爬京东

最新推荐文章于 2024-06-21 18:00:17 发布

ch_zs

最新推荐文章于 2024-06-21 18:00:17 发布

阅读量692

点赞数 1

分类专栏：爬虫

本文链接：https://blog.csdn.net/qq_43665891/article/details/109606084

版权

爬虫专栏收录该内容

4 篇文章 0 订阅

订阅专栏

import csv
import requests
from lxml import etree
from pymongo import MongoClient


class Pa_jd():
    def __init__(self):
        self.keyword = str(input('输入搜索内容'))
        self.num = int(input('爬取几页?'))
        self.list1 = []
        self.host = '127.0.0.1'
        self.port = 27017

    def run(self):
        '''爬取网页内容'''
        headers = {
            'Referer': 'https://item.jd.com/',
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Safari/537.36'
        }
        for i in range(1, self.num):
            page = i + (i - 1)
            params = {
                'keyword': self.keyword,
                'page': page,
                's': (page - 1) * 30 - 4,
                'click': 0

            }

            url = 'https://search.jd.com/Search'
            r = requests.get(url, headers=headers, params=params)

            print(r.headers)  # 响应头
            print(r.url)  # url
            with open('jd搜索%s%s.html' % (self.keyword, i), 'w', encoding='utf-8') as f:
                f.write(r.content.decode())

    def fetch(self):
        '''提取出有用的数据,放到list1里'''
        for i in range(1, self.num):
            with open('jd搜索%s%s.html' % (self.keyword, i), 'r', encoding='utf-8') as f:
                text = f.read()
                html = etree.HTML(text)

                price_list = html.xpath('//li/div/div[@class="p-price"]/strong/i/text()')
                title_list = html.xpath('//li/div/div[@class="p-name p-name-type-2"]/a/em/text()')
                href_list = html.xpath('//li/div/div[@class="p-name p-name-type-2"]/a/@href')

                for price in price_list:
                    item = dict()
                    item["price"] = price
                    item["title"] = title_list[price_list.index(price)]
                    item["href"] = href_list[price_list.index(price)]
                    self.list1.append(item)

    def csv(self):
        '''存储为cvs格式文件'''
        with open('jd手机搜索%s.csv' % self.keyword, 'w', encoding='utf-8') as f:
            # 创建一个csv的DictWriter对象，这样才能够将写入csv格式数据到这个文件
            f_csv = csv.DictWriter(f, ['title', 'price', 'href'])
            f_csv.writeheader()
            f_csv.writerows(self.list1)

    def mongo_db(self):
        '''连接数据库,插入数据'''
        client = MongoClient(self.host, self.port)
        collection = client['jd']['jd1']
        # insert_many接收一个列表，列表中为所有需要插入的字典
        t = collection.insert_many(self.list1)


p = Pa_jd()
p.run()  # 爬取
p.fetch()  # 提取
p.mongo_db()  # 存数据库
# p.cvs()