如何修改TrackmaniaExchange搜索链接以生成地图下载链接

我正在编写Python脚本，从TrackmaniaExchange网站的搜索结果批量下载地图。已知地图下载链接格式为https://trackmania.exchange/maps/download/(map id)，但搜索结果的href格式为/maps/(map id)/(map name)。计划用Selenium获取href，通过正则修改链接并移除末尾的地图名，但不知具体实现方法。现有脚本如下：

import requests
import os.path
import os
import selenium.webdriver as webdriver
from selenium.webdriver.firefox.options import Options
import time
import re

def Search():
    link="https://trackmania.exchange/mapsearch2?limit=100" #Trackmania Exchange link, will scrape all 100 results
    checkedlink = re.sub("\s", "+", link) #Replaces spaces with + for track names (this shouldnt happen with authors/tags)
    options = Options() #This is for selenium
    options.binary_location = "C:/Program Files/Mozilla Firefox/firefox.exe"
    driver = webdriver.Firefox(options=options)
    search_box = driver.find_element_by_name("trackname")
    sitelinks = driver.find_element_by_xpath("/html/[div/@id='container'/@data-select2-id='container']/[div/@class='container-inner']/[div/@class='ly-box-open']/[div/@class='box-col-6']/[div/@class='windowv2-panel']/[div/@id='searchResults-container']/div/div/table/tbody/[tr/@class='WindowTableCell2v2 with-hover has-image']/[td/@class='cell-ellipsis']")
    results = []
    name=input("Track Name (if nothing, hit enter)") #Prompts the user to input stuff
    author=input("Track Author (if nothing, hit enter)")
    tags=input("Tags (separate with %2C if there's multiple, if nothing, hit enter)")
    path=input("Map download directory (do not leave blank, use forward slashes)")
    print("WARNING: Download wget for this script to work.")
    type(name) #These are to make a link to find html with
    type(author)
    type(tags)
    type(path)
    if path == "":
        print("Please put a path next time you start this")
        time.sleep(3)
        os.exit()
    else: #And so begins the if/else hellhole to find out what needs to be added to the link
        if tags == "":
            if name == "":
                if author == "":
                    print("Chief, you cant just enter nothing.  Put something in here next time")
                    time.sleep(3)
                    os.exit()
                else:
                    link = link+"&author="+author
            else:
                link = link+"&trackname="+name
                if author != "":
                    link = link+"&author="+author
        else:
            link = link+"&tags="+tags
            if name != "":
                link = link+"&trackname="+name
                if author != "":
                    link = link+"&author="+author
            else:
                if author != "":
                    link = link+"&author="+author
    print("Checking link...")
    checkedlink() #this is to make sure there's no spaces in the link.  tags are separated by %2C, but track names are separated by +
    print("Attempting to download...")
    driver.get(link)
    links = sitelinks
    for link in links
        href = link.get_attribute("href")
        browser.close()
        with open("list.txt", "w", encoding="utf-8") as f:
            f.write(href)
            for line in f:
                h = re.findall("\d") #My failed attempt at removing the end of the link
                re.sub("/maps/", "https://trackmania.exchange/maps/download", f)
                re.sub("") #unfinished part cause i was stubbed
    os.system("wget --directory-prefix="path" -i list.txt")

Search()

解决方案 #

1. 核心：生成下载链接的方法 #

不需要复杂的字符串替换，直接从href中提取地图ID，再拼接成标准下载链接。用正则表达式可以快速捕获ID：

def convert_to_download_link(href):
    # 匹配/maps/后面的数字ID
    match_result = re.search(r'/maps/(\d+)/', href)
    if match_result:
        map_id = match_result.group(1)
        return f"https://trackmania.exchange/maps/download/{map_id}"
    # 匹配失败时返回None
    return None

比如输入/maps/91677/cloudy-day，会返回https://trackmania.exchange/maps/download/91677。

2. 修正脚本中的其他关键错误 #

原脚本存在语法、逻辑错误，以下是修正后的完整可运行脚本：

import os
import time
import re
import selenium.webdriver as webdriver
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

def convert_to_download_link(href):
    match_result = re.search(r'/maps/(\d+)/', href)
    if match_result:
        map_id = match_result.group(1)
        return f"https://trackmania.exchange/maps/download/{map_id}"
    return None

def Search():
    base_link = "https://trackmania.exchange/mapsearch2?limit=100"
    options = Options()
    options.binary_location = "C:/Program Files/Mozilla Firefox/firefox.exe"
    driver = webdriver.Firefox(options=options)
    
    # 获取用户输入
    name = input("Track Name (if nothing, hit enter): ")
    author = input("Track Author (if nothing, hit enter): ")
    tags = input("Tags (separate with %2C if multiple, if nothing, hit enter): ")
    path = input("Map download directory (do not leave blank, use forward slashes): ")
    
    print("WARNING: Download wget for this script to work.")
    
    # 校验路径
    if not path:
        print("Please provide a valid path next time.")
        time.sleep(3)
        driver.quit()
        os.exit()
    
    # 构建搜索链接
    params = []
    if name:
        params.append(f"trackname={re.sub(r'\s', '+', name)}")
    if author:
        params.append(f"author={author}")
    if tags:
        params.append(f"tags={tags}")
    
    if not params:
        print("You must enter at least one search criteria.")
        time.sleep(3)
        driver.quit()
        os.exit()
    
    final_link = f"{base_link}&{'&'.join(params)}"
    print(f"Checking link: {final_link}")
    
    # 加载搜索页面并等待结果加载
    driver.get(final_link)
    try:
        WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.XPATH, "//table[@id='searchResults']//td[@class='cell-ellipsis']/a"))
        )
    except:
        print("Failed to load search results.")
        driver.quit()
        return
    
    # 获取所有地图链接并转换为下载链接
    map_links = driver.find_elements(By.XPATH, "//table[@id='searchResults']//td[@class='cell-ellipsis']/a")
    download_links = []
    
    for link in map_links:
        href = link.get_attribute("href")
        download_link = convert_to_download_link(href)
        if download_link:
            download_links.append(download_link)
    
    # 写入下载链接到文件
    with open("list.txt", "w", encoding="utf-8") as f:
        f.write("\n".join(download_links))
    
    # 调用wget批量下载
    os.system(f'wget --directory-prefix="{path}" -i list.txt')
    
    # 关闭浏览器
    driver.quit()
    print("Download process completed.")

if __name__ == "__main__":
    Search()

关键修正点说明 #

• 用WebDriverWait等待页面加载，避免元素未找到的错误
• 修正XPATH选择器，正确定位搜索结果中的地图链接
• 重构搜索链接构建逻辑，替代嵌套if/else的复杂写法
• 修复文件写入逻辑，一次性写入所有下载链接
• 修正循环语法、函数调用等基础错误

内容的提问来源于stack exchange，提问作者j0cffex2