【依葫芦画瓢】之 Scrapy 虎牙封面爬取 笔记

【依葫芦画瓢】之 Scrapy 虎牙封面爬取 笔记

现学现卖

import scrapy
import json
from huya.items import HuyaItem



class HuyaaSpider(scrapy.Spider):
    name = 'huyaa'
    allowed_domains = ['www.huya.com']
    base_url = 'https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&gameId=2168&tagAll=0&page={}'
    offset = 0
    start_urls = [base_url.format(offset)]

    def parse(self, response):
        res = json.loads(response.body)['data']

        if len(res['datas']) == 0:
            return
        for re in res['datas']:#1
            item = HuyaItem()
            item['nicheng'] = re['nick'].strip()
            item['img'] = re['screenshot']
            print(item['nicheng'],item['img'])
            yield item
        self.offset += 1
        url = self.base_url.format(self.offset)
        print('页数'.center(50, '*'))
        print(url)
        print('页数'.center(50, '*'))
        yield scrapy.Request(url,callback=self.parse,dont_filter=True)#位置

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

BOT_NAME = 'huya'

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

IMAGES_STORE='G:\\py\\huya\\huya\\spiders\\imgs\\'#手动添加
LOG_LEVEL = 'WARNING'    #级别

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

# 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 https://docs.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',
  'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Mobile Safari/537.36'
}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'huya.middlewares.HuyaSpiderMiddleware': 543,
#}

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

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

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'huya.pipelines.HuyaPipeline': 300,
}

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