Class: HttpCrawler::HTTP
- Defined in:
- lib/http_crawler/http.rb
Constant Summary collapse
- @@proxy_list =
[]
Instance Attribute Summary collapse
-
#auto_proxy ⇒ Object
自动获取代理,true 表示自动获取代理 、false 表示不自动获取.
-
#max_error_num ⇒ Object
请求错误后的重复最大请求次数.
-
#proxy_api ⇒ Object
代理API的别名 主要关联 HttpCrawler::Proxy中维护的代理API.
-
#proxy_key ⇒ Object
调用自己的代理池所需要的主键 key.
Instance Method Summary collapse
-
#get_fetch(uri_or_path, initheader = nil, dest = nil, limit = 10, &block) ⇒ Object
重定向请求.
-
#get_proxy ⇒ Object
通过调用 api 获取代理或者通过自定义设置代理.
- #http_error_sleep ⇒ Object
-
#initialize(address, port = nil) ⇒ HTTP
constructor
A new instance of HTTP.
-
#post_fetch(uri_or_path, data, initheader = nil, dest = nil, &block) ⇒ Object
重定向请求.
-
#proxy(p = {}) ⇒ Object
为 @http 重设代理.
-
#request(req, body = nil, &block) ⇒ Object
重写 发送请求的方法.
- #server_error_sleep ⇒ Object
- #update_proxy(p = {}) ⇒ Object
-
#update_proxy?(p = {}) ⇒ Boolean
如果自动更新代理 则更新代理返回 true,否则返回false.
Constructor Details
#initialize(address, port = nil) ⇒ HTTP
Returns a new instance of HTTP.
16 17 18 19 20 21 |
# File 'lib/http_crawler/http.rb', line 16 def initialize(address, port = nil) super(address, port) @max_error_num = 2 @error_num = 0 @proxy_key = "default" end |
Instance Attribute Details
#auto_proxy ⇒ Object
自动获取代理,true 表示自动获取代理 、false 表示不自动获取
8 9 10 |
# File 'lib/http_crawler/http.rb', line 8 def auto_proxy @auto_proxy end |
#max_error_num ⇒ Object
请求错误后的重复最大请求次数
14 15 16 |
# File 'lib/http_crawler/http.rb', line 14 def max_error_num @max_error_num end |
#proxy_api ⇒ Object
代理API的别名 主要关联 HttpCrawler::Proxy中维护的代理API
10 11 12 |
# File 'lib/http_crawler/http.rb', line 10 def proxy_api @proxy_api end |
#proxy_key ⇒ Object
调用自己的代理池所需要的主键 key
12 13 14 |
# File 'lib/http_crawler/http.rb', line 12 def proxy_key @proxy_key end |
Instance Method Details
#get_fetch(uri_or_path, initheader = nil, dest = nil, limit = 10, &block) ⇒ Object
重定向请求
111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
# File 'lib/http_crawler/http.rb', line 111 def get_fetch(uri_or_path, initheader = nil, dest = nil, limit = 10, &block) # You should choose a better exception. raise ArgumentError, 'too many HTTP repeated' if limit == 0 # 更新uri_or_path uri_or_path = URI.encode(uri_or_path) if String === uri_or_path && CharDet.detect(uri_or_path)["encoding"] != "ascii" response = get(uri_or_path, initheader, dest, &block) case response when Net::HTTPSuccess then response when Net::HTTPRedirection then location = response['location'] Rails.logger.warn "redirected to #{location}" # 传入 location 进行跳转 get_fetch(location, initheader, dest, limit - 1, &block) when Net::HTTPServerError then Rails.logger.warn "Net::HTTPServerError 5XX to #{address}" server_error_sleep # 重新请求 get_fetch(uri_or_path, initheader, dest, &block) when Net::HTTPProxyAuthenticationRequired then Rails.logger.warn "Net::HTTPProxyAuthenticationRequired 407 to proxy:[#{@proxy_address}:#{@proxy_port}] =>#{address}" if update_proxy? server_error_sleep # 重新请求 get_fetch(uri_or_path, initheader, dest, &block) else response.error! end else server_error_sleep response.error! end end |
#get_proxy ⇒ Object
通过调用 api 获取代理或者通过自定义设置代理
58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
# File 'lib/http_crawler/http.rb', line 58 def get_proxy while @@proxy_list.blank? Rails.logger.debug("@@proxy_list 为空进行更新") proxy_client = HttpCrawler::Proxy.for(proxy_api) proxy_r = proxy_client.get_proxy(key: proxy_key) @@proxy_list << proxy_r.parsing Rails.logger.debug("@@proxy_list => #{@@proxy_list}") sleep(1) end p = @@proxy_list.delete_at(0) Rails.logger.debug("当前IP => #{@proxy_address}:#{@proxy_port},获取最新代理 => #{p}") unless p && p["p_addr"] && p["p_port"] Rails.logger.warn "无最新代理等待5秒后重新获取" sleep(5) p = get_proxy end if (@proxy_address == p["p_addr"] && @proxy_port == p["p_port"]) Rails.logger.warn "无最新代理等待5秒后重新获取" sleep(5) p = get_proxy end p end |
#http_error_sleep ⇒ Object
23 24 25 |
# File 'lib/http_crawler/http.rb', line 23 def http_error_sleep sleep(0.5) end |
#post_fetch(uri_or_path, data, initheader = nil, dest = nil, &block) ⇒ Object
重定向请求
147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 |
# File 'lib/http_crawler/http.rb', line 147 def post_fetch(uri_or_path, data, initheader = nil, dest = nil, &block) # 更新uri_or_path 如果 uri_or_path 是 String类型 同时 又不是 ascii编码格式就进行转码 uri_or_path = URI.encode(uri_or_path) if String === uri_or_path && CharDet.detect(uri_or_path)["encoding"] != "ascii" # Rails.logger.debug "post_fetch => #{uri_or_path}" response = post(uri_or_path, data, initheader, dest, &block) case response when Net::HTTPSuccess then response when Net::HTTPRedirection then location = response['location'] Rails.logger.warn "redirected to #{location}" # 传入 location 进行跳转 get_fetch(location, initheader, dest, 9, &block) when Net::HTTPServerError then Rails.logger.warn "Net::HTTPServerError 5XX to #{address}" server_error_sleep # 重新请求 post_fetch(uri_or_path, initheader, dest, &block) when Net::HTTPProxyAuthenticationRequired then Rails.logger.warn "Net::HTTPProxyAuthenticationRequired 407 to proxy:[#{http.proxy_address}:#{http.proxy_port}] =>#{address}" if update_proxy? server_error_sleep # 重新请求 post_fetch(uri_or_path, initheader, dest, &block) else response.error! end else server_error_sleep response.error! end end |
#proxy(p = {}) ⇒ Object
为 @http 重设代理
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
# File 'lib/http_crawler/http.rb', line 37 def proxy(p = {}) raise '代理设置 p_addr 不能为空' unless p["p_addr"] raise '代理设置 p_port 不能为空' unless p["p_port"] p["p_user"] ||= nil p["p_pass"] ||= nil Rails.logger.info("切换代理至 => #{p}") # 设为 false 否则不会启用代理 @proxy_from_env = false # 初始化代理数据 @proxy_address = p["p_addr"] @proxy_port = p["p_port"] @proxy_user = p["p_user"] @proxy_pass = p["p_pass"] end |
#request(req, body = nil, &block) ⇒ Object
重写 发送请求的方法
185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 |
# File 'lib/http_crawler/http.rb', line 185 def request(req, body = nil, &block) begin Rails.logger.debug("#{req.class} => #{use_ssl? ? "https://" : "http://" }#{address}:#{port}#{req.path}") if started? Rails.logger.debug("body => #{body}") if started? && body super(req, body, &block) rescue => error if started? # started? 是为了判断是否结束http请求,如果不添加则会处理2次异常 raise error else # 最大错误尝试次数 if @error_num < @max_error_num @error_num += 1 http_error_sleep retry # 这将把控制移到 begin 的开头 else # 超过最大错误限制 判断错误类型 case error when Net::HTTPFatalError raise error when EOFError Rails.logger.warn "EOFError!" if update_proxy? proxy(get_proxy) http_error_sleep retry # 这将把控制移到 begin 的开头 else raise error end when Timeout::Error Rails.logger.warn "请求超时!" if update_proxy? @error_num = 0 http_error_sleep retry # 这将把控制移到 begin 的开头 else raise error end else raise error end end end end # begin end |
#server_error_sleep ⇒ Object
27 28 29 |
# File 'lib/http_crawler/http.rb', line 27 def server_error_sleep sleep(3) end |
#update_proxy(p = {}) ⇒ Object
87 88 89 90 91 92 93 |
# File 'lib/http_crawler/http.rb', line 87 def update_proxy(p = {}) if p.blank? proxy(get_proxy) else proxy(p) end end |
#update_proxy?(p = {}) ⇒ Boolean
如果自动更新代理 则更新代理返回 true,否则返回false
96 97 98 99 100 101 102 103 104 105 106 107 |
# File 'lib/http_crawler/http.rb', line 96 def update_proxy?(p = {}) if auto_proxy if p.blank? proxy(get_proxy) else proxy(p) end return true else return false end end |