写了一个爬虫抓取 并判断的问题求助

hahawangzi

class iswitch():

def __init__(self):
    self.url='http://www.paopaoche.net/psp/114_PSP_'
    self.headers={
     'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
     #'Referer':"https://www.manhuadb.com/author/370"

       }
    self.zidian={}
def shuru(self):

    gname=input("input you wan search game name:")#这里定义了gname
def main(self):
    for p in range(1,10):

        r =requests.get(self.url+str(p)+'.html',self.headers)
        r.encoding="gbk"
        soup = BeautifulSoup(r.text,'lxml')
        soup2=soup.find('p',class_="list clearfix")
        #print(soup2)
        for j in soup2.find_all('u'):
            #print(j.getText())
            self.zidian["name"]=j.getText()
            if self.shuru().gname in self.zidian["name"]:#想在这里将gname 放到循环的字典里判断是否出现我搜索的游戏名字，然后搜索到了 打印出来，但是这里 报错，说gname是空值 应该怎么定义？
                print(self.zidian["name"])

if name == "main":
x = iswitch()
x.main()

superain

弱弱的问一句 你执行以后有显示input you wan search game name这个让你输入吗

rsnodame

这是在用流程控制的思路写面向对象的类，思路的起点就错了……
gname这个变量不是 iswitch 这个类的属性，调用肯定出问题

枼小天

[Python] 纯文本查看 复制代码

class iswitch():

    def __init__(self):
        self.url = 'http://www.paopaoche.net/psp/114_PSP_'
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
            # 'Referer':"https://www.manhuadb.com/author/370"

        }
        self.zidian = {}

    def main(self):
        gname = input("input you wan search game name:")  # 这里定义了gname

        for p in range(1, 10):

            r = requests.get(self.url + str(p) + '.html', self.headers)
            r.encoding = "gbk"
            soup = BeautifulSoup(r.text, 'lxml')
            soup2 = soup.find('p', class_="list clearfix")
            # print(soup2)
            for j in soup2.find_all('u'):
                # print(j.getText())
                self.zidian["name"] = j.getText()
                if gname in self.zidian["name"]:
                    print(self.zidian["name"])

花都开啦

rsnodame 发表于 2020-9-9 11:20
这是在用流程控制的思路写面向对象的类，思路的起点就错了……
gname这个变量不是 iswitch 这 ...

我看着一直怪怪的，一语道破哈哈

luanshils

感觉是作用域的问题

hahawangzi

superain 发表于 2020-9-9 11:11
弱弱的问一句 你执行以后有显示input you wan search game name这个让你输入吗

你还别说 跳出来了。。。。就是输入了报错的

lr881015

[Python] 纯文本查看 复制代码

import requests
from bs4 import BeautifulSoup
url='https://s.paopaoche.net/'
headers={
 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
   }
plantform = ('android','apple','pc','zj','xcx','vr')
gname=input("请输入游戏名称:")
plantform_numb = input('输入下载平台（安卓请输入0，苹果请输入1，PC请输入2，主机请输入3，小程序请输入4，VR请输入5）：') or '0'
cid = plantform[int(plantform_numb)]
params ={
    'cid':cid,
    'k':gname
}
r_page = requests.get(url,params = params, headers = headers)
soup = BeautifulSoup(r_page.text, 'lxml')
result = soup.find('dl',attrs={'id':"result"})
for child in result.children:
    if not child.string:
        temp_name_version = child.div.a.text
        temp_name,temp_version = temp_name_version.split('下载')
        name = temp_name.strip()
        version = temp_version.strip()
        url = child.div.a['href']
        print(name,version,url)