前言:
本片文章主要对爬虫爬取网页数据来进行一个简单的解答,对与其中的数据来进行一个爬取。
一:环境配置
Python版本:3.7.3
IDE:PyCharm
所需库:requests ,parsel
二:网站页面
我们需要获取以下数据:
'地区', '店名', '标题', '价格', '浏览次数', '卖家承诺', '在售只数',
'年龄', '品种', '预防', '联系人', '联系方式', '异地运费', '是否纯种',
'猫咪性别', '驱虫情况', '能否视频', '详情页'文章来源:https://www.toymoban.com/news/detail-694633.html
三:具体代码实现
# _*_ coding : utf-8 _*_
# @Time : 2023/9/3 23:03
# @Author : HYT
# @File : 猫
# @Project : 爬虫教程
import requests
import parsel
import csv
url ='http://www.maomijiaoyi.com/index.php?/list_0_78_0_0_0_0.html'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
}
response = requests.get(url=url, headers=headers)
selector = parsel.Selector(response.text)
href = selector.css('div.content:nth-child(1) a::attr(href)').getall()
areas = selector.css('div.content:nth-child(1) a .area span.color_333::text').getall()
areas = [i.strip() for i in areas]
zip_data = zip(href, areas)
for index in zip_data:
# http://www.maomijiaoyi.com/index.php?/chanpinxiangqing_546549.html
index_url = 'http://www.maomijiaoyi.com' + index[0]
response_1 = requests.get(url=index_url, headers=headers)
selector_1 = parsel.Selector(response_1.text)
area = index[1] # 地区
shop = selector_1.css('.dinming::text').get().strip() # 店名
title = selector_1.css('.detail_text .title::text').get().strip() # 标题
price = selector_1.css('span.red.size_24::text').get() # 价格
views = selector_1.css('.info1 span:nth-child(4)::text').get() # 浏览次数
promise = selector_1.css('.info1 div:nth-child(2) span::text').get().replace('卖家承诺: ', '') # 卖家承诺
sale = selector_1.css('.info2 div:nth-child(1) div.red::text').get() # 在售
age = selector_1.css('.info2 div:nth-child(2) div.red::text').get() # 年龄
breed = selector_1.css('.info2 div:nth-child(3) div.red::text').get() # 品种
safe = selector_1.css('.info2 div:nth-child(4) div.red::text').get() # 预防
people = selector_1.css('div.detail_text .user_info div:nth-child(1) .c333::text').get() # 联系人
phone = selector_1.css('div.detail_text .user_info div:nth-child(2) .c333::text').get() # 联系方式
fare = selector_1.css('div.detail_text .user_info div:nth-child(3) .c333::text').get().strip() # 异地运费
purebred = selector_1.css(
'.xinxi_neirong div:nth-child(1) .item_neirong div:nth-child(1) .c333::text').get().strip() # 是否纯种
sex = selector_1.css(
'.xinxi_neirong div:nth-child(1) .item_neirong div:nth-child(4) .c333::text').get().strip() # 猫咪性别
worming = selector_1.css(
'.xinxi_neirong div:nth-child(2) .item_neirong div:nth-child(2) .c333::text').get().strip() # 驱虫情况
video = selector_1.css(
'.xinxi_neirong div:nth-child(2) .item_neirong div:nth-child(4) .c333::text').get().strip() # 能否视频
dit = {
'地区': area,
'店名': shop,
'标题': title,
'价格': price,
'浏览次数': views,
'卖家承诺': promise,
'在售只数': sale,
'年龄': age,
'品种': breed,
'预防': safe,
'联系人': people,
'联系方式': phone,
'异地运费': fare,
'是否纯种': purebred,
'猫咪性别': sex,
'驱虫情况': worming,
'能否视频': video,
'详情页': index_url,
}
print(area, shop, title, price, views, promise, sale, age, breed,
safe, people, phone, fare, purebred, sex, worming, video, index_url, sep=' | ')
四:结果展示
文章来源地址https://www.toymoban.com/news/detail-694633.html
到了这里,关于爬虫源码---爬取小猫猫交易网站的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!