微博.spider

weibo/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = weibo.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = weibo

weibo/weibo/items.py

@@ -0,0 +1,24 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class WeiboItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    name = scrapy.Field() #昵称
+    jianjie = scrapy.Field() #简介
+    gender = scrapy.Field() #性别
+    weibodengji = scrapy.Field() #微博等级
+    weiboshu = scrapy.Field() #微博数
+    fensishu = scrapy.Field() #粉丝数
+    guanzhuzhe = scrapy.Field() #关注者
+    chushengriqi = scrapy.Field() # 年龄
+    location = scrapy.Field()   #地区
+    xueli = scrapy.Field() #学历
+    # hangye = scrapy.Field() # 行业

weibo/weibo/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class WeiboSpiderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Request, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class WeiboDownloaderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

weibo/weibo/pipelines.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+# 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
+
+from pymongo import MongoClient
+
+class WeiboPipeline:
+    def process_item(self, item, spider):
+        return item
+
+class WeiboMongoPipeline(object):
+
+    def __init__(self, mongodb_url, mongodb_db, mongodb_table_name):
+        self.mongodb_url = mongodb_url
+        self.mongodb_db = mongodb_db
+        self.table_name = mongodb_table_name
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        return cls(
+            mongodb_url=crawler.settings.get('MONGODB_URL'),
+            mongodb_db=crawler.settings.get('MONGODB_DB'),
+            mongodb_table_name=crawler.settings.get('MONGODB_TABLE_NAME')
+        )
+
+    def open_spider(self, spider):
+        self.client = MongoClient(self.mongodb_url)
+        self.db = self.client[self.mongodb_db]
+
+    def process_item(self, item, spider):
+        self.db[self.table_name].insert(dict(item))
+        print('插入成功')
+        return item
+
+    def close_spider(self, spider):
+        self.client.close()