Add files via upload

20200521_duban-movie-analysis/movietest2/items.py

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class Movietest2Item(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+
+    # 电影 id
+    movie_id=scrapy.Field()
+
+    # 电影名称
+    movie_title=scrapy.Field()
+
+    # tag
+    movie_tag=scrapy.Field()
+
+    # 电影评分
+    movie_rate=scrapy.Field()
+
+    # 导演
+    movie_director=scrapy.Field()
+
+    # 类型
+    movie_types=scrapy.Field()
+
+    # 制片国家
+    movie_country=scrapy.Field()
+
+    # 片长
+    how_long=scrapy.Field()
+
+    # 用户名
+    user_name=scrapy.Field()
+
+    # 评论内容
+    content=scrapy.Field()
+
+    # 发布时间
+    release_time=scrapy.Field()
+
+    # 用户链接
+    user_link=scrapy.Field()
+
+    # 用户id
+    user_id=scrapy.Field()
+
+
+

20200521_duban-movie-analysis/movietest2/middlewares.py

@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+
+# 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
+
+class Movietest2SpiderMiddleware(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 Request, 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 Movietest2DownloaderMiddleware(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)
+
+
+

20200521_duban-movie-analysis/movietest2/pipelines.py

@@ -0,0 +1,96 @@
+# -*- coding: utf-8 -*-
+
+# 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
+
+import pymongo
+import json
+
+class Movietest2Pipeline(object):
+    collection_name="test"
+
+    def __init__(self,mongo_uri,mongo_db):
+
+        self.mongo_uri=mongo_uri
+        self.mongo_db=mongo_db
+
+    @classmethod
+    def from_crawler(cls,crawler):
+
+        return cls(
+            mongo_uri=crawler.settings.get('MONGO_URI'),
+            mongo_db=crawler.settings.get('MONGO_DATABASE','Movie')
+        )
+
+
+    def open_spider(self,spider):
+
+        self.client=pymongo.MongoClient(self.mongo_uri)
+        self.db=self.client[self.mongo_db]
+
+
+    def close_spider(self,spider):
+
+        self.client.close()
+
+
+    def process_item(self, item, spider):
+
+        self.db[self.collection_name].insert(dict(item))
+        return item
+
+
+class Movietest2FilePipeline(object):
+
+    def open_spider(self,spider):
+        #self.file=open("review_final.json","a",encoding="utf-8")
+        self.file = open("test.json", "a", encoding="utf-8")
+
+    def process_item(self,item,spider):
+
+        line = json.dumps(dict(item), ensure_ascii=False) + "\n"
+
+        self.file.write(line)
+
+        return item
+
+    def close_spider(self,spider):
+
+        self.file.close()
+
+
+"""
+class Movietest2CsvPipeline(object):
+
+    def __init__(self):
+
+        self.f=open('review.csv','a',encoding="utf-8")
+
+        self.exportre=CsvItemExporter(
+            self.f,
+            include_headers_line=True,
+            encoding='utf-8'
+        )
+
+    def open_spider(self,spider):
+
+        pass
+
+    def process_item(self,item,spider):
+
+        self.exportre.export_item(item)
+
+        return item
+
+    def close_spider(self,spider):
+
+        self.f.close()
+
+
+"""
+
+
+
+

20200521_duban-movie-analysis/movietest2/settings.py

@@ -0,0 +1,96 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for movietest2 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 = 'movietest2'
+
+SPIDER_MODULES = ['movietest2.spiders']
+NEWSPIDER_MODULE = 'movietest2.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'movietest2 (+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 = 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 = {
+    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36",
+    'Cookie':'bid=9JMhtyhKwCI; gr_user_id=dfc4a657-74ee-4905-90d1-afdcc278240c; _vwo_uuid_v2=D817A52A7B1A438F346CA5145718FC70D|11c7965ceae6dae41bda579ad8cc07ad; _ga=GA1.2.704102812.1568950460; ll="118254"; __yadk_uid=KJcw8kSGqgo0bzV13fiv89IQHblmzQnp; trc_cookie_storage=taboola%2520global%253Auser-id%3D6db6843a-c51d-4dd1-929b-c64a9d65c502-tuct47b1992; __gads=ID=3f19cf254ba723db:T=1572747084:S=ALNI_Mao2HHyRrl7R9fbqqQ-8L9y6ur9jw; douban-fav-remind=1; push_noty_num=0; push_doumail_num=0; viewed="34839848_26337727_30136932_26342364_1234142_26416562_2061116_26827295"; __utmz=30149280.1588833276.3.2.utmcsr=douban.com|utmccn=(referral)|utmcmd=referral|utmcct=/; dbcl2="175718936:oI/7dGsQRCM"; __utmv=30149280.17571; ck=eH3o; __utmc=30149280; __utmc=223695111; ct=y; __utma=30149280.704102812.1568950460.1589080211.1589087550.8; __utmb=30149280.2.10.1589087550; _pk_ref.100001.4cf6=%5B%22%22%2C%22%22%2C1589087552%2C%22https%3A%2F%2Fwww.douban.com%2F%22%5D; _pk_ses.100001.4cf6=*; __utma=223695111.704102812.1568950460.1589080211.1589087552.41; __utmb=223695111.0.10.1589087552; __utmz=223695111.1589087552.41.22.utmcsr=douban.com|utmccn=(referral)|utmcmd=referral|utmcct=/; _pk_id.100001.4cf6=3297dbc060884462.1570180143.41.1589088238.1589080924.'
+}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'movietest2.middlewares.Movietest2SpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'movietest2.middlewares.Movietest2DownloaderMiddleware': 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 = {
+    'movietest2.pipelines.Movietest2Pipeline': 300,
+    'movietest2.pipelines.Movietest2FilePipeline':400
+}
+
+
+MONGO_URI='localhost:27017'
+MONGO_DATABASE='Movie'
+
+
+# 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'

20200521_duban-movie-analysis/movietest2/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.