scrapy实例下载GIF

spider 文件

from sys import path
#此处是个坑。。。不然找不到GifItem
path.append('..')
from ..items import GifItem


class GifSpiderSpider(scrapy.Spider):
    name = 'gif_spider'
    list_start_urls = []
    for i in range(1,774):
        url = 'https://bbs7.s6vx.xyz/2048/thread.php?fid-29-page-{}.html'.format(i)
        list_start_urls.append(url)
    start_urls = list_start_urls

    def parse(self, response):
        a = response.xpath('//td/a[2]/@href')
        for i in a:
            href = i.extract()
            if 'read' in href:
                url = 'https://bbs7.s6vx.xyz/2048/' + href
                yield scrapy.Request(url, callback=self.pic_down)

    def pic_down(self, response):
        list_urls_gif = re.findall('https.*?gif', response.text)
        for url in list_urls_gif:
            yield scrapy.Request(url, callback=self.saveGIF)

    def saveGIF(self, response):
        item = GifItem()
        item['name'] = response.url.split('/')[-1]
        item['content'] = response.body
        yield item

#######################################################
#######################################################

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


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
import os

class GifPipeline:
    def process_item(self, item, spider):
        print(item['name'])
        if os.path.exists('f:\\gif\\' + item['name']):
            print('已经在了!' * 20)
            return 0
        with open('f:\\gif\\' + item['name'], 'wb')as f:
            f.write(item['content'])
            f.close()
        return len(item['content'])

####################################################
####################################################

# Scrapy settings for gif 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 = 'gif'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'gif (+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 = 1
# 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://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'gif.middlewares.GifSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'gif.middlewares.GifDownloaderMiddleware': 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 = {
    'gif.pipelines.GifPipeline': 300,
}
'''不启用不生效PIPLINE'''
# 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'

DOWNLOAD_TIMEOUT = 60
RETRY_ENABLED = True
RETRY_TIMES = 10
#LOG_LEVEL = "WARNING"

######################################################
######################################################

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

import scrapy


class GifItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    name = scrapy.Field()
    content = scrapy.Field()

你可能感兴趣的:(scrapy实例下载GIF)