基于scrapy的一些实例

一.爬取斗鱼主播

　1.　爬虫文件

# -*- coding: utf-8 -*-
import scrapy
import json
from Douyu.items import DouyuItem

class DouyuSpider(scrapy.Spider):
    name = 'douyu'
    # allowed_domains = ['www.xxx.com']
    baseurl = 'http://capi.douyucdn.cn/api/v1/getVerticalRoom?limit=20&offset='
    # 偏移量,指的是起始值,从0开始的偏移值
    offset = 0
    start_urls = [baseurl + str(offset)]

    def parse(self, response):
        # 对获取的数据进转jsao格式后进行判断
        data = json.loads(response.text)['data']

        if len(data) == 0:
            return
        data = json.loads(response.text)['data']
        # //循环data这个列表,拿到的是每一个主播信息的字典
        for each in data:
            name = each['nickname']
            img_url = each['vertical_src']
            # //实例一个item对象来装获取到的数据
            item = DouyuItem()
            item['name'] = name
            item['img_url'] = img_url
            # 这边要记得返回，否则管道文件接不到数据
            yield item

        # 获取所有页的数据
        # 这样不容出错,上面有判断了状态表示码,如果为1就不会走if这边了
        self.offset += 20
        url = self.baseurl + str(self.offset)
        yield scrapy.Request(url=url, callback=self.parse)

　　2.item

import scrapy

class DouyuItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name=scrapy.Field()  #保存昵称
    img_url=scrapy.Field()  #保存图片url

　　3.pipeline

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
from scrapy.pipelines.images import ImagesPipeline
from Douyu.settings import IMAGES_STORE as images_store
import os
import scrapy

#文字存储
class DouyuPipeline(object):
    f = None

    def open_spider(self, spider):
        self.f = open('./douyu.txt', 'w', encoding='utf-8')

    def process_item(self, item, spider):
        name = item['name']
        img_url = item['img_url']
        self.f.write(name + ":" + img_url + "\n")
        return item

    def close_spider(self, spider):
        self.f.close()

# 设置照片存储
class ImagesPipieline(ImagesPipeline):
    # 从爬虫文件赤岸过来的item中获取诈骗的url,对照片的url进行请求,获取照片
    # 照片默认获取保存到settingts.py中IMGS_STORE,自己要去设置路径
    def get_media_requests(self, item, info):
        img_url = item['img_url']

        yield scrapy.Request(img_url)

    # 对图片修改名字
    def item_completed(self, results, item, info):
        # 固定写法,获取图片路径,同时判断这个路径是否正确,如果正确就放到imgpath里面
        # results:把图片从文件读出来的信息
        img_path = [x['path'] for ok, x in results if ok]
        os.rename(images_store + img_path[0], images_store + item['name'] + '.jpg')

　　4.settings

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

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

BOT_NAME = 'Douyu'

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

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 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 https://doc.scrapy.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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    'Douyu.middlewares.DouyuSpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'Douyu.middlewares.DouyuDownloaderMiddleware': 543,
# }

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

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'Douyu.pipelines.DouyuPipeline': 300,
    'Douyu.pipelines.ImagesPipieline': 301,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://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 https://doc.scrapy.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'

# 图片的存储路径
#settings都要大写,这边的字一个都不能错
IMAGES_STORE ='D:/scrapy/Douyu/imgs/'