class LagouSpider(scrapy.Spider):
    name = 'lagou'
    allowed_domains = ['www.lagou.com']
    start_urls = []
    headers = {
        "Accept": "application/json, text/javascript, */*; q=0.01",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        # "Content-Length": "25",
        "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
        "Host": "www.lagou.com",
        "Origin": "https://www.lagou.com",
        "Referer": "https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36",
        "X-Anit-Forge-Code": "0",
        "X-Anit-Forge-Token": "None",
        "X-Requested-With": "XMLHttpRequest"
    }
    
    def start_requests(self):
    api = 'https://www.lagou.com/jobs/positionAjax.json?px=new&city=%E6%B7%B1%E5%9C%B3&needAddtionalResult=false'
    post_data = {
        "first": "true",
        "pn": "1",
        "kd": "python"
    }
    yield FormRequest(url=api, formdata=post_data, headers=self.headers, callback=self.parse)

老师这里的header中不带content-length可以正常爬 状态码200 ，但是带上后就成302了

api = 'https://www.lagou.com/jobs/positionAjax.json?px=new&city=%E6%B7%B1%E5%9C%B3&needAddtionalResult=false'
headers = {
    "Accept": "application/json, text/javascript, */*; q=0.01",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "Connection": "keep-alive",
    "Content-Length": "25",
    "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
    "Host": "www.lagou.com",
    "Origin": "https://www.lagou.com",
    "Referer": "https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36",
    "X-Anit-Forge-Code": "0",
    "X-Anit-Forge-Token": "None",
    "X-Requested-With": "XMLHttpRequest"
}

data = {
    "first": " true",
    "pn": " 1",
    "kd": " python"
}

r = requests.post(api, headers=headers, data=data)
print(r.status_code, r.history, r.encoding, r.text, sep='\n')

而使用requests模块来爬的话，不管header中是否有content-length都可以正常爬取 状态码都为200

这是为什么呢。。百思不得其解。。