变更

python爬虫/python爬虫练习/douban/douban/items.py

@@ -0,0 +1,15 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class DoubanItem(scrapy.Item):
+    # define the fields for your item here like:
+    name = scrapy.Field()
+    info = scrapy.Field()
+    score = scrapy.Field()
+    desc = scrapy.Field()
+

python爬虫/python爬虫练习/douban/douban/middlewares.py

@@ -0,0 +1,134 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+import base64
+
+from scrapy import signals
+import random
+from douban.settings import USER_AGENT_LIST
+from douban.settings import PROXY_LIST
+from .myextend import pro
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class RandomUserAgent(object):
+    def process_request(self, request, spider):
+        ua = random.choice(USER_AGENT_LIST)
+        request.headers["'User-Agent'"] = ua
+        # print(request.headers)
+
+
+class RandomProxy(object):
+    def process_request(self, request, spider):
+        proxy = random.choice(pro.proxy_list)
+        print(proxy)
+
+        username = "azonhgez"
+        password = "7lvu0dnm"
+        request.meta['proxy'] = "http://%(user)s:%(pwd)s@%(proxy)s/" % {"user": username, "pwd": password, "proxy": proxy}
+
+        # if "user_passwd" in proxy:
+        # # # 对账号密码进行base64编码
+        #     # b64_up=base64.b64encode(proxy["user_passwd"].encode())
+        #     # #设置认证
+        #     # request.headers["Proxy-Authorization"] = "basic "+b64_up.decode()
+        #     # #设置代理
+        #     # request.meta['proxy']=proxy['ip_port']
+        # else:
+        #     request.meta['proxy']=proxy['ip_port']
+
+class DoubanSpiderMiddleware:
+    # 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 DoubanDownloaderMiddleware:
+    # 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)

python爬虫/python爬虫练习/douban/douban/myextend.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python
+# -- coding: utf-8 --
+import time
+import threading
+
+import requests
+from scrapy import signals
+
+# 提取代理IP的api
+api_url = 'https://kps.kdlapi.com/api/getkps/?secret_id=ou5nlcm9klazz4rhi8ht&signature=1ffl6otrop2on40eyeuxe46c0cavc9k6&num=10&pt=1&format=json&sep=1'
+foo = True
+
+class Proxy:
+
+    def __init__(self, ):
+        self._proxy_list = requests.get(api_url).json().get('data').get('proxy_list')
+
+    @property
+    def proxy_list(self):
+        return self._proxy_list
+
+    @proxy_list.setter
+    def proxy_list(self, list):
+        self._proxy_list = list
+
+
+pro = Proxy()
+print(pro.proxy_list)
+
+
+class MyExtend:
+
+    def __init__(self, crawler):
+        self.crawler = crawler
+        # 将自定义方法绑定到scrapy信号上,使程序与spider引擎同步启动与关闭
+        # scrapy信号文档: https://www.osgeo.cn/scrapy/topics/signals.html
+        # scrapy自定义拓展文档: https://www.osgeo.cn/scrapy/topics/extensions.html
+        crawler.signals.connect(self.start, signals.engine_started)
+        crawler.signals.connect(self.close, signals.spider_closed)
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        return cls(crawler)
+
+    def start(self):
+        t = threading.Thread(target=self.extract_proxy)
+        t.start()
+
+    def extract_proxy(self):
+        while foo:
+            pro.proxy_list = requests.get(api_url).json().get('data').get('proxy_list')
+            #设置每15秒提取一次ip
+            time.sleep(15)
+
+    def close(self):
+        global foo
+        foo = False

python爬虫/python爬虫练习/douban/douban/pipelines.py

@@ -0,0 +1,13 @@
+# 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 DoubanPipeline:
+    def process_item(self, item, spider):
+        return item

python爬虫/python爬虫练习/douban/douban/settings.py

@@ -0,0 +1,119 @@
+# Scrapy settings for douban 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"
+
+SPIDER_MODULES = ["douban.spiders"]
+NEWSPIDER_MODULE = "douban.spiders"
+LOG_LEVEL="WARNING"
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+USER_AGENT = """
+Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36 Edg/127.0.0.0"""
+
+USER_AGENT_LIST = ["Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36",
+                   "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.1 Safari/537.36",
+                   "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 6.4; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.93 Safari/537.36",
+                   "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.124 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 4.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36",
+                   "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36",
+                   "Mozilla/5.0 (X11; OpenBSD i386) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.125 Safari/537.36"
+                   ]
+
+PROXY_LIST=[
+    {"ip_port":"119.96.179.83:16819","user_passwd":"7lvu0dnm"},
+    # {"ip_port":"185.195.107.254:23445"}
+
+]
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# 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",
+#}
+
+# Enable or disable spider middlewares
+# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    "douban.middlewares.DoubanSpiderMiddleware": 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+   # "douban.middlewares.DoubanDownloaderMiddleware": 543,
+   "douban.middlewares.RandomUserAgent": 542,
+   "douban.middlewares.RandomProxy": 541,
+}
+
+# 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.pipelines.DoubanPipeline": 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"

python爬虫/python爬虫练习/douban/douban/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.

python爬虫/python爬虫练习/douban/douban/spiders/db250.py

@@ -0,0 +1,28 @@
+import scrapy
+from douban.items import DoubanItem
+
+class Db250Spider(scrapy.Spider):
+    name = "db250"
+    allowed_domains = ["douban.com"]
+    start_urls = ["https://movie.douban.com/top250"]
+
+    def parse(self, response):
+        el_list = response.xpath("//div[@class='info']")
+
+
+        for el in el_list:
+            item = DoubanItem()
+            item['name']=el.xpath("./div[1]/a/span[1]/text()").extract_first()
+            item['info']=el.xpath("./div[2]/p[1]/text()").extract_first()
+            item['score']=el.xpath("./div[2]/div/span[2]/text()").extract_first()
+            item['desc']=el.xpath("./p[2]/span/text()").extract_first()
+            # print(item)
+            yield item
+
+
+        url = response.xpath("//span[@class='next']/a/@href").extract_first()
+        if url != None:
+            url = response.urljoin(url)
+            yield scrapy.Request(
+                url=url
+            )

python爬虫/python爬虫练习/douban/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = douban.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = douban