网站数据监控：
思路：对网站数据字段监控并做MD5加密存入到数据，为了后期监控数据是否更新作比对，然后邮件通知，存入四个字段。
引入的包：
md5_tools.py
# -*- coding:utf-8 -*-
import hashlib
# md5 加密
def md5_encode(md5):
md5 = md5
hash = hashlib.md5()
hash.update(bytes(md5, encoding='utf-8')) # 要对哪个字符串进行加密，就放这里
return hash.hexdigest() # 拿到加密字符串
wenzhou.py
# -*- coding: utf-8 -*-
import scrapy
import time
import re
from WEB.conmon.md5_tool import md5_encode
from WEB.items import WebItem
class CompanyInfoSpider(scrapy.Spider):
name = 'wenzhou'
allowed_domains = ['wzszjw.wenzhou.gov.cn']
start_urls = ['http://wzszjw.wenzhou.gov.cn/col/col1357901/index.html']
custom_settings = {"DOWNLOAD_DELAY": 0.5,
"ITEM_PIPELINES":{'WEB.pipelines.MysqlPipeline': 320},
"DOWNLOADER_MIDDLEWARES": {
'WEB.middlewares.RandomUaseragentMiddleware': 500,
},
}
def parse(self, response):
#gbk解码
_response=response.text.encode('utf-8')
# print(_response)
# 转码
_response=_response.decode('utf-8')
texts=re.findall("<span>.*?</span><b>·</b><a href=\'.*?\'",_response)
str = ""
for text in texts:
str = str + "".join(text)
# print(str)
text_md5 = md5_encode(str)
item = WebItem()
item["website_name"] = "温州市建设工程造价管理处"
item["website_url"] = response.url
item["content_md5"] = text_md5
item["date_time"] = time.time()
print(item)
yield item
items.py
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class WebItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
content_md5 = scrapy.Field() # 监控文本
website_url = scrapy.Field() # 采集页面url
website_name = scrapy.Field() # 网站名称
date_time = scrapy.Field() # 当前时间戳
piplines.py
# -*- coding: utf-8 -*-
from scrapy.conf import settings
import pymysql
class WebPipeline(object):
def process_item(self, item, spider):
return item
# 数据保存mysql
class MysqlPipeline(object):
def open_spider(self, spider):
self.host = settings.get('MYSQL_HOST')
self.port = settings.get('MYSQL_PORT')
self.user = settings.get('MYSQL_USER')
self.password = settings.get('MYSQL_PASSWORD')
self.db = settings.get(('MYSQL_DB'))
self.table = settings.get('TABLE')
self.client = pymysql.connect(host=self.host, user=self.user, password=self.password, port=self.port, db=self.db, charset='utf8')
def process_item(self, item, spider):
item_dict = dict(item)
cursor = self.client.cursor()
values = ','.join(['%s'] * len(item_dict))
keys = ','.join(item_dict.keys())
sql = 'INSERT INTO {table}({keys}) VALUES ({values})'.format(table=self.table, keys=keys, values=values)
try:
if cursor.execute(sql, tuple(item_dict.values())): # 第一个值为sql语句第二个为 值 为一个元组
print('数据入库成功!')
self.client.commit()
except Exception as e:
print(e)
print('数据已存在，网站未更新!')
self.client.rollback()
return item
def close_spider(self, spider):
self.client.close()
setting.py
# -*- coding: utf-8 -*-
# Scrapy settings for WEB project
#
# For simplicity, this download 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 = 'WEB'
SPIDER_MODULES = ['WEB.spiders']
NEWSPIDER_MODULE = 'WEB.spiders'
# mysql配置参数
MYSQL_HOST = "172.16.0.55"
MYSQL_PORT = 3306
MYSQL_USER = "root"
MYSQL_PASSWORD = "concom603"
MYSQL_DB = 'web_page'
TABLE = "web_page_update"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'WEB (+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',
#}
# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'WEB.middlewares.WebSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'WEB.middlewares.WebDownloaderMiddleware': 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 = {
# 'WEB.pipelines.WebPipeline': 300,
#}
# 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'
middlewares.py
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
import random
from scrapy import signals
class WebSpiderMiddleware(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)
class WebDownloaderMiddleware(object):
# 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)
# 随机更换 USER_AGENT
class RandomUaseragentMiddleware(object):
def __init__(self):
self.user_agent = [
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 GTB5",
"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0 )",
"HTC_Dream Mozilla/5.0 (Linux; U; Android 1.5; en-ca; Build/CUPCAKE) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 2.1; en-us; HTC Legend Build/cupcake) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 2.0; en-us; Milestone Build/ SHOLS_U2_01.03.1) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727; TheWorld)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.648; .NET CLR 3.5.21022; .NET4.0E; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; .NET4.0C)",
"Opera/9.80 (Windows NT 5.1; U; zh-cn) Presto/2.9.168 Version/11.50"
]
def process_request(self, request, spider):
request.headers["User-Agent"] = random.choice(self.user_agent)