
            print(book_content)
            print(file_name, second_titles[j])
            for data in book_content:
                note.writr_text(file_name, second_titles[j], data)
except Exception as e:
    print("出现异常",e)