Python之scrapy的post请求、日志和代理

def start_requests(self) 

scrapy.FormRequest(url=url, headers=headers, callback=self.parse_item, formdata=data) 		
	url: 要发送的post地址 
	headers：可以定制头信息 
	callback: 回调函数 
	formdata: post所携带的数据，这是一个字典

# 创建项目
scrapy startproject scrapy_post
cd scrapy_post/scrapy_post/spiders
scrapy genspider testpost http://fanyi.baidu.com/

import scrapy

import json

class TestpostSpider(scrapy.Spider):
    name = 'testpost'
    allowed_domains = ['fanyi.baidu.com']

    # post请求 如果没有参数 那么这个请求将没有任何意义
    # 所以start_urls 也没有用了
    # parse方法也没有用了
    # start_urls = ['http://fanyi.baidu.com/']
    #
    # def parse(self, response):
    #     pass

    # def parse(self, response):
    #     pass
    def start_requests(self):
        url = 'https://fanyi.baidu.com/sug'

        data = {
            'kw': 'final'
        }

        yield scrapy.FormRequest(url=url, formdata=data, callback=self.parse_second)

    def parse_second(self, response):
        content = response.text
        obj = json.loads(content, encoding='utf-8')

        print(obj)

DOWNLOADER_MIDDLEWARES = { 
    'postproject.middlewares.Proxy': 543, 
}

def process_request(self, request, spider): 
    request.meta['proxy'] = 'https://113.68.202.10:9999' 
    return None