Python 详解通过Scrapy框架实现爬取百度新冠疫情数据流程

前言

闲来无聊，写了一个爬虫程序获取百度疫情数据。申明一下，研究而已。而且页面应该会进程做反爬处理，可能需要调整对应xpath。

github仓库地址：代码仓库

本文主要使用的是scrapy框架。

环境部署

主要简单推荐一下

插件推荐

这里先推荐一个google chrome的扩展插件xpath helper，可以验证xpath语法是不是正确。

爬虫目标

需要爬取的页面：实时更新：新型冠状病毒肺炎疫情地图

主要爬取的目标选取了全国的数据以及各个身份的数据。

项目创建

使用scrapy命令创建项目

scrapy startproject yqsj

webdriver部署

这里就不重新讲一遍了，可以参考我这篇文章的部署方法：python 详解通过scrapy框架实现爬取csdn全站热榜标题热词流程

项目代码

开始撸代码，看一下百度疫情省份数据的问题。

页面需要点击展开全部span。所以在提取页面源码的时候需要模拟浏览器打开后，点击该按钮。所以按照这个方向，我们一步步来。

item定义

定义两个类yqsjprovinceitem和yqsjchinaitem，分别定义国内省份数据和国内数据。

# 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()
    # *输入
    overseas_input = scrapy.field()
    # 累计治愈
    cumulative_cure = scrapy.field()
    # 累计死亡
    cumulative_dead = scrapy.field()

中间件定义

需要打开页面后点击一下展开全部。

完整代码

# 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("//*[@id='nationtable']/div/span").click()
            # actionchains(spider.browser).click(searchbuttonelement)
            time.sleep(5)
            return htmlresponse(url=spider.browser.current_url, body=spider.browser.page_source,
                                encoding="utf-8", request=request)
        except timeoutexception as e:
            print('超时异常:{}'.format(e))
            spider.browser.execute_script('window.stop()')
        finally:
            spider.browser.close()
 
    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)

定义爬虫

分别获取国内疫情数据以及省份疫情数据。完整代码：

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @time    : 2021/11/7 22:05
# @author  : 至尊宝
# @site    : 
# @file    : baidu_yq.py
 
import scrapy
from selenium import webdriver
from selenium.webdriver.chrome.options import options
 
from yqsj.items import yqsjchinaitem, yqsjprovinceitem
 
 
class yqsjspider(scrapy.spider):
    name = 'yqsj'
    # allowed_domains = ['blog.csdn.net']
    start_urls = ['https://voice.baidu.com/act/newpneumonia/newpneumonia#tab0']
    china_xpath = "//div[contains(@class, 'virussummarysix_1-1-317_2zjjbj')]/text()"
    province_xpath = "//*[@id='nationtable']/table/tbody/tr[{}]/td/text()"
    province_xpath_1 = "//*[@id='nationtable']/table/tbody/tr[{}]/td/div/span/text()"
 
    def __init__(self):
        chrome_options = options()
        chrome_options.add_argument('--headless')  # 使用无头谷歌浏览器模式
        chrome_options.add_argument('--disable-gpu')
        chrome_options.add_argument('--no-sandbox')
        self.browser = webdriver.chrome(chrome_options=chrome_options,
                                        executable_path="e:\\chromedriver_win32\\chromedriver.exe")
        self.browser.set_page_load_timeout(30)
 
    def parse(self, response, **kwargs):
        country_info = response.xpath(self.china_xpath)
        yq_china = yqsjchinaitem()
        yq_china['exist_diagnosis'] = country_info[0].get()
        yq_china['asymptomatic'] = country_info[1].get()
        yq_china['exist_suspecte'] = country_info[2].get()
        yq_china['exist_severe'] = country_info[3].get()
        yq_china['cumulative_diagnosis'] = country_info[4].get()
        yq_china['overseas_input'] = country_info[5].get()
        yq_china['cumulative_cure'] = country_info[6].get()
        yq_china['cumulative_dead'] = country_info[7].get()
        yield yq_china
        
        # 遍历35个地区
        for x in range(1, 35):
            path = self.province_xpath.format(x)
            path1 = self.province_xpath_1.format(x)
            province_info = response.xpath(path)
            province_name = response.xpath(path1)
            yq_province = yqsjprovinceitem()
            yq_province['location'] = province_name.get()
            yq_province['new'] = province_info[0].get()
            yq_province['exist'] = province_info[1].get()
            yq_province['total'] = province_info[2].get()
            yq_province['cure'] = province_info[3].get()
            yq_province['dead'] = province_info[4].get()
            yield yq_province

pipeline输出结果文本

将结果按照一定的文本格式输出出来。完整代码：

# 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 yqsj.items import yqsjchinaitem, yqsjprovinceitem
 
 
class yqsjpipeline:
    def __init__(self):
        self.file = open('result.txt', 'w', encoding='utf-8')
 
    def process_item(self, item, spider):
        if isinstance(item, yqsjchinaitem):
            self.file.write(
                "国内疫情\n现有确诊\t{}\n无症状\t{}\n现有疑似\t{}\n现有重症\t{}\n累计确诊\t{}\n*输入\t{}\n累计治愈\t{}\n累计死亡\t{}\n".format(
                    item['exist_diagnosis'],
                    item['asymptomatic'],
                    item['exist_suspecte'],
                    item['exist_severe'],
                    item['cumulative_diagnosis'],
                    item['overseas_input'],
                    item['cumulative_cure'],
                    item['cumulative_dead']))
        if isinstance(item, yqsjprovinceitem):
            self.file.write(
                "省份:{}\t新增:{}\t现有:{}\t累计:{}\t治愈:{}\t死亡:{}\n".format(
                    item['location'],
                    item['new'],
                    item['exist'],
                    item['total'],
                    item['cure'],
                    item['dead']))
        return item
 
    def close_spider(self, spider):
        self.file.close()

配置文件改动

直接参考，自行调整：

# scrapy settings for yqsj 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 = 'yqsj'
 
spider_modules = ['yqsj.spiders']
newspider_module = 'yqsj.spiders'
 
 
# crawl responsibly by identifying yourself (and your website) on the user-agent
#user_agent = 'yqsj (+http://www.yourdomain.com)'
user_agent = 'mozilla/5.0'
 
# 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 = 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',
    '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'

验证结果

看看结果文件

总结

emmmm，闲着无聊，写着玩，没啥好总结的。

分享：

修心，亦是修行之一。顺境修力，逆境修心，缺一不可。 ——《剑来》

如果本文对你有作用的话，不要吝啬你的赞，谢谢。

以上就是python 详解通过scrapy框架实现爬取百度新冠疫情数据流程的详细内容，更多关于python scrapy框架的资料请关注其它相关文章！