Python 爬虫豆瓣 Python 通过xpath属性爬取豆瓣热映的电影信息

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
 
import scrapy
 
 
class DoubanPlayingItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 电影名
    title = scrapy.Field()
    # 电影分数
    score = scrapy.Field()
    # 电影发行年份
    release = scrapy.Field()
    # 电影时长
    duration = scrapy.Field()
    # 地区
    region = scrapy.Field()
    # 电影导演
    director = scrapy.Field()
    # 电影主演
    actors = scrapy.Field()

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
import time
 
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
 
 
class DoubanPlayingSpiderMiddleware:
    # 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 DoubanPlayingDownloaderMiddleware:
    # 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='nowplaying']/div[@class='more']").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)

#!/user/bin/env python
# coding=utf-8
"""
@project : douban_playing
@author  : huyi
@file   : douban_playing.py
@ide    : PyCharm
@time   : 2021-11-10 16:31:23
"""
 
import scrapy
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
 
from douban_playing.items import DoubanPlayingItem
 
 
class DoubanPlayingSpider(scrapy.Spider):
    name = 'dbp'
    # allowed_domains = ['blog.csdn.net']
    start_urls = ['https://movie.douban.com/cinema/nowplaying/nanjing/']
    nowplaying = "//*[@id='nowplaying']/div[@class='mod-bd']//*[@class='list-item']/@{}"
    properties = ['data-title', 'data-score', 'data-release', 'data-duration', 'data-region', 'data-director',
                  'data-actors']
 
    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):
        titles = response.xpath(self.nowplaying.format(self.properties[0])).extract()
        scores = response.xpath(self.nowplaying.format(self.properties[1])).extract()
        releases = response.xpath(self.nowplaying.format(self.properties[2])).extract()
        durations = response.xpath(self.nowplaying.format(self.properties[3])).extract()
        regions = response.xpath(self.nowplaying.format(self.properties[4])).extract()
        directors = response.xpath(self.nowplaying.format(self.properties[5])).extract()
        actors = response.xpath(self.nowplaying.format(self.properties[6])).extract()
        for x in range(len(titles)):
            item = DoubanPlayingItem()
            item['title'] = titles[x]
            item['score'] = scores[x]
            item['release'] = releases[x]
            item['duration'] = durations[x]
            item['region'] = regions[x]
            item['director'] = directors[x]
            item['actors'] = actors[x]
            yield item

# 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 DoubanPlayingPipeline:
    def __init__(self):
        self.file = open('result.txt', 'w', encoding='utf-8')
 
    def process_item(self, item, spider):
        self.file.write(
            "电影:{}\t分数:{}\t发行年份:{}\t电影时长:{}\t地区:{}\t电影导演:{}\t电影主演:{}\n".format(
                item['title'],
                item['score'],
                item['release'],
                item['duration'],
                item['region'],
                item['director'],
                item['actors']))
        return item
 
    def close_spider(self, spider):
        self.file.close()

# Scrapy settings for douban_playing 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 = 'douban_playing'
 
SPIDER_MODULES = ['douban_playing.spiders']
NEWSPIDER_MODULE = 'douban_playing.spiders'
 
 
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'douban_playing (+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 = {
   'douban_playing.middlewares.DoubanPlayingSpiderMiddleware': 543,
}
 
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'douban_playing.middlewares.DoubanPlayingDownloaderMiddleware': 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 = {
   'douban_playing.pipelines.DoubanPlayingPipeline': 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'