方法一:
直接在spider文件下设置代理,通过传参的方式设置在Request中
import scrapy class MimvpSpider(scrapy.spiders.Spider):
name = "mimvp"
allowed_domains = ["mimvp.com"]
start_urls = [
"http://proxy.mimvp.com/exist.php",
"https://proxy.mimvp.com/exist.php",
] ## 代理设置方式1:直接在代理里设置
def start_requests(self):
urls = [
"http://proxy.mimvp.com/exist.php",
"https://proxy.mimvp.com/exist.php",
]
for url in urls:
meta_proxy = ""
if url.startswith("http://"):
meta_proxy = "http://180.96.27.12:88" # http代理
elif url.startswith("https://"):
meta_proxy = "http://109.108.87.136:53281" # https代理 yield scrapy.Request(url=url, callback=self.parse, meta={'proxy': meta_proxy}) def parse(self, response):
mimvp_url = response.url # 爬取时请求的url
body = response.body # 返回网页内容 print("mimvp_url : " + str(mimvp_url))
print("body : " + str(body))
方法二:
利用中间件middlewares.py+settings配置
middlewares.py
## 代理设置方式2: 通过 middlewares.py + settings.py 配置文件设置
## mimvp custom by yourself
class ProxyMiddleware(object):
def process_request(self,request,spider): if request.url.startswith("http://"):
request.meta['proxy']="http://180.96.27.12:88" # http代理
elif request.url.startswith("https://"):
request.meta['proxy']="http://109.108.87.136:53281" # https代理 # # proxy authentication
# proxy_user_pass = "USERNAME:PASSWORD"
# encoded_user_pass = base64.encodestring(proxy_user_pass)
# request.headers['Proxy-Authorization'] = 'Basic ' + encoded_user_pass
settings.py
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# 优先级越小越先执行
DOWNLOADER_MIDDLEWARES = {
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 110,
'mimvp_proxy_python_scrapy.middlewares.ProxyMiddleware': 100,
}