scrapy之内蒙古自治区环境保护厅

Posted 2020-10-31 mayunji

主程序：

# -*- coding: utf-8 -*-
import re, scrapy
from urllib.parse import urljoin
from nmgepb.items import NmgepbItem


class BasicNmgepbSpider(scrapy.Spider):
    name = ‘basic_nmgepb‘
    allowed_domains = [‘nmgepb.gov.cn‘]
    start_urls = [‘http://nmgepb.gov.cn/‘]


    def __init__(self):
        self.countNum = 1
        self.startLink ="http://www.nmgepb.gov.cn/ywgl/hjpj/xmslqk/index.html"


    def start_requests(self):
        yield scrapy.Request(url=self.startLink, dont_filter=True, callback=self.link_parse)


    def customXpathParse(self, value):
        return ‘‘.join(value).strip()


    def customReParse(self, condition, index=1):
        if condition:
            return condition.group(index).strip()
        else:
            return ""


    def link_parse(self, response):
        if (len(response.text) < 1000):
            yield scrapy.Request(url=response.url, dont_filter=True, callback=self.link_parse)
        else:
            allLinks = response.xpath("/html/body/div[3]/div/div[3]/div[2]/ul/li/span[2]/a/@href").extract()
            for link in allLinks:
                link = urljoin(response.url, link)
                yield scrapy.Request(url=link, callback=self.info_parse)
            if (response.url == self.startLink):
                for pageNum in range(1, 6):
                    link = ‘{0}_{1}.html‘.format(self.startLink.split(‘.html‘)[0], pageNum)
                    yield scrapy.Request(url=link, callback=self.link_parse)


    def info_parse(self, response):
        if ‘http://www.nmgepb.gov.cn/ywgl/hjpj/xmslqk/201412/t20141230_1472451.html‘ != response.url and ‘http://www.nmgepb.gov.cn/ywgl/hjpj/xmslqk/201412/t20141230_1472450.html‘ != response.url and ‘http://www.nmgepb.gov.cn/ywgl/hjpj/xmslqk/201412/t20141230_1472443.html‘ != response.url:
            item = NmgepbItem()
            trData = response.xpath(‘//table//tr‘)
            tableClass = self.customXpathParse(response.xpath(‘//table/@class‘).extract())

            if trData:
                for data in trData:
                    tdNum = len(data.xpath(‘./td‘))
                    firstTd = self.customXpathParse(data.xpath(‘./td[1]//text()‘).extract())
                    lastTd = self.customXpathParse(data.xpath(‘./td[6]//text()‘).extract())

                    if (tdNum == 3):
                        if (tableClass == ‘MsoTableGrid‘):
                            item[‘link‘] = response.url
                            item[‘title‘] = self.customXpathParse(data.xpath(‘./td[2]//text()‘).extract())
                            item[‘place‘] = self.customXpathParse(data.xpath(‘./td[3]//text()‘).extract())
                            item[‘company‘] = ‘‘
                            item[‘mechanism‘] = ‘‘
                            item[‘date‘] = ‘‘
                            if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                                print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                                self.countNum += 1
                                yield item

                        elif (tableClass == ‘FCK__ShowTableBorders‘):
                            item[‘link‘] = response.url
                            item[‘title‘] = self.customXpathParse(data.xpath(‘./td[3]//text()‘).extract())
                            item[‘place‘] = ‘‘
                            item[‘company‘] = ‘‘
                            item[‘mechanism‘] = ‘‘
                            item[‘date‘] = self.customXpathParse(data.xpath(‘./td[2]//text()‘).extract())
                            if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                                print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                                self.countNum += 1
                                yield item

                    elif (tdNum == 6) and (lastTd):
                        item[‘link‘] = response.url
                        item[‘title‘] = self.customXpathParse(data.xpath(‘./td[2]//text()‘).extract())
                        item[‘place‘] = self.customXpathParse(data.xpath(‘./td[3]//text()‘).extract())
                        item[‘company‘] = self.customXpathParse(data.xpath(‘./td[4]//text()‘).extract())
                        item[‘mechanism‘] = self.customXpathParse(data.xpath(‘./td[5]//text()‘).extract())
                        item[‘date‘] = self.customXpathParse(data.xpath(‘./td[6]//text()‘).extract())
                        if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                            print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                            self.countNum += 1
                            yield item

                    elif (tdNum == 5 or tdNum == 6) and (not lastTd):
                        if firstTd.isdigit():
                            item[‘link‘] = response.url
                            item[‘title‘] = self.customXpathParse(data.xpath(‘./td[2]//text()‘).extract())
                            item[‘place‘] = self.customXpathParse(data.xpath(‘./td[3]//text()‘).extract())
                            item[‘company‘] = self.customXpathParse(data.xpath(‘./td[4]//text()‘).extract())
                            item[‘mechanism‘] = ‘‘
                            item[‘date‘] = self.customXpathParse(data.xpath(‘./td[5]//text()‘).extract())
                            if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                                print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                                self.countNum += 1
                                yield item
                        else:
                            item[‘link‘] = response.url
                            item[‘title‘] = self.customXpathParse(data.xpath(‘./td[1]//text()‘).extract())
                            item[‘place‘] = self.customXpathParse(data.xpath(‘./td[2]//text()‘).extract())
                            item[‘company‘] = self.customXpathParse(data.xpath(‘./td[3]//text()‘).extract())
                            item[‘mechanism‘] = self.customXpathParse(data.xpath(‘./td[4]//text()‘).extract())
                            item[‘date‘] = self.customXpathParse(data.xpath(‘./td[5]//text()‘).extract())
                            if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                                print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                                self.countNum += 1
                                yield item

                    elif (tdNum == 7):
                        item[‘link‘] = response.url
                        item[‘title‘] = self.customXpathParse(data.xpath(‘./td[2]//text()‘).extract())
                        item[‘place‘] = self.customXpathParse(data.xpath(‘./td[3]//text()‘).extract())
                        item[‘company‘] = self.customXpathParse(data.xpath(‘./td[4]//text()‘).extract())
                        item[‘mechanism‘] = ‘‘
                        item[‘date‘] = self.customXpathParse(data.xpath(‘./td[7]//text()‘).extract())
                        if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                            print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                            self.countNum += 1
                            yield item

                    elif (tdNum == 9):
                        item[‘link‘] = response.url
                        item[‘title‘] = self.customXpathParse(data.xpath(‘./td[2]//text()‘).extract())
                        item[‘place‘] = self.customXpathParse(data.xpath(‘./td[3]//text()‘).extract())
                        item[‘company‘] = self.customXpathParse(data.xpath(‘./td[4]//text()‘).extract())
                        item[‘mechanism‘] = ‘‘
                        item[‘date‘] = self.customXpathParse(data.xpath(‘./td[9]//text()‘).extract())
                        if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                            print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                            self.countNum += 1
                            yield item

            else:
                item[‘link‘] = response.url
                item[‘title‘] = self.customReParse(re.search(r‘<strong>项目名称：</strong>(.*?)<‘, response.text, re.I))
                item[‘place‘] = self.customReParse(re.search(r‘<strong>建设地点：</strong>(.*?)<‘, response.text, re.I))
                item[‘company‘] = self.customReParse(re.search(r‘<strong>建设单位：</strong>(.*?)<‘, response.text, re.I))
                item[‘mechanism‘] = self.customReParse(re.search(r‘<strong>环境影响评价机构：</strong>(.*?)<‘, response.text, re.I))
                item[‘date‘] = self.customReParse(re.search(r‘<strong>受理日期：</strong>(.*?)<‘, response.text, re.I))
                if (item[‘title‘]) and (item[‘title‘] != ‘编号‘) and (item[‘title‘] != ‘项目名称‘):
                    print(‘{0:>3}：\n\t项目链接：{1}\n\t项目名称：{2}\n\n‘.format(self.countNum, item[‘link‘], item[‘title‘]))
                    self.countNum += 1
                    yield item

items:

import scrapy


class NmgepbItem(scrapy.Item):
    link = scrapy.Field()
    title = scrapy.Field()
    place = scrapy.Field()
    company = scrapy.Field()
    mechanism = scrapy.Field()
    date = scrapy.Field()

middlewares:

from scrapy import signals


class NmgepbSpiderMiddleware(object):
    # 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, dict 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 Response, dict
        # 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 NmgepbDownloaderMiddleware(object):
    # 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)

pipelines:

import os, csv


class NmgepbPipeline(object):
    def __init__(self):
        self.csvFilePath = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), ‘nmgepb.csv‘)
        self.csvFile = open(self.csvFilePath, ‘w‘, encoding=‘gb18030‘, newline=‘‘)
        self.csvWrite = csv.writer(self.csvFile)
        self.csvWrite.writerow([‘页面链接‘, ‘项目名称‘, ‘建设地点‘, ‘建设单位‘, ‘评价机构‘, ‘受理日期‘])


    def process_item(self, item, spider):
        self.csvWrite.writerow(
            [item.get(‘link‘), item.get(‘title‘), item.get(‘place‘), item.get(‘company‘), item.get(‘mechanism‘), item.get(‘date‘)]
        )
        return item


    def close_spider(self, spider):
        self.csvFile.close()
        print("恭喜, 数据采集完成, 存储路径：%s"%self.csvFilePath)

settings（加入）:

DEFAULT_REQUEST_HEADERS = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:59.0) Gecko/20100101 Firefox/59.0"
}
ITEM_PIPELINES = {
   ‘nmgepb.pipelines.NmgepbPipeline‘: 300,
}