Python API 进阶

import instaloader

L = instaloader.Instaloader(
    # 下载选项
    download_pictures=True,       # 下载图片
    download_videos=True,         # 下载视频
    download_video_thumbnails=False,  # 不下载视频缩略图
    download_geotags=False,       # 不下载地理信息
    download_comments=False,      # 不下载评论
    save_metadata=True,           # 保存元数据
    compress_json=False,          # JSON 不压缩

    # 文件名模式
    filename_pattern="{date_utc:%Y%m%d}_{shortcode}",
    dirname_pattern="{profile}",

    # 速率控制
    max_connection_attempts=3,
    request_timeout=300.0,

    # 其他
    quiet=False,                  # 显示进度
    user_agent=None,              # 自定义 UA
)

import instaloader
from datetime import datetime
from itertools import islice

L = instaloader.Instaloader()
L.load_session_from_file("YOUR_USERNAME")

profile = instaloader.Profile.from_username(L.context, "target_user")

# 只下载轮播帖（多图）
for post in profile.get_posts():
    if post.typename == "GraphSidecar":  # 轮播帖
        L.download_post(post, target="carousels")

# 只下载特定时间段内点赞数 > 500 的视频
since = datetime(2024, 6, 1)
for post in profile.get_posts():
    if post.date_utc < since:
        break
    if post.is_video and post.likes > 500:
        L.download_post(post, target="popular_videos")

import instaloader

L = instaloader.Instaloader()

post = instaloader.Post.from_shortcode(L.context, "CxxxxxxYYYY")

if post.typename == "GraphSidecar":
    for index, node in enumerate(post.get_sidecar_nodes()):
        print(f"图片 {index + 1}: {node.display_url}")
        print(f"  是视频: {node.is_video}")
        if node.is_video:
            print(f"  视频 URL: {node.video_url}")

import instaloader

L = instaloader.Instaloader()

profile = instaloader.Profile.from_username(L.context, "profile_name")

# 下载头像
L.download_profilepic(profile)

import instaloader
import json
from itertools import islice

L = instaloader.Instaloader()
L.load_session_from_file("YOUR_USERNAME")

profile = instaloader.Profile.from_username(L.context, "target_user")

# 收集帖子数据用于分析
posts_data = []
for post in islice(profile.get_posts(), 100):
    posts_data.append({
        "shortcode": post.shortcode,
        "date": post.date_utc.isoformat(),
        "likes": post.likes,
        "comments": post.comments,
        "is_video": post.is_video,
        "caption": post.caption,
        "hashtags": post.caption_hashtags,
        "typename": post.typename,  # GraphImage, GraphVideo, GraphSidecar
    })

# 导出为 JSON
with open("posts_analysis.json", "w", encoding="utf-8") as f:
    json.dump(posts_data, f, ensure_ascii=False, indent=2)

print(f"已收集 {len(posts_data)} 个帖子的数据")