Scrapy框架进行Spiders简单爬虫

Author: CodeJCSON

.DS_Store

@@ -0,0 +1,2 @@
+from scrapy import cmdline
+cmdline.execute('scrapy crawl myteacher'.split())

teacherInfo/.idea/misc.xml

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

teacherInfo/.idea/modules.xml

@@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+# Item 定义结构化数据字段,用来保存爬取到的数据
+class TeacherinfoItem(scrapy.Item):
+
+    # 获取名字
+    name = scrapy.Field()
+    # 职称
+    position = scrapy.Field()
+    # 个人信息
+    info = scrapy.Field()
+
+

teacherInfo/.idea/teacherInfo.iml

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class TeacherinfoSpiderMiddleware(object):
+    # 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 Response, 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)

teacherInfo/.idea/workspace.xml

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+import codecs
+class TeacherinfoPipeline(object):
+    def __init__(self):
+        self.filename = codecs.open('teacher.json','wb','utf-8')
+    def process_item(self, item, spider):
+        print(item)
+        html = json.dumps(dict(item),ensure_ascii=False)
+        self.filename.write(html + '\n')
+        return item
+
+    def open_spider(self, spider):
+        pass
+        # self.filename.close()

teacherInfo/begin.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for teacherInfo project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'teacherInfo'
+
+SPIDER_MODULES = ['teacherInfo.spiders']
+NEWSPIDER_MODULE = 'teacherInfo.spiders'
+USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:56.0)'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'teacherInfo (+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 http://scrapy.readthedocs.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',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+SPIDER_MIDDLEWARES = {
+   'teacherInfo.middlewares.TeacherinfoSpiderMiddleware': 543,
+}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'teacherInfo.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'teacherInfo.pipelines.TeacherinfoPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://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 http://scrapy.readthedocs.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'

teacherInfo/scrapy.cfg

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

teacherInfo/teacher.json

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from teacherInfo.items import TeacherinfoItem
+
+class MyteacherSpider(scrapy.Spider):
+    name = 'myteacher'
+    allowed_domains = ['itcast.cn']
+    # start_urls = ("http://www.itcast.cn/channel/teacher.shtml",) 元组也可以
+    start_urls = ['http://www.itcast.cn/channel/teacher.shtml#ac',
+                  'http://www.itcast.cn/channel/teacher.shtml#acloud',
+                  'http://www.itcast.cn/channel/teacher.shtml#adesign',
+                  'http://www.itcast.cn/channel/teacher.shtml#ads',
+                  'http://www.itcast.cn/channel/teacher.shtml#ajavaee',
+                  'http://www.itcast.cn/channel/teacher.shtml#anetmarket',
+                  'http://www.itcast.cn/channel/teacher.shtml#aphp',
+                  'http://www.itcast.cn/channel/teacher.shtml#apm',
+                  'http://www.itcast.cn/channel/teacher.shtml#apython',
+                  'http://www.itcast.cn/channel/teacher.shtml#astack',
+                  'http://www.itcast.cn/channel/teacher.shtml#atest',
+                  'http://www.itcast.cn/channel/teacher.shtml#aui',
+                  'http://www.itcast.cn/channel/teacher.shtml#auijp',
+                  'http://www.itcast.cn/channel/teacher.shtml#aweb']
+    # 爬虫的约束区域
+    def parse(self, response):
+        # 存放老师信息的集合
+        items = []
+        print(response.body)
+        for each in response.xpath("//div[@class='li_txt']"):
+            # 将我们得到的数据封装到一个 `ItcastItem` 对象
+            item = TeacherinfoItem()
+            # extract()方法返回的都是unicode字符串
+            name = each.xpath("h3/text()").extract()
+            position = each.xpath("h4/text()").extract()
+            info = each.xpath("p/text()").extract()
+
+            # xpath返回的是包含一个元素的列表
+            item['name'] = name[0]
+            item['position'] = position[0]
+            item['info'] = info[0]
+
+            items.append(item)
+            yield item
+        # 直接返回最后数据
+        # return items