python 爬取豆瓣图书

Posted Louiszj

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了python 爬取豆瓣图书相关的知识,希望对你有一定的参考价值。

#!-*-coding:utf-8-*-
import requests
import xlwt
from bs4 import BeautifulSoup
from collections import OrderedDict


class DouBanBookSpider(object):

    def __init__(self, book_type, quantity):
        self.book_type = book_type
        self.quantity = quantity
        self.url_list = []
        self.book_dict = OrderedDict()
        self.count = 0

    #获取url
    def get_url(self):
        count = 0
        while count < self.quantity+1:
            url = https://book.douban.com/tag/%s?start=%d&type=S % (self.book_type, count)
            self.url_list.append(url)
            #每页20本书,
            count += 20
        return self.url_list

    #爬虫主体
    def main_spider(self, url):
        rsp = requests.get(url)
        tag_bf = BeautifulSoup(rsp.text, lxml)
        content = tag_bf.find_all(li, class_=subject-item)
        if content:
            for i in content:
                bt_bf = BeautifulSoup(str(i), lxml)
                self.count += 1
                book_name = bt_bf.h2.a.get_text(strip=True)
                author = bt_bf.find(div, class_=pub).string.strip()
                comment_info = bt_bf.find(div, class_=star clearfix)
                co_bf = BeautifulSoup(str(comment_info), lxml)
                grade = co_bf.find(span, class_=rating_nums)
                if grade:
                    grade = grade.string
                comment_count = co_bf.find(span, class_=pl).string.strip()
                self.book_dict[str(self.count)] = {序号: self.count, 书名: book_name, 评分: grade, 评论数: comment_count, 作者: author}
        else:
            return

    #执行爬虫
    def do_spider(self):
        for i in self.get_url():
            self.main_spider(i)

    #数据写入excel
    def write_excel(self):
        wb = xlwt.Workbook(encoding=ascii)
        ws = wb.add_sheet(self.book_type)
        style = xlwt.XFStyle()
        font = xlwt.Font()
        font.name = Times New Roman
        font.bold = True
        style.font = font
        row0 = [序号, 书名, 评分, 评论数, 出版信息]
        for i in range(0, len(row0)):
            ws.write(0, i, row0[i], style)
        for k, v in self.book_dict.items():
            for j in range(0, len(v.values())):
                ws.write(int(k), j, list(v.values())[j])
        wb.save(%s.xlsx % self.book_type)


if __name__ == "__main__":
    ds = DouBanBookSpider(中国历史, 2000)
    ds.do_spider()
    ds.write_excel()

 

以上是关于python 爬取豆瓣图书的主要内容,如果未能解决你的问题,请参考以下文章

python 爬取豆瓣图书

豆瓣爬取图书标签

Python爬虫入门 | 4 爬取豆瓣TOP250图书信息

python爬取豆瓣新书清单

爬取豆瓣网图书TOP250的信息

Python-利用beautifulsoup写个豆瓣热门图书爬虫