scrapy 爬取豆瓣互联网图书

安装scrapy
1. 　　
```
conda install scrapy
```
生成一个scrapy项目
1. 　　
```
scrapy startproject douban
```

settings文件

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

# Scrapy settings for douban project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'douban'

SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'douban (+http://www.yourdomain.com)'
# USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0'
USER_AGENT='Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'douban.middlewares.DoubanSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'douban.middlewares.MyCustomDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'douban.pipelines.DoubanPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

编写爬虫文件,位于spiders下面

import scrapy

from douban.items    import  DoubanItem

class MeijuSpider(scrapy.Spider):
    name = 'doubanmovie'
    allowed_domains=['book.douban.com']
    start_urls=['https://book.douban.com/tag/%E4%BA%92%E8%81%94%E7%BD%91']
    number=1;
    def parse(self, response):
        self.number = self.number+1;
        # print(response.text)
        objs=response.xpath('//*[@id="subject_list"]/ul/li')
        # print(objs)
        # print('test',response.xpath('//*[@id="content"]/div/div[1]/div/div/table[1]/tr/td[2]/div/a/text()').extract_first())
        print(len(objs))
        for i in objs :
            item=DoubanItem()
            item['name']=i.xpath('./div[2]/h2/a/text()').extract_first() or ''
            item['score']=i.xpath('./div[2]/div[2]/span[2]/text()').extract_first() or ''
            item['author']=i.xpath('./div[2]/div[1]/text()').extract_first() or ''
            item['describe']=i.xpath('./div[2]/p/text()').extract_first() or ''
            yield item
        next_page = response.xpath('//*[@id="subject_list"]/div[2]/span[4]/a/@href').extract()
        print(self.number);
        if(self.number >11):
            next_page = response.xpath('//*[@id="subject_list"]/div[2]/span[5]/a/@href').extract()
        print(next_page)
        if next_page:
            next_link=next_page[0];
            print("https://book.douban.com"+next_link)
            yield scrapy.Request("https://book.douban.com"+next_link,callback=self.parse)

编写pipe文件

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html


class DoubanPipeline(object):
    def process_item(self, item, spider):
        with open('douban.txt','a',encoding='utf-8') as file:
            file.write(str(item['name'].replace("\n","").replace("\t","").replace(",","，").replace("\r","").strip() )
                       +','+item['score'].replace("\n","").replace("\t","").replace(",","，").replace("\r","").strip()
                       +','+str(item['author']).replace("\n","").replace("\t","").replace(",","，").replace("\r","").strip()
                       +','+item['describe'].replace("\n","").replace("\t","").replace(",","，").replace("\r","").strip()
                       + "\n"
                       )

执行

　　编写一个start.py文件

from scrapy.cmdline import execute
execute("scrapy crawl doubanmovie".split())

效果
1.

scrapy 爬取豆瓣互联网图书

猜你喜欢