变更

python爬虫/python爬虫练习/wangyizhaopin/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 = wangyizhaopin.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = wangyizhaopin

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/items.py

@@ -0,0 +1,18 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class WangyizhaopinItem(scrapy.Item):
+    # define the fields for your item here like:
+    name = scrapy.Field()
+    postTypeFullName = scrapy.Field()
+    description = scrapy.Field()
+    reqEducationName = scrapy.Field()
+    reqWorkYearsName = scrapy.Field()
+    requirement = scrapy.Field()
+    workPlaceNameList = scrapy.Field()
+

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/middlewares.py

@@ -0,0 +1,103 @@
+# 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
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class WangyizhaopinSpiderMiddleware:
+    # 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, 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 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 WangyizhaopinDownloaderMiddleware:
+    # 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)

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/pipelines.py

@@ -0,0 +1,46 @@
+# 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
+
+
+# useful for handling different item types with a single interface
+from itemadapter import ItemAdapter
+
+
+class WangyizhaopinPipeline:
+    def open_spider(self, spider):
+        if spider.name == "wyzp":
+            print("数据爬取开始")
+            self.f = open("wyzp.csv", mode="a", encoding="utf-8")
+
+    def close_spider(self, spider):
+        if spider.name == "wyzp":
+            print("数据爬取结束")
+            if self.f:
+                self.f.close()
+
+    def process_item(self, item, spider):
+        if spider.name == "wyzp":
+            # csv写入
+            self.f.write(f"{item['name']}\n")
+            return item
+
+
+class WangyizhaopinPipeline1:
+    def open_spider(self, spider):
+        if spider.name == "wyzp1":
+            print("数据爬取开始")
+            self.f = open("wyzp1.csv", mode="a", encoding="utf-8")
+
+    def close_spider(self, spider):
+        if spider.name == "wyzp1":
+            print("数据爬取结束")
+            if self.f:
+                self.f.close()
+
+    def process_item(self, item, spider):
+        if spider.name == "wyzp1":
+            # csv写入
+            self.f.write(f"{item['name']}\n")
+            return item

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/settings.py

@@ -0,0 +1,95 @@
+# Scrapy settings for wangyizhaopin 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
+
+BOT_NAME = "wangyizhaopin"
+
+SPIDER_MODULES = ["wangyizhaopin.spiders"]
+NEWSPIDER_MODULE = "wangyizhaopin.spiders"
+LOG_LEVEL = "WARNING"
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = "wangyizhaopin (+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://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 = {
+#    "wangyizhaopin.middlewares.WangyizhaopinSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    "wangyizhaopin.middlewares.WangyizhaopinDownloaderMiddleware": 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 = {
+   "wangyizhaopin.pipelines.WangyizhaopinPipeline": 300,
+   "wangyizhaopin.pipelines.WangyizhaopinPipeline1": 301,
+}
+
+# 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"
+
+# Set settings whose default value is deprecated to a future-proof value
+REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
+TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
+FEED_EXPORT_ENCODING = "utf-8"

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/spiders/__init__.py

@@ -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.

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/spiders/request.py

@@ -0,0 +1,6 @@
+# import requests
+#
+# url = "https://hr.163.com/api/hr163/position/queryPage"
+#
+# a = requests.get(url)
+# print(a.text)

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/spiders/tencent_crawl.py

@@ -0,0 +1,27 @@
+import scrapy
+from scrapy.linkextractors import LinkExtractor
+from scrapy.spiders import CrawlSpider, Rule
+
+#无法传参，只能应用于数据在一个页面里传参
+class TencentCrawlSpider(CrawlSpider):
+    name = "tencent_crawl"
+    allowed_domains = ["tencent.com"]
+    start_urls = ["https://careers.tencent.com/search.html?pcid=40001  "]
+
+    #链接提取规则
+    rules = (
+        #使用Rule类生成连接提取规则对象
+        # LinkExtracto 用于设置连接提取规则，一般永allow，接受正则表达式
+        # follow参数决定是否在提取后的响应中继续提取链接
+
+        # 设置详情页面链接提取规则
+        Rule(LinkExtractor(allow=r"https://careers.tencent.com/jobdesc.html?postId=\d+"), callback="parse_item"),)
+        # Rule(LinkExtractor(allow=r"https://careers.tencent.com/jobdesc.html?postId=\?"), callback="parse_item", follow=True),)
+
+    def parse_item(self, response):
+        item = {}
+        print(response.url)
+        # item["domain_id"] = response.xpath('//input[@id="sid"]/@value').get()
+        # item["name"] = response.xpath('//div[@id="name"]').get()
+        # item["description"] = response.xpath('//div[@id="description"]').get()
+        return item

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/spiders/wyzp.py

@@ -0,0 +1,57 @@
+import scrapy
+import json
+from wangyizhaopin.items import WangyizhaopinItem
+
+#该项目无法翻页，需要scrapy结合selenium等模拟点击
+
+class WyzpSpider(scrapy.Spider):
+    name = "wyzp"
+    allowed_domains = ["hr.163.com"]
+    start_urls = ["https://hr.163.com/job-list.html"]
+
+    def start_requests(self):
+
+
+        post_body = {"currentPage": 1, "pageSize": 10}
+        url = "https://hr.163.com/api/hr163/position/queryPage"
+
+        yield scrapy.Request(
+            url=url,
+            callback=self.parse_detail,
+            body=json.dumps(post_body),
+            method='POST',
+            headers={'Content-Type': 'application/json;charset=UTF-8'}
+        )
+
+    #     yield scrapy.Request(
+    #         url=self.start_urls[0],
+    #         callback=self.parse,
+    #         headers={'Content-Type': 'application/json;charset=UTF-8'}
+    #     )
+    # def parse(self, response, **kwargs):
+    #     part_url = response.xpath('//li[@class=" ant-pagination-next"]').extract_first()
+    #     print(part_url)
+    #     print(response.json)
+    #
+    #     if part_url != response.xpath('//li[@class="ant-pagination-disabled ant-pagination-next"]').extract_first():
+    #         pass
+
+    def parse_detail(self, response):
+        # 打印整个响应对象
+        # print(response.json())
+        # 解析JSON响应
+        data = response.json()
+        # print(1)
+        # 提取您需要的数据
+        for item in data['data']['list']:
+            info = WangyizhaopinItem()
+            info["name"] = item.get('name')
+            info["postTypeFullName"] = item.get('postTypeFullName')
+            info["description"] = item.get('description')
+            info["reqEducationName"] = item.get('reqEducationName')
+            info["reqWorkYearsName"] = item.get('reqWorkYearsName')
+            info["requirement"] = item.get('requirement')
+            info["workPlaceNameList"] = item.get('workPlaceNameList')
+            yield info
+
+

python爬虫/python爬虫练习/wangyizhaopin/wangyizhaopin/spiders/wyzp1.py

@@ -0,0 +1,57 @@
+import scrapy
+import json
+from wangyizhaopin.items import WangyizhaopinItem
+
+#该项目无法翻页，需要scrapy结合selenium等模拟点击
+
+class WyzpSpider(scrapy.Spider):
+    name = "wyzp1"
+    allowed_domains = ["hr.163.com"]
+    start_urls = ["https://hr.163.com/job-list.html"]
+
+    def start_requests(self):
+
+
+        post_body = {"currentPage": 1, "pageSize": 10}
+        url = "https://hr.163.com/api/hr163/position/queryPage"
+
+        yield scrapy.Request(
+            url=url,
+            callback=self.parse_detail,
+            body=json.dumps(post_body),
+            method='POST',
+            headers={'Content-Type': 'application/json;charset=UTF-8'}
+        )
+
+    #     yield scrapy.Request(
+    #         url=self.start_urls[0],
+    #         callback=self.parse,
+    #         headers={'Content-Type': 'application/json;charset=UTF-8'}
+    #     )
+    # def parse(self, response, **kwargs):
+    #     part_url = response.xpath('//li[@class=" ant-pagination-next"]').extract_first()
+    #     print(part_url)
+    #     print(response.json)
+    #
+    #     if part_url != response.xpath('//li[@class="ant-pagination-disabled ant-pagination-next"]').extract_first():
+    #         pass
+
+    def parse_detail(self, response):
+        # 打印整个响应对象
+        # print(response.json())
+        # 解析JSON响应
+        data = response.json()
+
+        # 提取您需要的数据
+        for item in data['data']['list']:
+            info = WangyizhaopinItem()
+            info["name"] = item.get('name')
+            info["postTypeFullName"] = item.get('postTypeFullName')
+            info["description"] = item.get('description')
+            info["reqEducationName"] = item.get('reqEducationName')
+            info["reqWorkYearsName"] = item.get('reqWorkYearsName')
+            info["requirement"] = item.get('requirement')
+            info["workPlaceNameList"] = item.get('workPlaceNameList')
+            yield info
+
+

python爬虫/python爬虫练习/wangyizhaopin/wyzp.csv

@@ -0,0 +1,10 @@
+内容运营实习生（AI音乐）
+高级游戏测试工程师（仙侠单机）
+算法实习生（搜索LLM和多模态技术）
+资深VFX特效设计师（界面）-第五人格
+资深UI视觉设计师-七日世界
+资深动画设计师-风格化在研
+资深概念设计师（场景）（天下）
+资深UI视觉设计师-卡通风格
+概念设计专家（角色）-萤火突击
+资深级UI 视觉设计师（萤火突击）