python→ Language

圆弧YH2026-06-07 8:56

乌尔都语

代码如下：

python 复制代码 
import requests
import re
 
from bs4 import BeautifulSoup as bs
 
import os
 
 
# 创建mp3保存文件夹
save_dir = "Locense Urdu audio"
if not os.path.exists(save_dir):
    os.mkdir(save_dir)
    
# 配置参数
BASE_URL = "https://www.loecsen.com/en/vocabulary-urdu"
AUDIO_PREFIX = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"
SAVE_FOLDER = "russian_audio"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
 
base_mp3_url = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"  # 替换成mp3真实域名，拼接ru_mp3_filename
 
 
 
def get_page_html():
    """获取页面源码"""
 
    resp = requests.get(BASE_URL, headers=HEADERS)
    resp.raise_for_status()
    resp.encoding = "utf-8"
    return resp.text    
html = get_page_html()
 
 
soup = bs(html, 'html.parser')
all_data = []
topr_all = soup.select('div.topr')
 
# 遍历每一组topr，group_idx=组号（从1开始）
for group_idx, block in enumerate(topr_all, start=1):
    colonnes_div = block.select_one('div.colonnes')
    if not colonnes_div:
        continue
    cate_name = colonnes_div.find('span').get_text(strip=True)
    voc_wrap = block.select_one('div.contentfiches.voc')
    if not voc_wrap:
        all_data.append({"category": cate_name, "words": []})
        continue
 
    word_rows = voc_wrap.select('tr[data-id]')
    temp_words = []
    for tr in word_rows:
        tds = tr.find_all('td')
        if len(tds) != 3:
            continue
        td_en, td_ru, td_pron = tds
        mp3_file_name = td_ru.get('data-id', '')
        en = td_en.get_text(strip=True).replace('🔊\xa0', '')
        ru = td_ru.get_text(strip=True).replace('🔊\xa0', '')#ru,代表语言
        pron = td_pron.get_text(strip=True)
 
        # 拼接mp3完整下载链接
        full_mp3_url = base_mp3_url + mp3_file_name
 
        word_info = {
            "group_num": group_idx,
            "category": cate_name,    # 补充分类名进单条数据
            "english": en,
            "language": ru,           # 原ru → 修改为表头的language
            "pronunciation": pron,
            "mp3_filename": full_mp3_url #原ru_mp3_filename → mp3_filename
        }
        
        temp_words.append(word_info)
 
        # 构造文件名：
        save_name = f"{group_idx}，{en}，{ru}，{pron}.mp3"
        save_path = os.path.join(save_dir, save_name)
 
        # 下载mp3
        try:
            resp = requests.get(full_mp3_url, timeout=15)
            if resp.status_code == 200:
                with open(save_path, "wb") as f:
                    f.write(resp.content)
                print(f"✅已下载：{save_name}")
            else:
                print(f"❌链接失效：{full_mp3_url}")
        except Exception as e:
            print(f"⚠️下载失败 {save_name} ,错误:{str(e)}")
 
    all_data.append({
        "category": cate_name,
        "words": temp_words
    })
 
# 导出csv
import csv
with open("乌尔都语词汇汇总.csv", "w", encoding="utf-8-sig", newline="") as f:
    headers = ["group_num","category","english","language","pronunciation","mp3_filename"]
    csv_w = csv.DictWriter(f, fieldnames=headers)
    csv_w.writeheader()
    for group in all_data:
        for word_info in group["words"]:
            csv_w.writerow(word_info)
print("\n📄csv文件导出完成")

阿拉伯语

python 复制代码 
import requests
import re
 
from bs4 import BeautifulSoup as bs
 
import os
 
 
# 创建mp3保存文件夹
save_dir = "Locense Arab_mp3_audio"
if not os.path.exists(save_dir):
    os.mkdir(save_dir)
    
# 配置参数
BASE_URL = "https://www.loecsen.com/en/vocabulary-arabic"
AUDIO_PREFIX = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"
SAVE_FOLDER = "russian_audio"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
 
base_mp3_url = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"  # 替换成mp3真实域名，拼接ru_mp3_filename

 
 
def get_page_html():
    """获取页面源码"""
 
    resp = requests.get(BASE_URL, headers=HEADERS)
    resp.raise_for_status()
    resp.encoding = "utf-8"
    return resp.text    
html = get_page_html()
 
 
soup = bs(html, 'html.parser')
all_data = []
topr_all = soup.select('div.topr')
 
# 遍历每一组topr，group_idx=组号（从1开始）
for group_idx, block in enumerate(topr_all, start=1):
    colonnes_div = block.select_one('div.colonnes')
    if not colonnes_div:
        continue
    cate_name = colonnes_div.find('span').get_text(strip=True)
    voc_wrap = block.select_one('div.contentfiches.voc')
    if not voc_wrap:
        all_data.append({"category": cate_name, "words": []})
        continue
 
    word_rows = voc_wrap.select('tr[data-id]')
    temp_words = []
    for tr in word_rows:
        tds = tr.find_all('td')
        if len(tds) != 3:
            continue
        td_en, td_ru, td_pron = tds
        mp3_file_name = td_ru.get('data-id', '')
        en = td_en.get_text(strip=True).replace('🔊\xa0', '')
        ru = td_ru.get_text(strip=True).replace('🔊\xa0', '')#ru,代表语言
        pron = td_pron.get_text(strip=True)
 
        # 拼接mp3完整下载链接
        full_mp3_url = base_mp3_url + mp3_file_name
 
        word_info = {
            "group_num": group_idx,
            "category": cate_name,    # 补充分类名进单条数据
            "english": en,
            "language": ru,           # 原ru → 修改为表头的language
            "pronunciation": pron,
            "mp3_filename": full_mp3_url #原ru_mp3_filename → mp3_filename
        }
        
        temp_words.append(word_info)
 
        # 构造文件名：
        save_name = f"{group_idx}，{en}，{ru}，{pron}.mp3"
        save_path = os.path.join(save_dir, save_name)
 
        # 下载mp3
        try:
            resp = requests.get(full_mp3_url, timeout=15)
            if resp.status_code == 200:
                with open(save_path, "wb") as f:
                    f.write(resp.content)
                print(f"✅已下载：{save_name}")
            else:
                print(f"❌链接失效：{full_mp3_url}")
        except Exception as e:
            print(f"⚠️下载失败 {save_name} ,错误:{str(e)}")
 
    all_data.append({
        "category": cate_name,
        "words": temp_words
    })
 
# 导出csv
import csv
with open("阿拉伯语词汇汇总.csv", "w", encoding="utf-8-sig", newline="") as f:
    headers = ["group_num","category","english","language","pronunciation","mp3_filename"]
    csv_w = csv.DictWriter(f, fieldnames=headers)
    csv_w.writeheader()
    for group in all_data:
        for word_info in group["words"]:
            csv_w.writerow(word_info)
print("\n📄csv文件导出完成")

日语

Japanese, 表格是三列，用如下代码：

python 复制代码 
import requests
import re
 
from bs4 import BeautifulSoup as bs
 
import os
 
 
# 创建mp3保存文件夹
save_dir = "Locense mp3_audio"
if not os.path.exists(save_dir):
    os.mkdir(save_dir)
    
# 配置参数
BASE_URL = "https://www.loecsen.com/en/vocabulary-japanese"
AUDIO_PREFIX = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"
SAVE_FOLDER = "russian_audio"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
 
base_mp3_url = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"  # 替换成mp3真实域名，拼接ru_mp3_filename

 
 
def get_page_html():
    """获取页面源码"""
 
    resp = requests.get(BASE_URL, headers=HEADERS)
    resp.raise_for_status()
    resp.encoding = "utf-8"
    return resp.text    
html = get_page_html()
 
 
soup = bs(html, 'html.parser')
all_data = []
topr_all = soup.select('div.topr')
 
# 遍历每一组topr，group_idx=组号（从1开始）
for group_idx, block in enumerate(topr_all, start=1):
    colonnes_div = block.select_one('div.colonnes')
    if not colonnes_div:
        continue
    cate_name = colonnes_div.find('span').get_text(strip=True)
    voc_wrap = block.select_one('div.contentfiches.voc')
    if not voc_wrap:
        all_data.append({"category": cate_name, "words": []})
        continue
 
    word_rows = voc_wrap.select('tr[data-id]')
    temp_words = []
    for tr in word_rows:
        tds = tr.find_all('td')
        if len(tds) != 3:
            continue
        td_en, td_ru, td_pron = tds
        mp3_file_name = td_ru.get('data-id', '')
        en = td_en.get_text(strip=True).replace('🔊\xa0', '')
        ru = td_ru.get_text(strip=True).replace('🔊\xa0', '')#ru,代表语言
        pron = td_pron.get_text(strip=True)
 
        # 拼接mp3完整下载链接
        full_mp3_url = base_mp3_url + mp3_file_name
 
        word_info = {
            "group_num": group_idx,
            "category": cate_name,    # 补充分类名进单条数据
            "english": en,
            "language": ru,           # 原ru → 修改为表头的language
            "pronunciation": pron,
            "mp3_filename": full_mp3_url #原ru_mp3_filename → mp3_filename
        }
        
        temp_words.append(word_info)
 
        # 构造文件名：
        save_name = f"{group_idx}，{en}，{ru}，{pron}.mp3"
        save_path = os.path.join(save_dir, save_name)
 
        # 下载mp3
        try:
            resp = requests.get(full_mp3_url, timeout=15)
            if resp.status_code == 200:
                with open(save_path, "wb") as f:
                    f.write(resp.content)
                print(f"✅已下载：{save_name}")
            else:
                print(f"❌链接失效：{full_mp3_url}")
        except Exception as e:
            print(f"⚠️下载失败 {save_name} ,错误:{str(e)}")
 
    all_data.append({
        "category": cate_name,
        "words": temp_words
    })
 
# 导出csv
import csv
with open("日语词汇汇总.csv", "w", encoding="utf-8-sig", newline="") as f:
    headers = ["group_num","category","english","language","pronunciation","mp3_filename"]
    csv_w = csv.DictWriter(f, fieldnames=headers)
    csv_w.writeheader()
    for group in all_data:
        for word_info in group["words"]:
            csv_w.writerow(word_info)
print("\n📄csv文件导出完成")

俄语

Russian, 表格是三列。代码如下

python 复制代码 
import requests
import re

from bs4 import BeautifulSoup as bs

import os


# 创建mp3保存文件夹
save_dir = "ru_mp3_audio"
if not os.path.exists(save_dir):
    os.mkdir(save_dir)
    
# 配置参数
BASE_URL = "https://www.loecsen.com/en/vocabulary-russian#in-case-of-trouble"
AUDIO_PREFIX = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"
SAVE_FOLDER = "russian_audio"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}



base_mp3_url = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"  # 替换成mp3真实域名，拼接ru_mp3_filename
# ===========================================================


def get_page_html():
    """获取页面源码"""

    resp = requests.get(BASE_URL, headers=HEADERS)
    resp.raise_for_status()
    resp.encoding = "utf-8"
    return resp.text    
html = get_page_html()


soup = bs(html, 'html.parser')
all_data = []
topr_all = soup.select('div.topr')

# 遍历每一组topr，group_idx=组号（从1开始）
for group_idx, block in enumerate(topr_all, start=1):
    colonnes_div = block.select_one('div.colonnes')
    if not colonnes_div:
        continue
    cate_name = colonnes_div.find('span').get_text(strip=True)
    voc_wrap = block.select_one('div.contentfiches.voc')
    if not voc_wrap:
        all_data.append({"category": cate_name, "words": []})
        continue

    word_rows = voc_wrap.select('tr[data-id]')
    temp_words = []
    for tr in word_rows:
        tds = tr.find_all('td')
        if len(tds) != 3:
            continue
        td_en, td_ru, td_pron = tds
        mp3_file_name = td_ru.get('data-id', '')
        en = td_en.get_text(strip=True).replace('🔊\xa0', '')
        ru = td_ru.get_text(strip=True).replace('🔊\xa0', '')
        pron = td_pron.get_text(strip=True)

        # 拼接mp3完整下载链接
        full_mp3_url = base_mp3_url + mp3_file_name

        word_info = {
            "english": en,
            "russian": ru,
            "pronunciation": pron,
            "ru_mp3_filename": full_mp3_url,
            "group_num": group_idx
        }
        temp_words.append(word_info)

        # 构造文件名："1，Hello，Здравствуйте，Zdravstvuyte.mp3"
        save_name = f"{group_idx}，{en}，{ru}，{pron}.mp3"
        save_path = os.path.join(save_dir, save_name)

        # 下载mp3
        try:
            resp = requests.get(full_mp3_url, timeout=15)
            if resp.status_code == 200:
                with open(save_path, "wb") as f:
                    f.write(resp.content)
                print(f"✅已下载：{save_name}")
            else:
                print(f"❌链接失效：{full_mp3_url}")
        except Exception as e:
            print(f"⚠️下载失败 {save_name} ,错误:{str(e)}")

    all_data.append({
        "category": cate_name,
        "words": temp_words
    })

# 导出csv
import csv
with open("俄语词汇汇总.csv", "w", encoding="utf-8-sig", newline="") as f:
    headers = ["group_num","category","english","russian","pronunciation","ru_mp3_filename"]
    csv_w = csv.DictWriter(f, fieldnames=headers)
    csv_w.writeheader()
    for group in all_data:
        for word_info in group["words"]:
            csv_w.writerow(word_info)
print("\n📄csv文件导出完成")

在loecsen网站上下载相关语言学习音频资料。

西班牙语

代码如下

python 复制代码 
import requests
import re
 
from bs4 import BeautifulSoup as bs
 
import os
 
 
# 创建mp3保存文件夹
save_dir = "Locense Spanish mp3_audio"
if not os.path.exists(save_dir):
    os.mkdir(save_dir)
    
# 配置参数
BASE_URL = "https://www.loecsen.com/en/vocabulary-spanish"
AUDIO_PREFIX = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"
SAVE_FOLDER = "russian_audio"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
 
base_mp3_url = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"  # 替换成mp3真实域名，拼接ru_mp3_filename

 
 
def get_page_html():
    """获取页面源码"""
 
    resp = requests.get(BASE_URL, headers=HEADERS)
    resp.raise_for_status()
    resp.encoding = "utf-8"
    return resp.text    
html = get_page_html()
 
 
soup = bs(html, 'html.parser')
all_data = []
topr_all = soup.select('div.topr')
 
# 遍历每一组topr，group_idx=组号（从1开始）
for group_idx, block in enumerate(topr_all, start=1):
    colonnes_div = block.select_one('div.colonnes')
    if not colonnes_div:
        continue
    cate_name = colonnes_div.find('span').get_text(strip=True)
    voc_wrap = block.select_one('div.contentfiches.voc')
    if not voc_wrap:
        all_data.append({"category": cate_name, "words": []})
        continue
 
    word_rows = voc_wrap.select('tr[data-id]')
    temp_words = []
    for tr in word_rows:
        tds = tr.find_all('td')
        if len(tds) != 2:
            continue
        td_en, td_ru = tds
        mp3_file_name = td_ru.get('data-id', '')
        en = td_en.get_text(strip=True).replace('🔊\xa0', '')
        ru = td_ru.get_text(strip=True).replace('🔊\xa0', '')#ru,代表语言
 
        # 拼接mp3完整下载链接
        full_mp3_url = base_mp3_url + mp3_file_name
 
        word_info = {
            "group_num": group_idx,
            "category": cate_name,    # 补充分类名进单条数据
            "english": en,
            "language": ru,           # 原ru → 修改为表头的language
            "mp3_filename": full_mp3_url #原ru_mp3_filename → mp3_filename
        }
        
        temp_words.append(word_info)
 
        # 构造文件名：
        save_name = f"{group_idx}，{en}，{ru}.mp3"
        save_path = os.path.join(save_dir, save_name)
 
        # 下载mp3
        try:
            resp = requests.get(full_mp3_url, timeout=15)
            if resp.status_code == 200:
                with open(save_path, "wb") as f:
                    f.write(resp.content)
                print(f"✅已下载：{save_name}")
            else:
                print(f"❌链接失效：{full_mp3_url}")
        except Exception as e:
            print(f"⚠️下载失败 {save_name} ,错误:{str(e)}")
 
    all_data.append({
        "category": cate_name,
        "words": temp_words
    })
 
# 导出csv
import csv
with open("西班牙语词汇汇总.csv", "w", encoding="utf-8-sig", newline="") as f:
    headers = ["group_num","category","english","language","mp3_filename"]
    csv_w = csv.DictWriter(f, fieldnames=headers)
    csv_w.writeheader()
    for group in all_data:
        for word_info in group["words"]:
            csv_w.writerow(word_info)
print("\n📄csv文件导出完成")

德语

对于该网站中的德语音频，因为网页中表格是两列，所以对代码略有调整，

如： if len(tds) != 2: continue。删去不必要的第三列信息。

如下：

python 复制代码 
import requests
import re
 
from bs4 import BeautifulSoup as bs
 
import os
 
 
# 创建mp3保存文件夹
save_dir = "Locense mp3_audio"
if not os.path.exists(save_dir):
    os.mkdir(save_dir)
    
# 配置参数
BASE_URL = "https://www.loecsen.com/en/vocabulary-german"
AUDIO_PREFIX = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"
SAVE_FOLDER = "russian_audio"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
 
base_mp3_url = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"  # 替换成mp3真实域名，拼接ru_mp3_filename

 
 
def get_page_html():
    """获取页面源码"""
 
    resp = requests.get(BASE_URL, headers=HEADERS)
    resp.raise_for_status()
    resp.encoding = "utf-8"
    return resp.text    
html = get_page_html()
 
 
soup = bs(html, 'html.parser')
all_data = []
topr_all = soup.select('div.topr')
 
# 遍历每一组topr，group_idx=组号（从1开始）
for group_idx, block in enumerate(topr_all, start=1):
    colonnes_div = block.select_one('div.colonnes')
    if not colonnes_div:
        continue
    cate_name = colonnes_div.find('span').get_text(strip=True)
    voc_wrap = block.select_one('div.contentfiches.voc')
    if not voc_wrap:
        all_data.append({"category": cate_name, "words": []})
        continue
 
    word_rows = voc_wrap.select('tr[data-id]')
    temp_words = []
    for tr in word_rows:
        tds = tr.find_all('td')
        if len(tds) != 2:
            continue
        td_en, td_ru = tds
        mp3_file_name = td_ru.get('data-id', '')
        en = td_en.get_text(strip=True).replace('🔊\xa0', '')
        ru = td_ru.get_text(strip=True).replace('🔊\xa0', '')#ru,代表语言
 
        # 拼接mp3完整下载链接
        full_mp3_url = base_mp3_url + mp3_file_name
 
        word_info = {
            "group_num": group_idx,
            "category": cate_name,    # 补充分类名进单条数据
            "english": en,
            "language": ru,           # 原ru → 修改为表头的language
            "mp3_filename": full_mp3_url #原ru_mp3_filename → mp3_filename
        }
        
        temp_words.append(word_info)
 
        # 构造文件名：
        save_name = f"{group_idx}，{en}，{ru}.mp3"
        save_path = os.path.join(save_dir, save_name)
 
        # 下载mp3
        try:
            resp = requests.get(full_mp3_url, timeout=15)
            if resp.status_code == 200:
                with open(save_path, "wb") as f:
                    f.write(resp.content)
                print(f"✅已下载：{save_name}")
            else:
                print(f"❌链接失效：{full_mp3_url}")
        except Exception as e:
            print(f"⚠️下载失败 {save_name} ,错误:{str(e)}")
 
    all_data.append({
        "category": cate_name,
        "words": temp_words
    })
 
# 导出csv
import csv
with open("德语词汇汇总.csv", "w", encoding="utf-8-sig", newline="") as f:
    headers = ["group_num","category","english","language","mp3_filename"]
    csv_w = csv.DictWriter(f, fieldnames=headers)
    csv_w.writeheader()
    for group in all_data:
        for word_info in group["words"]:
            csv_w.writerow(word_info)
print("\n📄csv文件导出完成")

法语

代码如下：

python 复制代码 
import requests
import re
 
from bs4 import BeautifulSoup as bs
 
import os
 
 
# 创建mp3保存文件夹
save_dir = "Locense Franch mp3_audio"
if not os.path.exists(save_dir):
    os.mkdir(save_dir)
    
# 配置参数
BASE_URL = "https://www.loecsen.com/en/vocabulary-french"
AUDIO_PREFIX = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"
SAVE_FOLDER = "russian_audio"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
 
base_mp3_url = "https://www.loecsen.com/OrizonFlash_V2/ressources/son/"  # 替换成mp3真实域名，拼接ru_mp3_filename

 
 
def get_page_html():
    """获取页面源码"""
 
    resp = requests.get(BASE_URL, headers=HEADERS)
    resp.raise_for_status()
    resp.encoding = "utf-8"
    return resp.text    
html = get_page_html()
 
 
soup = bs(html, 'html.parser')
all_data = []
topr_all = soup.select('div.topr')
 
# 遍历每一组topr，group_idx=组号（从1开始）
for group_idx, block in enumerate(topr_all, start=1):
    colonnes_div = block.select_one('div.colonnes')
    if not colonnes_div:
        continue
    cate_name = colonnes_div.find('span').get_text(strip=True)
    voc_wrap = block.select_one('div.contentfiches.voc')
    if not voc_wrap:
        all_data.append({"category": cate_name, "words": []})
        continue
 
    word_rows = voc_wrap.select('tr[data-id]')
    temp_words = []
    for tr in word_rows:
        tds = tr.find_all('td')
        if len(tds) != 2:
            continue
        td_en, td_ru = tds
        mp3_file_name = td_ru.get('data-id', '')
        en = td_en.get_text(strip=True).replace('🔊\xa0', '')
        ru = td_ru.get_text(strip=True).replace('🔊\xa0', '')#ru,代表语言
 
        # 拼接mp3完整下载链接
        full_mp3_url = base_mp3_url + mp3_file_name
 
        word_info = {
            "group_num": group_idx,
            "category": cate_name,    # 补充分类名进单条数据
            "english": en,
            "language": ru,           # 原ru → 修改为表头的language
            "mp3_filename": full_mp3_url #原ru_mp3_filename → mp3_filename
        }
        
        temp_words.append(word_info)
 
        # 构造文件名：
        save_name = f"{group_idx}，{en}，{ru}.mp3"
        save_path = os.path.join(save_dir, save_name)
 
        # 下载mp3
        try:
            resp = requests.get(full_mp3_url, timeout=15)
            if resp.status_code == 200:
                with open(save_path, "wb") as f:
                    f.write(resp.content)
                print(f"✅已下载：{save_name}")
            else:
                print(f"❌链接失效：{full_mp3_url}")
        except Exception as e:
            print(f"⚠️下载失败 {save_name} ,错误:{str(e)}")
 
    all_data.append({
        "category": cate_name,
        "words": temp_words
    })
 
# 导出csv
import csv
with open("法语词汇汇总.csv", "w", encoding="utf-8-sig", newline="") as f:
    headers = ["group_num","category","english","language","mp3_filename"]
    csv_w = csv.DictWriter(f, fieldnames=headers)
    csv_w.writeheader()
    for group in all_data:
        for word_info in group["words"]:
            csv_w.writerow(word_info)
print("\n📄csv文件导出完成")

即可完成。

相关推荐
装不满的克莱因瓶1 小时前
掌握神经网络的模型结构
人工智能·python·深度学习·神经网络·机器学习·ai
稷下元歌1 小时前
7天学会plc加机器视觉关于运动控制部份，配套视频在bib
开发语言·c++·git·vscode·python·docker·pip
奋斗的小方1 小时前
Java进阶篇1-1:异常
java·开发语言·python
颜酱1 小时前
LangChain 调大模型：模板拼接 + invoke / stream / batch
python·langchain
ice8130331811 小时前
【Python】调用opencv识别图片人脸位置
人工智能·python·opencv
Full Stack Developme1 小时前
Hutool CollUtil 教程
java·开发语言·windows·python
2601_950368911 小时前
镁钆稀土合金粉末，专业供应助力精密制造升级
python·制造
染指11101 小时前
19.LangChain框架7-LangChain1.0版本使用Agent（中间件实例）
人工智能·python·机器学习·langchain·agent·rag
装不满的克莱因瓶1 小时前
从梯度下降到 Adam 优化器：掌握神经网络参数优化的核心原理
人工智能·python·深度学习·神经网络·机器学习·计算机视觉·ai
热门推荐
01GitHub 镜像站点02【AI】2026 年具身智能模型和世界模型总结032026 年 AI 编程工具终极横评：Cursor vs Claude Code vs Copilot vs Windsurf04Codex 下载安装指南：Windows 和 macOS 官方版下载05Codex 桌面端更新后 Chrome 插件和 Computer Use 不可用，怎么排查和修复06CC-Switch 下载、安装与使用配置指南【2026.5.29】07【踩坑记录 | 第一篇】微软商店无法使用时，如何手动安装 OpenAI Codex？附`.msix`文件系统错误解决方法08CC-Switch & Claude 基于 Linux 服务器安装使用指南09Codex 接入 DeepSeek API 完整配置文档10裂开！ChatGPT 居然开始要手机号验证，附详细解决方法