Python 详解通过Scrapy框架实现爬取百度新冠疫情数据流程

scrapy startproject yqsj

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
 
import scrapy
 
 
class YqsjProvinceItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    location = scrapy.Field()
    new = scrapy.Field()
    exist = scrapy.Field()
    total = scrapy.Field()
    cure = scrapy.Field()
    dead = scrapy.Field()
 
 
class YqsjChinaItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 现有确诊
    exist_diagnosis = scrapy.Field()
    # 无症状
    asymptomatic = scrapy.Field()
    # 现有疑似
    exist_suspecte = scrapy.Field()
    # 现有重症
    exist_severe = scrapy.Field()
    # 累计确诊
    cumulative_diagnosis = scrapy.Field()
    # 境外输入
    overseas_input = scrapy.Field()
    # 累计治愈
    cumulative_cure = scrapy.Field()
    # 累计死亡
    cumulative_dead = scrapy.Field()

# 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
from scrapy.http import HtmlResponse
from selenium.common.exceptions import TimeoutException
from selenium.webdriver import ActionChains
import time
 
 
class YqsjSpiderMiddleware:
    # 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 YqsjDownloaderMiddleware:
    # 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
        try:
            spider.browser.get(request.url)
            spider.browser.maximize_window()
            time.sleep(2)
            spider.browser.find_element_by_xpath("/*;q=0.8',
    'Accept-Language': 'en',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36'
}
 
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
   'yqsj.middlewares.YqsjSpiderMiddleware': 543,
}
 
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'yqsj.middlewares.YqsjDownloaderMiddleware': 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 = {
   'yqsj.pipelines.YqsjPipeline': 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'