zoukankan html css js c++ java

python之scrapy爬取jd和qq招聘信息

1、settings.py文件

# -*- coding: utf-8 -*-

# Scrapy settings for jd project
#
# For simplicity, this file 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 = 'jd'

SPIDER_MODULES = ['jd.spiders']
NEWSPIDER_MODULE = 'jd.spiders'

LOG_LEVEL="WARNING"
LOG_FILE="./jingdong1.log"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'jd (+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 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 = {
#    'jd.middlewares.JdSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'jd.middlewares.JdDownloaderMiddleware': 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 = {
#    'jd.pipelines.JdPipeline': 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'

View Code

2、jingdong.py文件

# -*- coding: utf-8 -*-
import scrapy

import logging
import json
logger = logging.getLogger(__name__)
class JingdongSpider(scrapy.Spider):
    name = 'jingdong'
    allowed_domains = ['zhaopin.jd.com']
    start_urls = ['http://zhaopin.jd.com/web/job/job_list?page=1']
    pageNum = 1
    def parse(self, response):
        content  = response.body.decode()
        content = json.loads(content)
        ##########去除列表中字典集中的空值###########
        for i in range(len(content)):
            #list(content[i].keys()获取当前字典中的key
            for key in list(content[i].keys()): #content[i]为字典
                if not content[i].get(key):#content[i].get(key)根据key获取value
                    del content[i][key] #删除空值字典
        for i in range(len(content)):
            logging.warning(content[i])

        self.pageNum = self.pageNum+1
        if self.pageNum<=355:
            next_url = "http://zhaopin.jd.com/web/job/job_list?page="+str(self.pageNum)
            yield scrapy.Request(
                next_url,
                callback=self.parse
            )
        pass

3、注意点，针对jingdong的招聘翻页是使用javascrapt，所以无法使用crawlscrapy进行自动翻页，但是我们再network中查看其获取数据的方法。

如：http://zhaopin.jd.com/web/job/job_list?page=2

#############jingdong可以了，那么试试tencent公司的招聘信息吧###############

测试下吧！

结果知道了吧！！！！！开始干活！！！！！！！！！！

1、settings.py

# -*- coding: utf-8 -*-

# 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://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 = 'tencent'

SPIDER_MODULES = ['tencent.spiders']
NEWSPIDER_MODULE = 'tencent.spiders'

LOG_LEVEL="WARNING"
LOG_FILE="./qq.log"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'

# 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://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 = {
#    'tencent.middlewares.TencentSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'tencent.middlewares.TencentDownloaderMiddleware': 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 = {
#    'tencent.pipelines.TencentPipeline': 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'

View Code

2、mahuateng.py

# -*- coding: utf-8 -*-
import scrapy

import json
import logging
class MahuatengSpider(scrapy.Spider):
    name = 'mahuateng'
    allowed_domains = ['careers.tencent.com']
    start_urls = ['https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1561688387174&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=40003&attrId=&keyword=&pageIndex=1&pageSize=10&language=zh-cn&area=cn']
    pageNum = 1
    def parse(self, response):
        content = response.body.decode()
        content = json.loads(content)
        content=content['Data']['Posts']
        #删除空字典
        for con in content:
            #print(con)
            for key in list(con.keys()):
                if not con.get(key):
                    del con[key]
        #记录每一个岗位信息
        for con in content:
            logging.warning(con)

        #####翻页######
        self.pageNum = self.pageNum+1
        if self.pageNum<=118:
            next_url = "https://careers.tencent.com/tencentcareer/api/post/Query?timestamp=1561688387174&countryId=&cityId=&bgIds=&productId=&categoryId=&parentCategoryId=40003&attrId=&keyword=&pageIndex="+str(self.pageNum)+"&pageSize=10&language=zh-cn&area=cn"
            yield  scrapy.Request(
                next_url,
                callback=self.parse
            )

个人测试是可以的，你们的就看运气了，哈哈！

这些都是个人玩的，码的比较丑陋。

查看全文

相关阅读:
图的理论基础
 哈夫曼树(三)之 Java详解
 哈夫曼树(二)之 C++详解
 哈夫曼树(一)之 C语言详解
 基数排序
 桶排序
 归并排序
 堆排序
 选择排序
 希尔排序

原文地址：https://www.cnblogs.com/ywjfx/p/11101091.html