python scrapy 模拟登录(手动输入验证码)

用户5760343

发布于 2022-01-10 08:15:36

1.2K0

发布于 2022-01-10 08:15:36

文章被收录于专栏：sktj

scrapy startproject yelloweb vi item.py import scrapy

class YellowebItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() title = scrapy.Field() # 视频标题 link = scrapy.Field() # 视频链接 img = scrapy.Field() # 封面图片链接

vi spiders/yellowbSpider.py import scrapy

class yellowebSpider(scrapy.Spider): name = "webdata" # 爬虫的识别名，它必须是唯一的 allowed_domains = ["91.91p17.space"] def start_requests(self): return [Request("http://91.91p17.space/login.php", callback=self.login, meta={"cookiejar":1})]

 headers={
    "GET /index.php HTTP/1.1"
    "Host": "91.91p17.space",
    "Connection": "keep-alive",
    "Cache-Control": "max-age=0",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36",
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Referer": "http://91.91p17.space/login.php",
    "Accept-Encoding": "gzip, deflate",
    "Accept-Language": "zh-CN,zh;q=0.8"
}
def login(self, response):
    print("准备开始模拟登录！")
    captcha_image = response.xpath('//*[@id="safecode"]/@src').extract()
    print(urljoin("http://91.91p17.space", captcha_image[0]))
    if ( len(captcha_image) > 0):
        # 拟定文件名与保存路径
        localpath = "D:\SoftWare\Soft\WorkSpace\Python\scrapy\code\captcha.png"

        opener=urllib.request.build_opener()
        opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
        urllib.request.install_opener(opener)
        urllib.request.urlretrieve(urljoin("http://91.91p17.space", captcha_image[0]), localpath)

        print("此次登录有验证码，请查看本地captcha图片输入验证码:")
        captcha_value = input()
        data = {
            "username": "这里填用户名",
            "password": "这里填密码",
            "fingerprint": "1838373130",
            "fingerprint2": "1a694ef42547498d2142328d89e38c22",
            "captcha_input": captcha_value,
            "action_login": "Log In",
            "x": "54",
            "y": "21"
        }
    else:
        print("登录时没有验证码！代码又写错了！")
    # print(data)
    print("验证码对了！！！！")
    return [FormRequest.from_response(response,
                                      # 设置cookie信息
                                      meta={'cookiejar': response.meta['cookiejar']},
                                      # 设置headers信息模拟浏览器
                                      headers=self.headers,
                                      formdata=data,
                                      callback=self.next
                                      )]

def next(self, response): href = response.xpath('//*[@id="tab-featured"]/div/a/@href').extract() url=urljoin("http://91.91p17.space", href[0]) # print("\n\n\n\n\n\n"+url+"\n\n\n\n\n\n") yield scrapy.http.Request(url, meta={'cookiejar': response.meta['cookiejar']}, # 设置headers信息模拟浏览器 headers=response.headers, callback=self.parse) def parse(self, response): sel = Selector(response) print("进入更多精彩视频了")

    web_list = sel.css('.listchannel')
    for web in web_list:


        item = YellowebItem()
        try:
            item['link'] = web.xpath('a/@href').extract()[0]
            url = response.urljoin(item['link'])
            yield scrapy.Request(url, meta={'cookiejar': response.meta['cookiejar']}, callback=self.parse_content, dont_filter=True)
        except:
            print("完蛋了。。。。")
        # 跳转下一个页面

        href = response.xpath('//*[@id="paging"]/div/form/a[6]/@href').extract()
        nextPage = urljoin("http://91.91p17.space/video.php", href[0])
        print(nextPage)
        if nextPage:
            yield scrapy.http.Request(nextPage, meta={'cookiejar': response.meta['cookiejar']},
                                      # 设置headers信息模拟浏览器
                                      headers=response.headers, callback=self.parse)


def parse_content(self, response):
        try:
            name = response.xpath('//*[@id="head"]/h3/a[1]/text()').extract()[0]

            item = YellowebItem()
            item['link'] = response.xpath('///*[@id="vid"]//@src').extract()[0]
            item['title'] = response.xpath('//*[@id="viewvideo-title"]/text()').extract()[0].strip()
            item['img'] = response.xpath('//*[@id="vid"]/@poster').extract()[0]
            yield item
        except:
            print("完蛋了。。。爬不下来了。。。")

vi pipeline.py import pymysql as db

class YellowebPipeline(object): def init(self): self.con = db.connect(user="root", passwd="root", host="localhost", db="python", charset="utf8") self.cur = self.con.cursor() self.cur.execute('drop table 91pron_content') self.cur.execute("create table 91pron_content(id int auto_increment primary key, title varchar(200), img varchar(244), link varchar(244))")

def process_item(self, item, spider):
    self.cur.execute("insert into 91pron_content(id,title,img,link) values(NULL,%s,%s,%s)", (item['title'], item['img'], item['link']))
    self.con.commit()
    return item

vi settings.py DOWNLOADER_MIDDLEWARES = { 'yelloweb.middlewares.MyCustomDownloaderMiddleware': None, }

scrapy crawl yellowebSpider

本文参与腾讯云自媒体同步曝光计划，分享自作者个人站点/博客。

原始发表：2019.05.14 ，如有侵权请联系 cloudcommunity@tencent.com 删除

scrapy