requests + re 爬去网站图书信息（Python）

# -*- coding: utf-8 -*-

import requests
import re, json

if __name__ == '__main__':
content = requests.get('https://book.douban.com/').text
reg_base = '<ul.*?list-col list-col5 list-express slide-item">(.*?)</ul>'
base_pattern = re.compile(reg_base, re.S)
base_html = re.findall(base_pattern, content)

href = '<li.*?cover.*?href="(.*?)".*?'
title = '<div.*?title.*?title.*?>(.*?)</a>.*?'
author = '<div.*?more-meta.*?author.*?>(.*?)</span>.*?</li>'
regex = href + title + author
pattern = re.compile(regex, re.S)
results = []
# 匹配子标签中的图书信息
for html in base_html:
results += re.findall(pattern, html)

with open('touban.txt', 'w', encoding='utf-8') as f:
for result in results:
d = {
'href': result[0].strip(),
'title': result[1].strip(),
'author': result[2].replace(' ', '').strip()
}

f.write(json.dumps(d, ensure_ascii=False) + '\n')

{"author": "[法] 米歇尔·普西", "href": "https://book.douban.com/subject/30180673/?icn=index-editionrecommend", "title": "她不是我妈妈"}
{"author": "[意]马西米利亚诺·威尔吉利奥", "href": "https://book.douban.com/subject/30180821/?icn=index-editionrecommend", "title": "那不勒斯的萤火"}
{"author": "于蕾，吕逸涛", "href": "https://book.douban.com/subject/30206904/?icn=index-editionrecommend", "title": "国家宝藏"}
{"author": "张立民", "href": "https://book.douban.com/subject/30235899/?icn=index-editionrecommend", "title": "最后一公里的哲学：电商物流全链条运营管理"}
{"author": "【英】詹姆斯•霍尼伯内（James Honeyborne）/【英】马克•布朗罗（Mark Brownlow）", "href": "https://book.douban.com/subject/30183403/?icn=index-editionrecommend", "title": "BBC全新4K海洋百科：蓝色星球II"}
{"author": "[葡] 若泽·萨拉马戈", "href": "https://book.douban.com/subject/27598520/?icn=index-latestbook-subject", "title": "里卡尔多·雷耶斯离世那年"}
{"author": "[美] 史蒂芬·平克", "href": "https://book.douban.com/subject/30186025/?icn=index-latestbook-subject", "title": "风格感觉"}
{"author": "赵垒", "href": "https://book.douban.com/subject/30204837/?icn=index-latestbook-subject", "title": "傀儡城之荆轲刺秦"}
{"author": "梅贻琦/黄延复/王小宁", "href": "https://book.douban.com/subject/30197575/?icn=index-latestbook-subject", "title": "梅贻琦西南联大日记"}
{"author": "[日] 永井荷风", "href": "https://book.douban.com/subject/30171301/?icn=index-latestbook-subject", "title": "濹东绮谭"}
{"author": "[波兰] 安杰伊·瓦伊达/Andrzej Wajda", "href": "https://book.douban.com/subject/30211002/?icn=index-latestbook-subject", "title": "我们一起拍片！"}
{"author": "[德] 弗兰克·施茨廷", "href": "https://book.douban.com/subject/27604676/?icn=index-latestbook-subject", "title": "群"}
{"author": "[美] 克丽丝特尔·潘恩/Crystal Paine", "href": "https://book.douban.com/subject/30206819/?icn=index-latestbook-subject", "title": "会赚钱的妈妈"}
{"author": "[日] 石田衣良", "href": "https://book.douban.com/subject/27622428/?icn=index-latestbook-subject", "title": "美丽的孩子"}
{"author": "杨时旸", "href": "https://book.douban.com/subject/30218577/?icn=index-latestbook-subject", "title": "孤独的影猎人"}
{"author": "[德]沃尔夫冈·赫伦多夫", "href": "https://book.douban.com/subject/27598521/?icn=index-latestbook-subject", "title": "小心，沙漠有人"}
{"author": "[英] 珍妮特·温特森", "href": "https://book.douban.com/subject/27663541/?icn=index-latestbook-subject", "title": "我要快乐，不必正常"}
{"author": "朱一叶", "href": "https://book.douban.com/subject/30198364/?icn=index-latestbook-subject", "title": "死于象蹄"}
{"author": "[荷] 伊恩·布鲁玛", "href": "https://book.douban.com/subject/27662697/?icn=index-latestbook-subject", "title": "日本之镜"}
{"author": "[美] 威廉·莫尔顿·马斯顿", "href": "https://book.douban.com/subject/30210732/?icn=index-latestbook-subject", "title": "神奇女侠"}
{"author": "[美] 特德·焦亚", "href": "https://book.douban.com/subject/30203912/?icn=index-latestbook-subject", "title": "如何听爵士"}
{"author": "邓安庆", "href": "https://book.douban.com/subject/30221630/?icn=index-latestbook-subject", "title": "纸上王国"}
{"author": "朱伟", "href": "https://book.douban.com/subject/30205589/?icn=index-latestbook-subject", "title": "重读八十年代"}
{"author": "邓安庆", "href": "https://book.douban.com/subject/30190319/?icn=index-latestbook-subject", "title": "望花"}
{"author": "[美]沃尔特·李普曼", "href": "https://book.douban.com/subject/27662713/?icn=index-latestbook-subject", "title": "舆论"}
{"author": "[英] P•D•詹姆斯", "href": "https://book.douban.com/subject/27111572/?icn=index-latestbook-subject", "title": "人类之子"}
{"author": "骆仪", "href": "https://book.douban.com/subject/30198500/?icn=index-latestbook-subject", "title": "京都好物"}
{"author": "(美) 比尔·克林顿 (Bill Clinton)/[美] 詹姆斯·帕特森", "href": "https://book.douban.com/subject/30218923/?icn=index-latestbook-subject", "title": "失踪的总统"}
{"author": "刘冰/林秦文/李敏", "href": "https://book.douban.com/subject/30203973/?icn=index-latestbook-subject", "title": "中国常见植物野外识别手册（北京册）"}
{"author": "冶文彪", "href": "https://book.douban.com/subject/30205286/?icn=index-latestbook-subject", "title": "清明上河图密码 5"}
{"author": "[英] 劳拉·卡琳/Laura Carlin", "href": "https://book.douban.com/subject/30181220/?icn=index-latestbook-subject", "title": "创造自己的世界"}
{"author": "郭强生", "href": "https://book.douban.com/subject/30217599/?icn=index-latestbook-subject", "title": "断代"}
{"author": "史杰鹏", "href": "https://book.douban.com/subject/30183948/?icn=index-latestbook-subject", "title": "悠悠我心"}
{"author": "[俄] 柳德米拉·乌利茨卡娅", "href": "https://book.douban.com/subject/30205823/?icn=index-latestbook-subject", "title": "库科茨基医生的病案"}
{"author": "[美] 兰德尔·柯林斯", "href": "https://book.douban.com/subject/30143236/?icn=index-latestbook-subject", "title": "文凭社会"}
{"author": "[法] 让-皮埃尔·吉布拉", "href": "https://book.douban.com/subject/30205166/?icn=index-latestbook-subject", "title": "爱的缓刑"}
{"author": "[美]丽贝卡·特雷斯特", "href": "https://book.douban.com/subject/30128172/?icn=index-latestbook-subject", "title": "单身女性的时代"}
{"author": "[俄] 弗拉基米尔·索罗金", "href": "https://book.douban.com/subject/27200259/?icn=index-latestbook-subject", "title": "碲钉国"}
{"author": "苏精", "href": "https://book.douban.com/subject/30218894/?icn=index-latestbook-subject", "title": "铸以代刻"}
{"author": "[英] 石黑一雄", "href": "https://book.douban.com/subject/30181685/?icn=index-latestbook-subject", "title": "莫失莫忘"}

requests + re 爬去网站图书信息（Python）相关推荐

爬取起点网站图书信息（书名、作者、简介、图片url）
# 爬取qidian网站图书信息(书名.作者.简介.图片url) import requests from lxml import etree import jsonclass BookSpider( ...
Python Scrapy爬虫实战（1）：豆瓣网站图书信息案例- Scrapy初体验
Scrapy,Python开发的一个快速.高层次的屏幕抓取和web抓取框架,用于抓取web站点并从页面中提取结构化的数据.Scrapy用途广泛,可以用于数据挖掘.监测和自动化测试.Scrapy吸引人的 ...
Python爬虫：爬去韩国电视剧信息
最近看韩剧想重温一下以前看的韩剧但是就记得剧情到网站上找了太多点的太麻烦,网上问了也回答不了找的几个片名都不对,所以就想写个爬虫爬去某站上所有的韩剧信息,可以方便查找想看的韩剧爬取具体如下: ...
requests.get()爬去中文网页乱码解决方法
requests.get()爬去中文网页乱码解决方法当我们使用requests.get()爬取百度首页时会发现,返回的html代码中的中文发生乱码. import requestsheaders = ...
python爬火车票是不是违法_python利用selenium+requests+beautifulsoup爬取12306火车票信息...
在高速发展的时代.乘车出远门是必不可少的,有些查询信息是要收费的.这里打造免费获取火车票信息想要爬取12306火车票信息,访问12306官方网站,输入出发地,目的地 ,时间之后点击确定,这是我 ...
提取点位属性文本_手把手教你如何用Python爬取网站文本信息
提取网页源代码--Requests 工具包在我们提取网络信息之前,我们必须将网页的源代码进行提取,Requests工具包现在可以说是最好用和最普及的静态网页爬虫工具,它是由大神Kenneth Rei ...
python爬取网页文本_手把手教你如何用Python爬取网站文本信息
提取网页源代码--Requests 工具包在我们提取网络信息之前,我们必须将网页的源代码进行提取,Requests工具包现在可以说是最好用和最普及的静态网页爬虫工具,它是由大神Kenneth Rei ...
【selenium爬虫】 selenium自动化爬取京东图书信息
一.题目要求:搜索京东图书页,自动点击详情页进入,爬取数据信息并且存储到csv中二.解题思路:1.需要下载一个chromedriver.exe.下载地址:ChromeDriver Mirror 注意: ...
爬虫实战：Requests+BeautifulSoup 爬取京东内衣信息并导入表格（python）
准备工作假如我们想把京东内衣类商品的信息全部保存到本地,通过手工复制粘贴将是一项非常庞大的工程,此时,可以用python爬虫实现. 第一步:分析网页地址起始网页地址起始网页地址 https:// ...

requests + re 爬去网站图书信息（Python）

requests + re 爬去网站图书信息（Python）相关推荐

最新文章

热门文章