scrapy爬取豆瓣，携程代码，动态加载页面等

# -*- coding: utf-8 -*- # Scrapy settings for cnblogs project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # http://doc.scrapy.org/en/latest/topics/settings.html # http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html # http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html BOT_NAME = 'cnblogs' SPIDER_MODULES = ['cnblogs.spiders'] NEWSPIDER_MODULE = 'cnblogs.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'cnblogs (+http://www.yourdomain.com)' # Configure maximum concurrent requests performed by Scrapy (default: 16) #CONCURRENT_REQUESTS=32 # Configure a delay for requests for the same website (default: 0) # See http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'cnblogs.middlewares.MyCustomSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html DOWNLOADER_MIDDLEWARES = { # 'cnblogs.middlewares.MyCustomDownloaderMiddleware': 543, 'cnblogs.middlewares.RandomUserAgent': 1, #随机user agent #'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': 110, #此API已经弃用 #'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 110, #代理需要用到 #'cnblogs.middlewares.ProxyMiddleware': 100, #代理需要用到 #'scrapy_crawlera.CrawleraMiddleware': 600, #crawlera代理用到 } # Enable or disable extensions # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.telnet.TelnetConsole': None, #} # Configure item pipelines # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { 'cnblogs.pipelines.JsonWithEncodingPipeline': 300, #'cnblogs.pipelines.MySQLStorePipeline': 301, #'cnblogs.pipelines.MongoStorePipeline': 302, } # Enable and configure the AutoThrottle extension (disabled by default) # See http://doc.scrapy.org/en/latest/topics/autothrottle.html # NOTE: AutoThrottle will honour the standard settings for concurrency and delay #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 # Enable showing throttling stats for every response received: #AUTOTHROTTLE_DEBUG=False # Enable and configure HTTP caching (disabled by default) # See http://scrapy.readthedocs.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' LOG_LEVEL = 'INFO' # start MySQL database configure setting MYSQL_HOST = '101.200.36.72' MYSQL_DBNAME = 'cnblogsdb' MYSQL_USER = 'sxydb' MYSQL_PASSWD = 'sxydb' # end of MySQL database configure setting USER_AGENTS = [ "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)", "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)", "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)", "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)", "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)", "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)", "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1", "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0", "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20", "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52", ] PROXIES = [ {'ip_port': '111.11.228.75:80', 'user_pass': ''}, {'ip_port': '120.198.243.22:80', 'user_pass': ''}, {'ip_port': '111.8.60.9:8123', 'user_pass': ''}, {'ip_port': '101.71.27.120:80', 'user_pass': ''}, {'ip_port': '122.96.59.104:80', 'user_pass': ''}, {'ip_port': '122.224.249.122:8088', 'user_pass': ''}, ] #CRAWLERA_ENABLED = True #CRAWLERA_USER = '<API key>' #CRAWLERA_PASS = '你crawlera账号的密码' #MONGODB_HOST = 'localhost' # Change in prod #MONGODB_PORT = 27017 # Change in prod #MONGODB_DATABASE = "cnblog" # Change in prod #MONGODB_COLLECTION = "blogs_info" #MONGODB_USERNAME = "" # Change in prod #MONGODB_PASSWORD = "" # Change in prod