天气网七天以内的天气

python/spider/info/weather/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 = tianqi.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = tianqi

python/spider/info/weather/tianqi/items.py

@@ -0,0 +1,28 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class TianqiItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
+
+class WeatherItem(scrapy.Item):
+    region = scrapy.Field()
+    provincial = scrapy.Field()
+    data_time = scrapy.Field()
+    city = scrapy.Field()
+
+    weather_1 = scrapy.Field()
+    wind_direction_1 = scrapy.Field()
+    wind_power_1 = scrapy.Field()
+    temperature_1 = scrapy.Field()
+
+    weather_2 = scrapy.Field()
+    wind_direction_2 = scrapy.Field()
+    wind_power_2 = scrapy.Field()
+    temperature_2 = scrapy.Field()

python/spider/info/weather/tianqi/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 TianqiSpiderMiddleware:
+    # 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 TianqiDownloaderMiddleware:
+    # 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/spider/info/weather/tianqi/pipelines.py

@@ -0,0 +1,45 @@
+# 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 openpyxl import Workbook
+
+
+class TianqiPipeline:
+    def process_item(self, item, spider):
+        return item
+
+
+class ExcelPipeline:
+    def __init__(self):
+        self.workbook = Workbook()
+        self.worksheets = {}
+
+    def open_spider(self, spider):
+        self.workbook = Workbook()
+        self.workbook.remove(self.workbook.active)
+
+    def close_spider(self, spider):
+        self.workbook.save('weather.xlsx')
+        self.workbook.close()
+
+    def process_item(self, item, spider):
+        region = item['region']
+        if region not in self.worksheets:
+            ws = self.workbook.create_sheet(title=region)
+            # 定义列标题的顺序
+            ws.append(['省份', '日期时间', '城市', '白天温度', '白天天气', '白天风向', '白天风力',
+                       '夜间温度', '夜间天气', '夜间风向', '夜间风力'])
+            self.worksheets[region] = ws
+        ws = self.worksheets[region]
+        # 根据标题顺序将数据添加到对应列
+        ws.append([
+            item['provincial'], item['data_time'], item['city'],
+            item['temperature_1'], item['weather_1'], item['wind_direction_1'], item['wind_power_1'],
+            item['temperature_2'], item['weather_2'], item['wind_direction_2'], item['wind_power_2']
+        ])
+        return item

python/spider/info/weather/tianqi/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 = tianqi.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = tianqi

python/spider/info/weather/tianqi/settings.py

@@ -0,0 +1,95 @@
+# Scrapy settings for tianqi 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 = "tianqi"
+
+SPIDER_MODULES = ["tianqi.spiders"]
+NEWSPIDER_MODULE = "tianqi.spiders"
+
+LOG_LEVEL = "WARNING"
+# 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/125.0.0.0 Safari/537.36"
+
+# 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://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 2
+RANDOMIZE_DOWNLOAD_DELAY = True
+# 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 = {
+#    "tianqi.middlewares.TianqiSpiderMiddleware": 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    "tianqi.middlewares.TianqiDownloaderMiddleware": 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 = {
+   "tianqi.pipelines.TianqiPipeline": 300,
+   "tianqi.pipelines.ExcelPipeline": 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/spider/info/weather/tianqi/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/spider/info/weather/tianqi/spiders/weather.py

@@ -0,0 +1,76 @@
+import scrapy
+from urllib.parse import urljoin
+from ..items import WeatherItem
+
+class WeatherSpider(scrapy.Spider):
+    name = "weather"
+    allowed_domains = ["www.weather.com.cn"]
+    start_urls = ["http://www.weather.com.cn/textFC/hb.shtml"]
+
+    def parse(self, response):
+        areas = response.xpath('/html/body/div[4]/div[2]/div/div/ul[1]/li')
+        for area in areas:
+            area_suffix = area.xpath('.//a/@href').extract_first()
+            area_url = urljoin(response.url, area_suffix)
+            yield scrapy.Request(area_url, callback=self.each_page)
+
+    def each_page(self, response):
+        all_days_info = response.xpath("//div[@class='hanml']/div[not(@style='display: none;')]//table")
+        region = response.xpath('//title/text()').get().replace('天气预报', '')
+        print(f"正在爬取{region}")
+        for days_info in all_days_info:
+            info_trs = days_info.css('tr')
+
+            data_time = info_trs[0].xpath(".//td[3]/text()").extract_first().replace('白天', '').replace('夜间', '')
+            provincial = info_trs[2].xpath(".//td[1]/a/text()").extract_first()
+
+            loop_count = 1
+            for info_tr in info_trs:
+                loop_count += 1
+                if loop_count < 4:
+                    continue
+                if loop_count == 4:
+                    city = info_tr.xpath(".//td[2]/a/text()").extract_first()
+
+                    weather_1 = info_tr.xpath(".//td[3]/text()").extract_first()
+                    wind_direction_1 = info_tr.xpath(".//td[4]/span[1]/text()").extract_first()
+                    wind_power_1 = info_tr.xpath(".//td[4]/span[2]/text()").extract_first()
+                    temperature_1 = (info_tr.xpath(".//td[5]/text()").extract_first())
+
+                    weather_2 = info_tr.xpath(".//td[6]/text()").extract_first()
+                    wind_direction_2 = info_tr.xpath(".//td[7]/span[1]/text()").extract_first()
+                    wind_power_2 = info_tr.xpath(".//td[7]/span[2]/text()").extract_first()
+                    temperature_2 = (info_tr.xpath(".//td[8]/text()").extract_first())
+                else:
+                    city = info_tr.xpath(".//td[1]/a/text()").extract_first()
+
+                    weather_1 = info_tr.xpath(".//td[2]/text()").extract_first()
+                    wind_direction_1 = info_tr.xpath(".//td[3]/span[1]/text()").extract_first()
+                    wind_power_1 = info_tr.xpath(".//td[3]/span[2]/text()").extract_first()
+                    temperature_1 = (info_tr.xpath(".//td[4]/text()").extract_first())
+
+                    weather_2 = info_tr.xpath(".//td[5]/text()").extract_first()
+                    wind_direction_2 = info_tr.xpath(".//td[6]/span[1]/text()").extract_first()
+                    wind_power_2 = info_tr.xpath(".//td[6]/span[2]/text()").extract_first()
+                    temperature_2 = (info_tr.xpath(".//td[7]/text()").extract_first())
+                weather_item = WeatherItem()
+                weather_item['region'] = region
+                weather_item['provincial'] = provincial
+                weather_item['data_time'] = data_time
+                weather_item['city'] = city
+                weather_item['weather_1'] = weather_1
+                weather_item['weather_2'] = weather_2
+                weather_item['wind_direction_1'] = wind_direction_1
+                weather_item['wind_power_1'] = wind_power_1
+                weather_item['temperature_1'] = temperature_1
+                weather_item['weather_2'] = weather_2
+                weather_item['wind_direction_2'] = wind_direction_2
+                weather_item['wind_power_2'] = wind_power_2
+                weather_item['temperature_2'] = temperature_2
+                yield weather_item
+
+
+
+
+
+

python/spider/info/weather/tianqi/tianqi/items.py

@@ -0,0 +1,28 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class TianqiItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass
+
+class WeatherItem(scrapy.Item):
+    region = scrapy.Field()
+    provincial = scrapy.Field()
+    data_time = scrapy.Field()
+    city = scrapy.Field()
+
+    weather_1 = scrapy.Field()
+    wind_direction_1 = scrapy.Field()
+    wind_power_1 = scrapy.Field()
+    temperature_1 = scrapy.Field()
+
+    weather_2 = scrapy.Field()
+    wind_direction_2 = scrapy.Field()
+    wind_power_2 = scrapy.Field()
+    temperature_2 = scrapy.Field()

python/spider/info/weather/tianqi/tianqi/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 TianqiSpiderMiddleware:
+    # 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 TianqiDownloaderMiddleware:
+    # 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/spider/info/weather/tianqi/tianqi/pipelines.py

@@ -0,0 +1,45 @@
+# 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 openpyxl import Workbook
+
+
+class TianqiPipeline:
+    def process_item(self, item, spider):
+        return item
+
+
+class ExcelPipeline:
+    def __init__(self):
+        self.workbook = Workbook()
+        self.worksheets = {}
+
+    def open_spider(self, spider):
+        self.workbook = Workbook()
+        self.workbook.remove(self.workbook.active)
+
+    def close_spider(self, spider):
+        self.workbook.save('weather.xlsx')
+        self.workbook.close()
+
+    def process_item(self, item, spider):
+        region = item['region']
+        if region not in self.worksheets:
+            ws = self.workbook.create_sheet(title=region)
+            # 定义列标题的顺序
+            ws.append(['省份', '日期时间', '城市', '白天温度', '白天天气', '白天风向', '白天风力',
+                       '夜间温度', '夜间天气', '夜间风向', '夜间风力'])
+            self.worksheets[region] = ws
+        ws = self.worksheets[region]
+        # 根据标题顺序将数据添加到对应列
+        ws.append([
+            item['provincial'], item['data_time'], item['city'],
+            item['temperature_1'], item['weather_1'], item['wind_direction_1'], item['wind_power_1'],
+            item['temperature_2'], item['weather_2'], item['wind_direction_2'], item['wind_power_2']
+        ])
+        return item

python/spider/info/weather/tianqi/tianqi/settings.py

@@ -0,0 +1,95 @@
+# Scrapy settings for tianqi 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 = "tianqi"
+
+SPIDER_MODULES = ["tianqi.spiders"]
+NEWSPIDER_MODULE = "tianqi.spiders"
+
+LOG_LEVEL = "WARNING"
+# 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/125.0.0.0 Safari/537.36"
+
+# 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://docs.scrapy.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 2
+RANDOMIZE_DOWNLOAD_DELAY = True
+# 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 = {
+#    "tianqi.middlewares.TianqiSpiderMiddleware": 543,
+# }
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    "tianqi.middlewares.TianqiDownloaderMiddleware": 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 = {
+   "tianqi.pipelines.TianqiPipeline": 300,
+   "tianqi.pipelines.ExcelPipeline": 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/spider/info/weather/tianqi/tianqi/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/spider/info/weather/tianqi/tianqi/spiders/weather.py

@@ -0,0 +1,76 @@
+import scrapy
+from urllib.parse import urljoin
+from ..items import WeatherItem
+
+class WeatherSpider(scrapy.Spider):
+    name = "weather"
+    allowed_domains = ["www.weather.com.cn"]
+    start_urls = ["http://www.weather.com.cn/textFC/hb.shtml"]
+
+    def parse(self, response):
+        areas = response.xpath('/html/body/div[4]/div[2]/div/div/ul[1]/li')
+        for area in areas:
+            area_suffix = area.xpath('.//a/@href').extract_first()
+            area_url = urljoin(response.url, area_suffix)
+            yield scrapy.Request(area_url, callback=self.each_page)
+
+    def each_page(self, response):
+        all_days_info = response.xpath("//div[@class='hanml']/div[not(@style='display: none;')]//table")
+        region = response.xpath('//title/text()').get().replace('天气预报', '')
+        print(f"正在爬取{region}")
+        for days_info in all_days_info:
+            info_trs = days_info.css('tr')
+
+            data_time = info_trs[0].xpath(".//td[3]/text()").extract_first().replace('白天', '').replace('夜间', '')
+            provincial = info_trs[2].xpath(".//td[1]/a/text()").extract_first()
+
+            loop_count = 1
+            for info_tr in info_trs:
+                loop_count += 1
+                if loop_count < 4:
+                    continue
+                if loop_count == 4:
+                    city = info_tr.xpath(".//td[2]/a/text()").extract_first()
+
+                    weather_1 = info_tr.xpath(".//td[3]/text()").extract_first()
+                    wind_direction_1 = info_tr.xpath(".//td[4]/span[1]/text()").extract_first()
+                    wind_power_1 = info_tr.xpath(".//td[4]/span[2]/text()").extract_first()
+                    temperature_1 = (info_tr.xpath(".//td[5]/text()").extract_first())
+
+                    weather_2 = info_tr.xpath(".//td[6]/text()").extract_first()
+                    wind_direction_2 = info_tr.xpath(".//td[7]/span[1]/text()").extract_first()
+                    wind_power_2 = info_tr.xpath(".//td[7]/span[2]/text()").extract_first()
+                    temperature_2 = (info_tr.xpath(".//td[8]/text()").extract_first())
+                else:
+                    city = info_tr.xpath(".//td[1]/a/text()").extract_first()
+
+                    weather_1 = info_tr.xpath(".//td[2]/text()").extract_first()
+                    wind_direction_1 = info_tr.xpath(".//td[3]/span[1]/text()").extract_first()
+                    wind_power_1 = info_tr.xpath(".//td[3]/span[2]/text()").extract_first()
+                    temperature_1 = (info_tr.xpath(".//td[4]/text()").extract_first())
+
+                    weather_2 = info_tr.xpath(".//td[5]/text()").extract_first()
+                    wind_direction_2 = info_tr.xpath(".//td[6]/span[1]/text()").extract_first()
+                    wind_power_2 = info_tr.xpath(".//td[6]/span[2]/text()").extract_first()
+                    temperature_2 = (info_tr.xpath(".//td[7]/text()").extract_first())
+                weather_item = WeatherItem()
+                weather_item['region'] = region
+                weather_item['provincial'] = provincial
+                weather_item['data_time'] = data_time
+                weather_item['city'] = city
+                weather_item['weather_1'] = weather_1
+                weather_item['weather_2'] = weather_2
+                weather_item['wind_direction_1'] = wind_direction_1
+                weather_item['wind_power_1'] = wind_power_1
+                weather_item['temperature_1'] = temperature_1
+                weather_item['weather_2'] = weather_2
+                weather_item['wind_direction_2'] = wind_direction_2
+                weather_item['wind_power_2'] = wind_power_2
+                weather_item['temperature_2'] = temperature_2
+                yield weather_item
+
+
+
+
+
+