import scrapy
import jsonpath
###导入items
from tencent.items import TencentItem
class TencenthrSpider(scrapy.Spider):
name = 'tencenthr'
allowed_domains = ['careers.tencent.com']
#js接口
start_urls = ['https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1640657047807&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=&attrId=&keyword=&pageIndex=1&pageSize=10&language=zh-cn&area=cn']
def start_requests(self):
for i in range(0, 1):
url = f'https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1640657047807&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=&attrId=&keyword=&pageIndex={i}&pageSize=10&language=zh-cn&area=cn'
yield scrapy.Request(url=url, callback=self.parse)
# url 请求访问的网址
# callback 回调函数，引擎回将下载好的页面(Response对象)发给该方法，执行数据解析
# 这里可以使用callback指定新的函数，不是用parse作为默认的回调参数
def parse(self,response):
##转js
html = response.json() ###转json
#信息提取
title= jsonpath.jsonpath(html,'$...RecruitPostName')
# print(title)
LocationName= jsonpath.jsonpath(html,'$...LocationName')
# print(LocationName)
LastUpdateTime= jsonpath.jsonpath(html,'$...LastUpdateTime')
# print(LastUpdateTime)
##转自定义表
for i in range(len(title)):
# print(title[i],LocationName[i],LastUpdateTime[i]) #输出评论
###item=TencentItem() 二次判断爬取资源是否有错
item=TencentItem()
item["title"]=title[i]
item["LocationName"]=LocationName[i]
item["LastUpdateTime"]=LastUpdateTime[i]
print(item)
##转pip操作写入数据库
yield item
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class TencentItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
####判断tencenthr
title = scrapy.Field()
LocationName = scrapy.Field()
LastUpdateTime = scrapy.Field()
# Scrapy settings for tencent project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://docs.scrapy.org/en/latest/topics/settings.html
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
import random
BOT_NAME = 'tencent'
SPIDER_MODULES = ['tencent.spiders']
NEWSPIDER_MODULE = 'tencent.spiders'
# headers = {
# 'user-agent': UserAgent(verify_ssl=False).random ##随机UA头
# }
# Crawl responsibly by identifying yourself (and your website) on the user-agent
from fake_useragent import UserAgent ##随机UA头
USER_AGENT = UserAgent(verify_ssl=False).random
# 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 https://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
# 'tencent.middlewares.TencentSpiderMiddleware': 543,
# }
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'tencent.middlewares.TencentDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'tencent.pipelines.mysqlPipeline': 299,
'tencent.pipelines.TencentPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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://docs.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'
# 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
import pymysql
# useful for handling different item types with a single interface
# from pymongo import MongoClient
import pymysql
from itemadapter import ItemAdapter
from tencent.items import TencentItem
####判断来自 什么爬虫 和 items
class TencentPipeline:
def process_item(self, item, spider):
if isinstance(item,TencentItem):
collections.insert(dict(item))
print(item)
return item
####定义mysqlPipeline ###setting
class mysqlPipeline(object):
##链接数据库
def open_spider(self, spider):
self.conn = pymysql.connect(host='127.0.0.1',user='root',passwd='Sooele0000%',db='scrapy') #连接数据库
def process_item(self, item, spider):
#添加数据到chengjiao表中
self.conn.query(
"insert chengjiao(title,LocationName,LastUpdateTime)" #需要插入的字段
"values('{}','{}','{}')".format(
item['title'],item['LocationName'],item['LastUpdateTime'] #爬取项目中定义的字段
))
self.conn.commit()#执行添加
def close_spider(self, spider):
self.conn.close() #关闭连接
yield item
相关