<div class="content">
 <div class="widget-gallery">
 <ul class="pagelist-wrapper">
  <li class="gallery-item...

<div class="content">
 <div class="widget-gallery"></div>
</div>

https://tuchong.com/rest/tags/美女/posts?page=1&count=20&order=weekly&before_timestamp=

{
 "postList": [
 {
 "post_id": "15624611",
 "type": "multi-photo",
 "url": "https://weishexi.tuchong.com/15624611/",
 "site_id": "443122",
 "author_id": "443122",
 "published_at": "2017-10-28 18:01:03",
 "excerpt": "10月18日",
 "favorites": 4052,
 "comments": 353,
 "rewardable": true,
 "parent_comments": "165",
 "rewards": "2",
 "views": 52709,
 "title": "微风不燥 秋意正好",
 "image_count": 15,
 "images": [
 {
  "img_id": 11585752,
  "user_id": 443122,
  "title": "",
  "excerpt": "",
  "width": 5016,
  "height": 3840
 },
 {
  "img_id": 11585737,
  "user_id": 443122,
  "title": "",
  "excerpt": "",
  "width": 3840,
  "height": 5760
 },
 ...
 ],
 "title_image": null,
 "tags": [
 {
  "tag_id": 131,
  "type": "subject",
  "tag_name": "人像",
  "event_type": "",
  "vote": ""
 },
 {
  "tag_id": 564,
  "type": "subject",
  "tag_name": "美女",
  "event_type": "",
  "vote": ""
 }
 ],
 "favorite_list_prefix": [],
 "reward_list_prefix": [],
 "comment_list_prefix": [],
 "cover_image_src": "https://photo.tuchong.com/443122/g/11585752.webp",
 "is_favorite": false
 }
 ],
 "siteList": {...},
 "following": false,
 "coverUrl": "https://photo.tuchong.com/443122/ft640/11585752.webp",
 "tag_name": "美女",
 "tag_id": "564",
 "url": "https://tuchong.com/tags/%E7%BE%8E%E5%A5%B3/",
 "more": true,
 "result": "SUCCESS"
}

(PROJECT)
│ scrapy.cfg
│
└─tuchong
 │ items.py
 │ middlewares.py
 │ pipelines.py
 │ settings.py
 │ __init__.py
 │
 ├─spiders
 │ │ photo.py
 │ │ __init__.py
 │ │
 │ └─__pycache__
 │  __init__.cpython-36.pyc
 │
 └─__pycache__
  settings.cpython-36.pyc
  __init__.cpython-36.pyc

import scrapy

class TuchongItem(scrapy.Item):
 post_id = scrapy.Field()
 site_id = scrapy.Field()
 title = scrapy.Field()
 type = scrapy.Field()
 url = scrapy.Field()
 image_count = scrapy.Field()
 images = scrapy.Field()
 tags = scrapy.Field()
 excerpt = scrapy.Field()
 ...

import scrapy

class PhotoSpider(scrapy.Spider):
 name = 'photo'
 allowed_domains = ['tuchong.com']
 start_urls = ['http://tuchong.com/']

 def parse(self, response):
 pass

import scrapy, json
from ..items import TuchongItem

class PhotoSpider(scrapy.Spider):
 name = 'photo'
 # allowed_domains = ['tuchong.com']
 # start_urls = ['http://tuchong.com/']

 def start_requests(self):
 url = 'https://tuchong.com/rest/tags/%s/posts?page=%d&count=20&order=weekly';
 # 抓取10个页面，每页20个图集
 # 指定 parse 作为回调函数并返回 Requests 请求对象
 for page in range(1, 11):
  yield scrapy.Request(url=url % ('美女', page), callback=self.parse)

 # 回调函数，处理抓取内容填充 TuchongItem 属性
 def parse(self, response):
 body = json.loads(response.body_as_unicode())
 items = []
 for post in body['postList']:
  item = TuchongItem()
  item['type'] = post['type']
  item['post_id'] = post['post_id']
  item['site_id'] = post['site_id']
  item['title'] = post['title']
  item['url'] = post['url']
  item['excerpt'] = post['excerpt']
  item['image_count'] = int(post['image_count'])
  item['images'] = {}
  # 将 images 处理成 {img_id: img_url} 对象数组
  for img in post.get('images', ''):
  img_id = img['img_id']
  url = 'https://photo.tuchong.com/%s/f/%s.jpg' % (item['site_id'], img_id)
  item['images'][img_id] = url

  item['tags'] = []
  # 将 tags 处理成 tag_name 数组
  for tag in post.get('tags', ''):
  item['tags'].append(tag['tag_name'])
  items.append(item)
 return items

...
 def process_item(self, item, spider):
 # 不符合条件触发 scrapy.exceptions.DropItem 异常，符合条件的输出地址
 if int(item['image_count']) < 3:
  raise DropItem("美女太少: " + item['url'])
 elif item['type'] != 'multi-photo':
  raise DropItem("格式不对: " + + item['url'])
 else:
  print(item['url'])
 return item
...

ITEM_PIPELINES = {
 'tuchong.pipelines.TuchongPipeline': 300, # 管道名称: 运行优先级(数字小优先)
}

scrapy crawl photo

[scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 491,
 'downloader/request_count': 2,
 'downloader/request_method_count/GET': 2,
 'downloader/response_bytes': 10224,
 'downloader/response_count': 2,
 'downloader/response_status_count/200': 2,
 'finish_reason': 'finished',
 'finish_time': datetime.datetime(2017, 11, 27, 7, 20, 24, 414201),
 'item_dropped_count': 5,
 'item_dropped_reasons_count/DropItem': 5,
 'item_scraped_count': 15,
 'log_count/DEBUG': 18,
 'log_count/INFO': 8,
 'log_count/WARNING': 5,
 'response_received_count': 2,
 'scheduler/dequeued': 1,
 'scheduler/dequeued/memory': 1,
 'scheduler/enqueued': 1,
 'scheduler/enqueued/memory': 1,
 'start_time': datetime.datetime(2017, 11, 27, 7, 20, 23, 867300)}

scrapy crawl photo -o output.json # 输出为JSON文件
scrapy crawl photo -o output.csv # 输出为CSV文件

...
 def process_item(self, item, spider):
  ...
  else:
   print(item['url'])
   self.myblog.add_post(item) # myblog 是一个数据库类，用于处理数据库操作
  return item
...