爬取豆瓣电影排名前250部电影并且存入Mongo数据库

需求：爬取豆瓣电影top250（https://movie.douban.com/top250）的电影数据：

标题（title ），电影评分（score），电影信息（content），简介 info。

一、分析页面，用xpath得到相应的数据

标题的xpath是：//div[@class="info"]//span[@class="title"][1]/text()

电影信息xpath：//div[@class="info"]//div[@class="bd"]/p[1]

电影评分xpath：//div[@class="info"]//div[@class="star"]/span[2]/text()

得到简介的xpath：//div[@class="info"]//span[@class="inq"]/text()

二、创建项目并且完成items.py

创建项目命令：scrapy startproject douban

进入项目目录：cd douban

创建爬虫程序：scrapy genspider movetop250 douban.com

1.启动程序的脚本---main.py

代码语言：javascript复制

from scrapy import cmdline

cmdline.execute("scrapy crawl movetop250".split())

2.items.py

代码语言：javascript复制

import scrapy


class DoubanItem(scrapy.Item):
    # 电影标题
    title = scrapy.Field()
    # 电影评分
    score = scrapy.Field()
    # 电影信息
    content = scrapy.Field()
    # 简介
    info = scrapy.Field()

3.movetop250.py

代码语言：javascript复制

import scrapy

from douban.items import DoubanItem


class Movetop250Spider(scrapy.Spider):
    name = 'movetop250'
    allowed_domains = ['douban.com']
    offset = 0
    url = "https://movie.douban.com/top250?start="
    start_urls = [url   str(offset)]

    def parse(self, response):
        moves = response.xpath('//div[@class="info"]')
        for move in moves:
            item = DoubanItem()
            # 电影名称
            title = move.xpath('.//span[@class="title"][1]/text()').extract()[0]
            # 点击的信息,例如导演等
            content = move.xpath('.//div[@class="bd"]/p[1]/text()').extract()[0]
            content = "".join(content).strip()
            # 评分
            score = move.xpath('.//div[@class="star"]/span[2]/text()').extract()[0]
            # 电影一句话简介
            info = move.xpath('.//span[@class="inq"]/text()').extract()

            if len(info) > 0:
                info = info[0]
            item["title"] = title
            item["content"] = content
            item["score"] = score
            item["info"] = info
            yield item
        # 请求每一页数据
        if self.offset < 225:
            self.offset  = 25
            url = self.url   str(self.offset)
            yield scrapy.Request(url, callback=self.parse)

4.pipelines.py

代码语言：javascript复制

import json

import pymongo
from scrapy.conf import settings


class DoubanMongodbPipeline(object):
    def __init__(self):
        print("=====start=====")
        host = settings["MONGO_HOST"]
        port = settings["MONGO_PORT"]
        dbname = settings["MONGO_DBNAME"]
        sheetname = settings["MONGO_SHEETNAME"]

        print("host==", host)
        print("port==", port)
        print("dbname==", dbname)
        print("sheetname==", sheetname)

        # 创建客户端
        client = pymongo.MongoClient(host=host, port=port)
        # 得到或者创建数据库对象
        mydb = client[dbname]
        # 得到或者创建表
        self.post = mydb[sheetname]

    def process_item(self, item, spider):
        # dict_json = dict(item)
        # json_str = json.dumps(dict_json, ensure_ascii=False)   "n"
        # self.file.write(json_str)
        dict_item = dict(item)
        self.post.insert(dict_item)
        return item

    def close_spider(self, spider):
        print("======end======")
        self.file.close()


class DoubanPipeline(object):
    def __init__(self):
        print("=====start=====")
        self.file = open("movetop250.json", "w", encoding="utf-8")

    def process_item(self, item, spider):
        dict_json = dict(item)
        json_str = json.dumps(dict_json, ensure_ascii=False)   "n"
        self.file.write(json_str)
        return item
    def close_spider(self, spider):
        print("======close_spide======")
        self.file.close()

5.settings.py

代码语言：javascript复制

 BOT_NAME = 'douban'

SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'
ROBOTSTXT_OBEY = False  # 一般情况不遵循爬虫规则

DEFAULT_REQUEST_HEADERS = {
    'Accept': 'text/html,application/xhtml xml,application/xml;q=0.9,*/*;q=0.8',
    'Accept-Language': 'en',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'
                  ' Chrome/67.0.3396.99 Safari/537.36',
}

ITEM_PIPELINES = {
    'douban.pipelines.DoubanPipeline': 301,
    'douban.pipelines.DoubanMongodbPipeline': 300,
}

# 设置日志
LOG_FILE = "dongguan.log"
LOG_LEVEL = "DEBUG"
# 设置用户代理
USER_AGENT = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 " 
             "Safari/537.36"

# 配置mongodb数据库的信息
# mongo 主机
MONGO_HOST = "127.0.0.1"
# mongo 端口
MONGO_PORT = 27017
# mongo 数据存放数据库库名称
MONGO_DBNAME = "douban"
# mongo 数据存放的表名称
MONGO_SHEETNAME = "movetop250"
# Disable cookies (enabled by default)
COOKIES_ENABLED = False

python xslt&xpath scrapy

0 人点赞