scrapy框架爬取斗鱼女主播照片,依据颜值排行榜

spider爬虫文件 douyugirl.py

# -*- coding: utf-8 -*-
import scrapy
import json
from douyu.items import DouyuItem
import  requests
class DouyugirlSpider(scrapy.Spider):
    name = 'douyugirl'
    allowed_domains = ['douyucdn.cn']
    urlone = 'http://capi.douyucdn.cn/api/v1/getVerticalRoom?limit=20&offset='
    offset = 0
    start_urls = [urlone+str(offset)]

    def parse(self, response):
        a = json.loads(response.body)['data']
        for each in a:
            item  = DouyuItem()
            item['nickname'] = each['nickname']
            item['imageurl'] = each['vertical_src']
            # a = requests.get(each['vertical_src'])
            # a.encoding = 'utf-8'
            #
            # print(a.text)
            #print(item['nickname']+'*'*30)
            yield item
        if self.offset<500:
            self.offset+=20
            yield scrapy.Request(self.urlone+str(self.offset),callback=self.parse)

settings.py

此处注意开启 ITEM_PIPELINES,否则无效!

ITEM_PIPELINES = {
   'douyu.pipelines.DouyuPipeline': 300,
}

# -*- 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 = 'douyu (+http://www.yourdomain.com)'

# 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,
}

# 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'

items.py

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

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

import scrapy


class DouyuItem(scrapy.Item):
    nickname = scrapy.Field()
    imageurl = scrapy.Field()

pipelines.py

# -*- 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

import requests
class DouyuPipeline(object):
    def process_item(self, item, spider):
        name = item['nickname']
        url = item['imageurl']
        text = requests.get(url).content
        # print(text)
        with open('./girl/%s.jpg'%name , 'wb') as f:
            f.write(text)
            f.close()
        return item

成功

成果如下