import re
import requests
from scrapy import Selector
from urllib import parse
from datetime import datetime

from request_spider.models import *

class MovieSpider(object):
domain = "https://www.ysftv.com/"
url = "https://www.ysftv.com/Content/37918.html"
href = "https://www.ysftv.com/Class/1-1.html"
heards = {
“User - Agent”: “Mozilla / 5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 75.0.3770.142 Safari / 537.36”
}

def parse_tail(self,url,image):
    print("开始解析详情页 :" + url)
    movie = Movie()
    id_text = url.split("/")[-1]
    movie_id = int(re.search("(\d*)",id_text).group())
    tail_text = requests.get(url,headers=self.heards).text
    tail_res = Selector(text=tail_text)
    info = tail_res.xpath("//div[@class='content mb clearfix']/div[@class='info']")
    name = info.css("dl > dt.name::text").extract_first('None')
    status = info.xpath("./dl/dd[1]/text()").extract_first('None')
    type = info.xpath("./dl/dd[2]/a/text()").extract_first('None')
    director = info.xpath("./dl/dd[3]/text()").extract_first('None')
    area = info.xpath("./dl/dd[4]/text()").extract_first('None')
    create_year = info.xpath("./dl/dd[5]/text()").extract_first('None')
    actors = info.xpath("./dl/dd[6]/text()").extract_first('None')
    descript = info.css("dl > dt.desd > div.alldes > div.des2::text").extract_first()
    play1 = []
    play1_divs = tail_res.xpath("//div[@id='stab_1_71']")
    for div in play1_divs:
        play1_url = div.xpath(".//a/@href").extract_first()
        if  play1_url:
            play1_url = parse.urljoin(self.domain, play1_url)
        play1.append(play1_url)
    play_channel1 = "&".join( play1)

    play2 = []
    play2_divs = tail_res.xpath("//div[@id='stab_2_71']")
    for div in play2_divs:
        play2_url = div.xpath(".//a/@href").extract_first()
        if play2_url:
            play2_url = parse.urljoin(self.domain, play2_url)
        play2.append(play2_url)
    play_channel2 = "&".join(play2)

    play3 = []
    play3_divs = tail_res.xpath("//div[@id='stab_3_71']")
    for div in play3_divs:
        play3_url = div.xpath(".//a/@href").extract_first()
        if play3_url:
            play3_url = parse.urljoin(self.domain, play3_url)
        play3.append(play3_url)
    play_channel3 = "&".join(play3)

    play4 = []
    play4_divs = tail_res.xpath("//div[@id='stab_4_71']")
    for div in play4_divs:
        play4_url = div.xpath(".//a/@href").extract_first()
        if play4_url:
            play4_url = parse.urljoin(self.domain, play4_url)
        play4.append(play4_url)
    play_channel4 = "&".join(play4)

    movie.Movie_Id = movie_id
    movie.Movie_Image = image
    movie.Name = name
    movie.Status = status
    movie.Type = type
    movie.Director = director
    movie.Area = area
    movie.Creat_Year = create_year
    movie.Actors = actors
    movie.Descript = descript
    movie.Paly_Channel1 = play_channel1
    movie.Paly_Channel2 = play_channel2
    movie.Paly_Channel3 = play_channel3
    movie.Paly_Channel4 = play_channel4

    existed_movie = Movie.select().where(Movie.Movie_Id ==  movie.Movie_Id )
    if existed_movie:
        movie.save()
    else:
        movie.save(force_insert=True)


def parse_topic(self,href):
    print("开始解析主题  :" + href)
    topic_text = requests.get(href,headers=self.heards,verify=False).text
    topic_res = Selector(text=topic_text)
    topic_lis = topic_res.xpath("//div[@class='index-tj mb clearfix']/ul/li")
    for li in topic_lis:
        movie_image = li.xpath("./a[@class='li-hv']/div[@class='img']/img/@data-original").extract_first("None")
        tail_url = li.xpath("./a[@class='li-hv']/@href").extract_first("None")
        tail_url = parse.urljoin(self.domain,tail_url)
        self.parse_tail(tail_url,movie_image)
    next_page =  topic_res.xpath("//div[@class='page mb clearfix']/a[contains(text(),'下一页')]/@href").extract()[0]
    if next_page:
        next_page = parse.urljoin(self.domain,next_page)
        self.parse_topic(next_page)

def get_url(self):
    html_text = requests.get(self.domain,headers=self.heards,verify=False).text
    res = Selector(text=html_text)
    all_lis = res.css(".nav-pc > li")
    for li in all_lis[1:-1]:
        href = li.xpath("./b[@class='navb']/a/@href").extract_first("None")
        href = parse.urljoin(self.domain,href)
        self.parse_topic(href)

if name == “main”:
spider = MovieSpider()
spider.get_url()

models的代码：

`import MySQLdb
from peewee import *

db = MySQLDatabase(“movie”, host=“127.0.0.1”, port=3306, user=“root”, password="")

class BaseModel(Model):
class Meta:
database = db

class Movie(BaseModel):
Movie_Id = IntegerField(primary_key=True)
Movie_Image = CharField(null=True)
Name = TextField(null=True)
Status = CharField(max_length=20,null=True)
Type = CharField(max_length=30,null=True)
Director = TextField(null=True)
Area = CharField(max_length=20,null=True)
Creat_Year = CharField(max_length=10,null=True)
Actors = TextField(null=True)
Descript = TextField(null=True)
Paly_Channel1 = TextField(null=True)
Paly_Channel2 = TextField(null=True)
Paly_Channel3 = TextField(null=True)
Paly_Channel4 = TextField(null=True)

if name == “main”:
db.create_tables([Movie])``

Bobby老师：
这是我最近练习爬取静态网页写的的一个·爬虫，但运行多次都出现如下错误：
requests.exceptions.SSLError: HTTPSConnectionPool(host=‘www.ysftv.com’, port=443): Max retries exceeded with url: /Content/65596.html (Caused by SSLError(SSLError(“bad handshake: SysCallError(10054, ‘WSAECONNRESET’)”)))

百度了一下也没找到问题的解释，用了网上的解决办法将requests的verify改为等于false（ tail_text = requests.get(url,headers=self.heards,verify=False).text）但还是出现上述问题，学生想请老师指点一下：
1、这到底是个什么Error？
2、这个问题是怎么引起的？
3、这个问题该如何解决？