主页 / 问题 / 1436129
Accepted
MayorLeon19
Asked:2022-08-04 19:12:44 +0000 UTC2022-08-04 19:12:44 +0000 UTC

我的世界服务器解析器问题

  • 772

我想为我的世界服务器做一个解析器，所以我开始做它，这是一个死胡同。它显示相同的ip版本等等，我需要一切都不同，我的代码是：

import requests
from bs4 import BeautifulSoup as bs
import pandas as pd

URL_TEMPLATE = "https://monitoringminecraft.ru/novie-servera"
FILE_NAME = "test.csv"

def parse():
    result_list = {'href': [], 'title': [], 'about': []}
    r = requests.get(URL_TEMPLATE)
    soup = bs(r.text, "html.parser")
    server = soup.find('tr', class_='server')
    ru = soup.find_all('div', class_='flag ru')
    ip = soup.find('span', class_='ip_serv')
    version = soup.find('td', class_='ver')
    opened = soup.find('td', class_='opened')
    online = soup.find('div', class_='wrap')
    clear_ip = [c.text for c in ip]
    clear_version = [c.text for c in version]
    clear_opened = [c.text for c in opened]
    clear_online = [c.text for c in online]
    comps = []
    for servers in server:
        comps.append({
            'ip': clear_ip,
            'version': clear_version,
            'opened': clear_opened,
            'online': clear_online
        })
        for comp in comps:
            print(comp)
parse()

控制台输出什么：

{'ip': ['89.239.167.113:19132'], 'version': ['?'], 'opened': ['только что'], 'online': [' ', '0', ' из 2022 ']}
{'ip': ['89.239.167.113:19132'], 'version': ['?'], 'opened': ['только что'], 'online': [' ', '0', ' из 2022 ']}
{'ip': ['89.239.167.113:19132'], 'version': ['?'], 'opened': ['только что'], 'online': [' ', '0', ' из 2022 ']}
{'ip': ['89.239.167.113:19132'], 'version': ['?'], 'opened': ['только что'], 'online': [' ', '0', ' из 2022 ']}
python парсер

1 个回答

  1. Best Answer

    您的错误是您将 ip、版本等标签 1 次（遇到的第一个）并立即“将其投入战斗”。解决问题的代码：

    import requests
from bs4 import BeautifulSoup as bs
import pandas as pd

URL_TEMPLATE = "https://monitoringminecraft.ru/novie-servera"
FILE_NAME = "test.csv"
r = requests.get(URL_TEMPLATE)
soup = bs(r.text, "html.parser")
server = []
server = soup.find_all('tr', class_='server')
sym_ = len(server) - 1
amount = 0
_sym = 0
def parse(amount, _sym, sym_):
    result_list = {'href': [], 'title': [], 'about': []}
    r = requests.get(URL_TEMPLATE)
    soup = bs(r.text, "html.parser")
    ru = soup.find_all('div', class_='flag ru')
    ip = []
    ip += soup.find_all('span', class_='ip_serv')
    ip = ip[_sym:-sym_]
    version = []
    version = soup.find_all('td', class_='ver')
    version = version[_sym:-sym_]
    opened = []
    opened += soup.find_all('td', class_='opened')
    opened = opened[_sym:-sym_]
    online = []
    online += soup.find_all('div', class_='wrap')
    online = online[_sym:-sym_]
    clear_ip = [c.text for c in ip]
    clear_version = [c.text for c in version]
    clear_opened = [c.text for c in opened]
    clear_online = [c.text for c in online]
    comps = []
    comps.append({
        'ip': clear_ip,
        'version': clear_version,
        'opened': clear_opened,
        'online': clear_online
        })
        
    print(comps)
    
    if amount >= len(server)-1:
        pass
    else:
        _sym+=1
        sym_-=1
        amount += 1
        parse(amount, _sym, sym_)

parse(amount, _sym, sym_)
    • 0

相关问题