变更

python爬虫/scrapy/meinv/meinv/items.py

@@ -0,0 +1,14 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class MeinvItem(scrapy.Item):
+    # define the fields for your item here like:
+    name = scrapy.Field()
+    img = scrapy.Field()
+    local_path = scrapy.Field()
+

python爬虫/scrapy/meinv/meinv/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 MeinvSpiderMiddleware:
+    # 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 MeinvDownloaderMiddleware:
+    # 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/scrapy/meinv/meinv/pipelines.py

@@ -0,0 +1,60 @@
+# 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
+from scrapy.pipelines.images import ImagesPipeline
+import scrapy
+import pymysql
+from meinv.settings import MYSQL
+
+
+class MeinvPipeline:
+    def open_spider(self, spider):
+        print("数据爬取开始")
+        self.conn = pymysql.connect(
+            host=MYSQL["host"],
+            port=MYSQL["port"],
+            user=MYSQL["user"],
+            password=MYSQL["password"],
+            database=MYSQL["database"]
+        )
+
+    def close_spider(self, spider):
+        print("数据爬取结束")
+        self.conn.close()
+
+    def process_item(self, item, spider):
+        # mysql写入
+        try:
+            cursor = self.conn.cursor()
+            sql = "insert into tu (name, img) values (%s,%s)"
+            cursor.execute(sql, (item['name'], item["local_path"]))
+            self.conn.commit()
+            print("写入成功")
+        except:
+            self.conn.rollback()
+        finally:
+            if cursor:
+                cursor.close()
+        return item
+
+
+# 想使用image需要在setting中设置存放位置IMAGES_STORE
+class MeinvSavePipeline(ImagesPipeline):  # 利用图片管道下载
+    def get_media_requests(self, item, info):  # 负责下载
+        return scrapy.Request(item["img"])  # 直接返回结果
+
+    def file_path(self, request, response=None, info=None, *, item=None):  # 准备文件路径
+        file_name = request.url.split("/")[-1]
+        return f"img/{file_name}"  # 创建img/***
+
+    def item_completed(self, results, item, info):  # 返回文件详细信息
+        ok, finfo = results[0]
+        path = finfo['path']
+        item["local_path"] = path
+        print(results)
+        return item

python爬虫/scrapy/meinv/meinv/settings.py

@@ -0,0 +1,100 @@
+# Scrapy settings for meinv 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 = "meinv"
+
+SPIDER_MODULES = ["meinv.spiders"]
+NEWSPIDER_MODULE = "meinv.spiders"
+LOG_LEVEL = "WARNING"
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+# USER_AGENT = "meinv (+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 = {
+#    "meinv.middlewares.MeinvSpiderMiddleware": 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    "meinv.middlewares.MeinvDownloaderMiddleware": 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 = {
+    "meinv.pipelines.MeinvPipeline": 300,
+    "meinv.pipelines.MeinvSavePipeline": 280,
+}
+IMAGES_STORE = './meinvtupian'
+# 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"
+MYSQL = {
+    "host": "localhost",
+    "port": 3306,
+    "user": "root",
+    "password": "123123",
+    "database": "spider"
+}
+# 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/scrapy/meinv/meinv/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/scrapy/meinv/meinv/spiders/meinv_spider.py

@@ -0,0 +1,36 @@
+import scrapy
+from meinv.items import MeinvItem
+
+
+class MeinvSpiderSpider(scrapy.Spider):
+    name = "meinv_spider"
+    allowed_domains = ["www.tpzj.com"]
+    start_urls = ["https://www.tpzj.com/meinv/xiezhen/"]
+
+    def parse(self, response):
+        li_list = response.xpath("//ul[@class='list_con_box_ul']/li")
+        for li in li_list:
+            href = li.xpath("./a/@href").extract_first()
+            yield scrapy.Request(
+                url=response.urljoin(href),  # href不是完整的url地址，使用urljoin拼接url
+                method='get',
+                callback=self.parse_detail  # 回调函数，当相应回馈后，如何进行相应处理
+            )
+            # print(response.urljoin(href))
+        # 下一页
+        next_href = response.xpath(
+            "//div[@class='pages']/ul/li/a[contains(text(), '下一页')]/@href").extract_first()  # contains（text(),""）判断文字是否包含内容
+        if next_href:
+            yield scrapy.Request(
+                url=response.urljoin(next_href),
+                callback=self.parse
+            )
+
+    def parse_detail(self, response):
+        name = response.xpath('//div[@class="list_con bgff"]/h1/text()').extract_first()  # 没有first 会返回一个列表，导致报错
+        img_src = response.xpath("//div[@id='bigpic']/a/img/@src").extract_first()
+        item = MeinvItem()
+        item["name"] = name
+        item["img"] = img_src
+        print(item)
+        yield item