爬虫 Scrapy框架 爬取图虫图片并下载

Posted 2021-01-01 pantom0122

items.py,根据需求确定自己的数据要求

 1 # -*- coding: utf-8 -*-
 2 
 3 # Define here the models for your scraped items
 4 #
 5 # See documentation in:
 6 # https://doc.scrapy.org/en/latest/topics/items.html
 7 
 8 import scrapy
 9 
10 
11 class TodayScrapyItem(scrapy.Item):
12     # define the fields for your item here like:
13     # name = scrapy.Field()
14     pass
15 
16 
17 class TuchongItem(scrapy.Item):
18     title = scrapy.Field() #图片名字
19     views = scrapy.Field() #浏览人数
20     favorites = scrapy.Field()#点赞人数
21     img_url = scrapy.Field()#图片地址
22 
23     # def get_insert_sql(self):
24     #     # 存储时候用的sql语句
25     #     sql = ‘insert into tuchong(title,views,favorites,img_url)‘ 
26     #           ‘ VALUES (%s, %s, %s, %s)‘
27     #     # 存储的数据
28     #     data = (self[‘title‘], self[‘views‘], self[‘favorites‘], self[‘img_url‘])
29     #     return (sql, data)

setting.py 设置headers和items

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

# Scrapy settings for today_scrapy 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 = ‘today_scrapy‘

SPIDER_MODULES = [‘today_scrapy.spiders‘]
NEWSPIDER_MODULE = ‘today_scrapy.spiders‘


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘today_scrapy (+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‘,
  ‘User-Agnet‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36‘
}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    ‘today_scrapy.middlewares.TodayScrapySpiderMiddleware‘: 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    ‘today_scrapy.middlewares.TodayScrapyDownloaderMiddleware‘: 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 = {
   # ‘today_scrapy.pipelines.TodayScrapyPipeline‘: 300,
    ‘today_scrapy.pipelines.TuchongPipeline‘: 200,

}

# 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‘

pipelines.py 将图片下载到指定文件夹

 1 # -*- coding: utf-8 -*-
 2 
 3 # Define your item pipelines here
 4 #
 5 # Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
 6 # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
 7 import os
 8 import requests
 9 
10 class TodayScrapyPipeline(object):
11     def process_item(self, item, spider):
12         return item
13 
14 class TuchongPipeline(object):
15     def process_item(self, item, spider):
16         img_url = item[‘img_url‘] #从items中得到图片url地址
17         img_title= item[‘title‘] #得到图片的名字
18         headers = {
19             ‘User-Agnet‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36‘,
20             ‘cookie‘:‘webp_enabled=1; bad_ide7dfc0b0-b3b6-11e7-b58e-df773034efe4=78baed41-a870-11e8-b7fd-370d61367b46; _ga=GA1.2.1188216139.1535263387; _gid=GA1.2.1476686092.1535263387; phpSESSID=4k7pb6hmkml8tjsbg0knii25n6‘
21         }
22         if not os.path.exists(img_title):
23             os.mkdir(img_title)
24         filename =img_url.split(‘/‘)[-1]
25         with open(img_title+‘/‘+filename, ‘wb+‘) as f:
26             f.write(requests.get(img_url, headers=headers).content)
27         f.close()
28         return item

爬虫文件

tuchong.py

图片的url可以直接拼接

 1 # -*- coding: utf-8 -*-
 2 import scrapy
 3 import json
 4 from today_scrapy.items import TuchongItem
 5 
 6 
 7 class TuchongSpider(scrapy.Spider):
 8     name = ‘tuchong‘
 9     allowed_domains = [‘tuchong.com‘]
10     start_urls = [‘http://tuchong.com/‘]
11 
12     def start_requests(self):
13         for pag in range(1, 20):
14             referer_url = ‘https://tuchong.com/rest/tags/自然/posts?page={}&count=20‘.format(pag)   # url中红字部分可以换
15             form_req = scrapy.Request(url=referer_url, callback=self.parse)
16             form_req.headers[‘referer‘] = referer_url
17             yield form_req
18 
19     def parse(self, response):
20         tuchong_info_html = json.loads(response.text)
21         # print(tuchong_info_html)
22         postList_c = len(tuchong_info_html[‘postList‘])
23         # print(postList_c)
24         for c in range(postList_c):
25             print(c)
26             # print(tuchong_info_html[‘postList‘][c])
27             title = tuchong_info_html[‘postList‘][c][‘title‘]
28             print(‘图集名称:‘+title)
29             views = tuchong_info_html[‘postList‘][c][‘views‘]
30             print(‘有‘+str(views)+‘人浏览‘)
31             favorites = tuchong_info_html[‘postList‘][c][‘favorites‘]
32             print(‘喜欢的人数:‘+str(favorites))
33             images_c = len(tuchong_info_html[‘postList‘][c][‘images‘])
34             for img_c in range(images_c):
35                 user_id = tuchong_info_html[‘postList‘][c][‘images‘][img_c][‘user_id‘]
36                 img_id = tuchong_info_html[‘postList‘][c][‘images‘][img_c][‘img_id‘]
37                 img_url = ‘https://photo.tuchong.com/{}/f/{}.jpg‘.format(user_id,img_id)
38                 item = TuchongItem()
39                 item[‘title‘] = title
40                 item[‘img_url‘] = img_url
41             # 返回我们的item
42                 yield item