1、轮换出口IP
用scrapinghub提供的代理,因为是国外的IP,所以访问百度比国内要慢一些,但是提供的代理很稳定,方便配置,且免费,貌似没有使用次数的限制。
在sittings.py中添加:
'''crawlera账号、密码'''
CRAWLERA_ENABLED = True
CRAWLERA_USER = '账号'
CRAWLERA_PASS = '密码'
'''下载中间件设置'''
DOWNLOADER_MIDDLEWARES = {
'scrapy_crawlera.CrawleraMiddleware': 600
}
2、轮换UA
在sittings.py添加:
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)",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
.......
]
'''下载中间件设置'''
DOWNLOADER_MIDDLEWARES = {
'tutorial.middlewares.RandomUserAgent': 1,
}
在middlewares.py添加:
class RandomUserAgent(object):
"""Randomly rotate user agents based on a list of predefined ones"""
def __init__(self, agents):
self.agents = agents
@classmethod
def from_crawler(cls, crawler):
return cls(crawler.settings.getlist('USER_AGENTS'))
def process_request(self, request, spider):
#print "**************************" + random.choice(self.agents)
request.headers.setdefault('User-Agent', random.choice(self.agents))
3、轮换Cookie,并完全模拟浏览器请求头
在sittings.py添加:
def getCookie():
cookie_list = [
'cookie1', #自己从不同浏览器中获取cookie在添加到这
'cookie2',
......
]
cookie = random.choice(cookie_list)
return cookie
'''设置默认request headers'''
DEFAULT_REQUEST_HEADERS = {
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate, sdch',
'Accept-Language':'zh-CN,zh;q=0.8,en;q=0.6',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Host':'www.baidu.com',
'RA-Sid':'7739A016-20140918-030243-3adabf-48f828',
'RA-Ver':'3.0.7',
'Upgrade-Insecure-Requests':'1',
'Cookie':'%s' % getCookie()
}
sittings.py添加其他配置项:
'''下载延时,即下载两个页面的等待时间'''
DOWNLOAD_DELAY = 0.5
'''并发最大值'''
CONCURRENT_REQUESTS = 100
'''对单个网站并发最大值'''
CONCURRENT_REQUESTS_PER_DOMAIN = 100
'''启用AutoThrottle扩展,默认为False'''
AUTOTHROTTLE_ENABLED = False
'''设置下载超时'''
DOWNLOAD_TIMEOUT = 10
'''降低log级别,取消注释则输出抓取详情'''
LOG_LEVEL = 'INFO'
网友评论