python scrapy写个一个爬虫示例

middlewares.py

# 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 fake_useragent import UserAgent


class TianyanchaSpiderMiddleware:
    # 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 TianyanchaDownloaderMiddleware:
    # 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)


class RandomUserAgent:
    def __init__(self) -> None:
        self.cookies_file = 'cookies.txt'
        self.cookies = {}

    def process_request(self, request, spider):
        self.read_cookies()

        ua = UserAgent()
        request.headers['User-Agent'] = ua.random
        request.cookies = self.cookies

        print('       ---hhhhhhhhhhhh', request.headers)

    def read_cookies(self):
        self.cookies = {}
        with open(self.cookies_file, 'r') as f:
            lines = f.read().split(';')
            for line in lines:
                name, value = self.split_cookie_item(line.strip())
                self.cookies[name] = value

    def split_cookie_item(self, item):
        index = item.find('=')
        key = item[:index]
        value = item[index + 1:]
        return key, value
    
if __name__ == '__main__':
    a = RandomUserAgent()
    a.read_cookies()

pipelines.py

# 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


class TianyanchaPipeline:
    def __init__(self) -> None:
        self.file = open('tianyancha.txt', 'w', encoding='utf-8')
        
    def __del__(self):
        self.file.close()
    
    def process_item(self, item, spider):
        item = dict(item)
        self.file.write(str(item) + ',\n')
        self.file.flush()
        
        return item

settings.py

# Scrapy settings for tianyancha 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 = "tianyancha"

SPIDER_MODULES = ["tianyancha.spiders"]
NEWSPIDER_MODULE = "tianyancha.spiders"


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = "tianyancha (+http://www.yourdomain.com)"

# 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 = 15
RAMDOMIZE_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 = {
#    "tianyancha.middlewares.TianyanchaSpiderMiddleware": 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   "tianyancha.middlewares.TianyanchaDownloaderMiddleware": 543,
   "tianyancha.middlewares.RandomUserAgent": 542,
}

# 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 = {
   "tianyancha.pipelines.TianyanchaPipeline": 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"

# 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"

items.py

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class TianyanchaItem(scrapy.Item):
    # 公司名称
    name = scrapy.Field()
    # 法人
    legal_person = scrapy.Field()
    # 注册资本
    registered_capital = scrapy.Field()
    # 注册时间
    registered_time = scrapy.Field()
    # 经营状态
    business_status = scrapy.Field()
    # 统一信用代码
    credit_code = scrapy.Field()
    # 地址
    address = scrapy.Field()
    # 邮箱
    email = scrapy.Field()
    # url
    url = scrapy.Field()
    # 员工人数
    staff_num = scrapy.Field()

tianyancha_cs.py

import scrapy

from tianyancha.items import TianyanchaItem
from scrapy import Request

class TianyanchaCsSpider(scrapy.Spider):
    name = "tianyancha_cs"
    allowed_domains = ["tianyancha.com"]
    
    def start_requests(self):
        url = "https://www.tianyancha.com/search?key=&base=hun&city=zhangsha&cacheCode=00430100V2020&sessionNo=1707115565.34684048&moneyStart=1000&moneyEnd=null&pageNum={}"
        for i in range(1, 10):
            yield Request(url.format(i), callback=self.parse)

    def parse(self, response):
        # print(response.request.headers)
        # print(response.body)
        # with open('tianyancha.html', 'w', encoding='utf-8') as f:
        #     f.write(response.body.decode('utf-8'))
        node_list = response.xpath('//div[@class="index_header__x2QZ3"]/div[@class="index_name__qEdWi"]/a/@href')
        print(len(node_list))
        for node in node_list:
            item = TianyanchaItem()
            item['url'] = node.extract()
            if item['url']:
                yield scrapy.Request(url=item['url'], meta={'item': item}, callback=self.parse_detail)

    def parse_detail(self, response):
        item = response.meta['item']
        # with open('tianyancha_detail.html', 'w', encoding='utf-8') as f:
        #     f.write(response.body.decode('utf-8'))
        item['name'] = response.xpath('//h1[@class="index_company-name__LqKlo"]/text()').extract_first()
        item['legal_person'] = response.xpath('//a[@class="index_link-click__NmHxP"]/text()').extract_first()
        item['registered_capital'] = response.xpath('//*[@id="page-root"]/div[3]/div/div[1]/div[1]/div[2]/div[1]/div[2]/div[1]/div[1]/div[3]/span[2]/text()').extract_first()
        item['registered_time'] = response.xpath('//*[@id="page-root"]/div[3]/div/div[1]/div[1]/div[2]/div[1]/div[2]/div[1]/div[1]/div[4]/span[2]/text()').extract_first()
        item['business_status'] = ''
        item['credit_code'] = response.xpath('//*[@id="page-root"]/div[3]/div/div[1]/div[1]/div[2]/div[1]/div[2]/div[1]/div[1]/div[1]/div/span/text()').extract_first()
        item['address'] = response.xpath('//span[@class="index_copy-text__ri7W6 index_detail-address-moretext__9R_Z1"]/text()').extract_first()
        item['email'] = response.xpath('//a[@class="index_detail-email__B_1Tq"]/text()').extract_first()
        item['staff_num'] = response.xpath('//*[@id="page-root"]/div[3]/div/div[1]/div[1]/div[2]/div[1]/div[2]/div[1]/div[3]/div[3]/span[2]/span/text()').extract_first()
        print(item)
        yield item