scrapy爬取豆瓣书单

2019年6月11日 204次阅读 来源: HouserLin

模仿:http://www.cnblogs.com/voidsky/p/5490798.html

创建scrapy项目:scrapy startproject doubanbook
cd 到提示目录,执行scrapy genspider doubanshu_spider root_url 继承基本spider创建spider

spider代码:

# -*- coding: utf-8 -*-
import scrapy
from doubanshu.items import DoubanshuItem
import re
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

class DoubanshuSpiderSpider(scrapy.Spider):
    name = "doubanshu_spider"
    #allowed_domains = ["https://www.douban.com/doulist/1264675/"]
    start_urls = (
        'https://www.douban.com/doulist/1264675//',
    )
    def parse(self, response):
        #print response.body

        sel = scrapy.Selector(response)
        books = sel.xpath('//*[@id="content"]/div/div[1]/div[starts-with(@id,"item")]')
        item = DoubanshuItem()
        print len(books)
        for each in books:
            title = each.xpath('div/div[2]/div[@class="title"]/a/text()').extract()[0].replace('・', '').replace(' ','').replace('\n', '')
            rate = each.xpath('div/div[2]/div[@class="rating"]/span[3]/text()').extract()[0].replace("(",'').replace(')', '').replace('\n', '')
            author =  re.search('<div class="abstract">(.*?)<br>', each.extract(), re.S).group(1).replace('•', '').replace(' ','').replace('・', '').replace('\n', '')
            item['title'] = title
            item['rate'] = rate
            item['author'] = author
            yield item
        next_page = sel.xpath('//*[@id="content"]/div/div[1]/div[31]/span[@class="next"]/a/@href').extract()
        if next_page:
            next  = next_page[0]
            yield scrapy.http.Request(next, callback = self.parse)

items代码

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

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class DoubanshuItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    rate = scrapy.Field()
    author = scrapy.Field()

setting 代码

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

# Scrapy settings for doubanshu 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 = 'doubanshu'

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


FEED_URI = u'file:///E://pythonExercises//20160611//doubanshudouban.csv'
FEED_FORMAT = 'CSV'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'doubanshu (+http://www.yourdomain.com)'

USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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 = {
#    'doubanshu.middlewares.MyCustomSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'doubanshu.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 = {
#    'doubanshu.pipelines.SomePipeline': 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'

pipelines
不连接数据库不进行处理

总结:

《scrapy爬取豆瓣书单》 Paste_Image.png

逻辑:将下一个url生成Request对象,返回response, 调用 parse 函数

2.403错误表示资源不可用。服务器理解客户的请求，但拒绝处理它，通常由于服务器上文件或目录的权限设置导致的WEB访问错误。需要加一个请求头部，模拟浏览器登录.

《scrapy爬取豆瓣书单》 Paste_Image.png

3.将item输出为csv的方法
setting:

《scrapy爬取豆瓣书单》 Paste_Image.png

输出的csv乱码,使用sublime打开,保存编码为utf-8 with BOM,再使用excel打开

4.处理书本资源被删除的情况:

《scrapy爬取豆瓣书单》 Paste_Image.png

不足:解析书籍的作者存在编码问题,此处仅简单进行替换

    原文作者：HouserLin
    原文地址: https://www.jianshu.com/p/d7fc7b630d92
    本文转自网络文章，转载此文章仅为分享知识，如有侵权，请联系博主进行删除。
点赞