基于ScrapyPython岗位信息爬取与Socket通信实现.pdfVIP

#coding=utf-8

importsocket

importre

server_name=

#՗ऒݷ՗ഘ౮IP

list_info=

socket.getaddrinfo(hostserv

er_name,

port80,

familysocket.AF_INET,

typesocket.SOCK_STREAM,

protosocket.IPPROTO_TCP,

flagssocket.AI_ALL)

for_,_,_,_,addressinlist_info:

print(IP:%s,PORT:%d%address)

#ୌsocket

client_socket=

socket.socket(socket.AF_INET

,socket.SOCK_STREAM,

socket.IPPROTO_TCP)

#ֵ◌አ๐՗IP҅ᬳള๐՗

print(list_info[0][-1])

client_socket.connect(list_info[0][-1])

#՗᭜Request१ҁHTTPܐᦓ҂request_string

=

request_string+=GET/HTTP/1.1\r\n

request_string+=Host:%s:80\r\n%server_name

request_string+=Accept:

text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\r\n

request_string+=Upgrade-Insecure-Requests:1\r\n

request_string+=:

_xsrf=2|fab4a780|f1b7a8abb150de48e0effe|1548039281\r\n

Ӟ̵՗HTTPܐᦓԧᥴᶭᶎӥᬦᑕҔ

ֵ◌አ插座ᖫᑕᆻݐ

ᬩᤈӥᶎᑕଧ֛◌տӥ҅ᛔ૩◌插座ᆻݐ҅ᵱᥝ◌॒ቘय़ᰁጱᗑᕶᕡ◌◌ٟ҅

॒ቘ301ଫᎱ

॒ቘ

HTTPS᭗מܐᦓᕡ◌...

_

#编码=utf‑8导入套接字导入服务器

名称=

#՗ऒݷ՗ഘ౮IP

_

列表信息=socket.getaddrinfo(主机服务器

__

名称，端口80，系列socket.AFINET，类型

_

socket.SOCKSTREAM，原始=

__

socket.IPPROTOTCP，标志socket.AI

_____

ALL)对于、、、，列表中的地址信息：

print(IP:%s,PORT:%d%地址)

#ୌ套接字

_

客户端套接字

socket.socket(s