Question

我正在尝试从我提取的.json文件中提取文本。问题是，每次我尝试我都会得到上述错误（标题）。这是我的代码：

import json

with open('grtwe.json.json', 'r') as f:
    line = f.readline()
    tweet = json.loads(line)
    print(json.dumps(tweet, indent=4))

此外，推文也是希腊语。

我的.json文件的第一行是这个

{"place": null, "geo": null, "source": "<a href=\"" rel=\"nofollow\">Twitter Lite</a>", "id_str": "967369573505921024", "favorite_count": 0, "in_reply_to_status_id": null, "favorited": false, "in_reply_to_user_id": null, "in_reply_to_status_id_str": null, "contributors": null, "is_quote_status": false, "full_text": "RT @documentonews:#Novartis_gate\n\u0391\u03c0\u03bf\u03ba\u03ac\u03bb\u03c5\u03c8\u03b7-\u03c3\u03bf\u03ba: \u039a\u03b1\u03b9 \u03c4\u03c1\u03af\u03c4\u03bf\u03c2 \u03bd\u03b5\u03ba\u03c1\u03cc\u03c2 \u03c3\u03c4\u03bf \u03b4\u03c1\u03cc\u03bc\u03bf \u03c4\u03b7\u03c2 Novartis, \u03c3\u03c4\u03bf Documento \u03c0\u03bf\u03c5 \u03ba\u03c5\u03ba\u03bb\u03bf\u03c6\u03bf\u03c1\u03b5\u03af \u03c4\u03b7\u03bd \u039a\u03c5\u03c1\u03b9\u03b1\u03ba\u03ae | https\u2026", "truncated": false, "user": {"notifications": false, "is_translator": false, "profile_image_url": "", "profile_background_tile": false, "id_str": "387685829", "geo_enabled": false, "profile_image_url_https":"", "statuses_count": 47093, "screen_name": "satrapis21", "is_translation_enabled": false, "followers_count": 1692, "has_extended_profile": false, "profile_background_image_url_https": "", "url": null, "follow_request_sent": false, "profile_sidebar_border_color": "FFFFFF", "profile_use_background_image": true, "profile_link_color": "D02B55", "profile_text_color": "3E4415", "description":"\u03be\u03b5\u03bd\u03bf\u03b4\u03bf\u03c7\u03bf\u03c2 \u03b3\u03ba\u03bf\u03c5\u03bb\u03b1\u03b3\u03ba \u03b5\u03c0\u03b5\u03bd\u03b4\u03c5\u03c4\u03b7\u03c2", "profile_background_color": "352726", "id": 387685829, "friends_count": 1689, "favourites_count": 3380, "created_at": "Sun Oct 09 14:01:48 +0000 2011", "default_profile": false, "translator_type": "none", "entities": {"description": {"urls": []}}, "profile_sidebar_fill_color": "99CC33", "default_profile_image": false, "listed_count": 39, "profile_banner_url": "","following": false, "utc_offset": 7200, "protected": false, "verified": false, "name": "\u03ba\u03bf\u03c5\u03bb\u03b7\u03c2satrapis", "profile_background_image_url":"", "time_zone": "Vilnius", "lang": "el", "contributors_enabled": false,"location": ""}, "metadata": {"result_type": "recent", "iso_language_code": "el"}, "id": 967369573505921024, "in_reply_to_screen_name": null, "created_at": "Sat Feb 2412:04:13 +0000 2018", "display_text_range": [0, 140], "retweeted": false, "in_reply_to_user_id_str": null, "lang": "el", "coordinates": null, "retweeted_status": {"place": null, "geo": null, "source": "<a href=\"http://twitter.com\" rel=\"nofollow\">Twitter Web Client</a>", "id_str": "967369433864863744", "favorite_count": 13, "in_reply_to_status_id": null, "favorited": false, "in_reply_to_user_id": null, "in_reply_to_status_id_str": null, "contributors": null, "is_quote_status": false,"full_text": "#Novartis_gate\n\u0391\u03c0\u03bf\u03ba\u03ac\u03bb\u03c5\u03c8\u03b7-\u03c3\u03bf\u03ba: \u039a\u03b1\u03b9 \u03c4\u03c1\u03af\u03c4\u03bf\u03c2 \u03bd\u03b5\u03ba\u03c1\u03cc\u03c2 \u03c3\u03c4\u03bf \u03b4\u03c1\u03cc\u03bc\u03bf \u03c4\u03b7\u03c2 Novartis, \u03c3\u03c4\u03bf Documento \u03c0\u03bf\u03c5 \u03ba\u03c5\u03ba\u03bb\u03bf\u03c6\u03bf\u03c1\u03b5\u03af \u03c4\u03b7\u03bd \u039a\u03c5\u03c1\u03b9\u03b1\u03ba\u03ae | ","truncated": false, "user": {"notifications": false, "is_translator": false, "profile_image_url": "", "profile_background_tile": false, "id_str": "795738344906952705", "geo_enabled": false, "profile_image_url_https": "", "statuses_count": 39383, "screen_name": "documentonews", "is_translation_enabled": false, "followers_count": 4607, "has_extended_profile": false, "profile_background_image_url_https": null, "url": "", "follow_request_sent": false, "profile_sidebar_border_color": "C0DEED", "profile_use_background_image": true, "profile_link_color": "1DA1F2", "profile_text_color": "333333", "description": "H \u039d\u03ad\u03b1 \u039c\u03b5\u03b3\u03ac\u03bb\u03b7 \u039a\u03c5\u03c1\u03b9\u03b1\u03ba\u03ac\u03c4\u03b9\u03ba\u03b7 \u0395\u03c6\u03b7\u03bc\u03b5\u03c1\u03af\u03b4\u03b1", "profile_background_color": "F5F8FA", "id": 795738344906952705, "friends_count": 180, "favourites_count": 0, "created_at": "Mon Nov 07 21:23:00 +0000 2016", "default_profile": true, "translator_type": "none", "entities": {"url": {"urls": [{"url": "", "display_url": "documentonews.gr", "expanded_url": "", "indices": [0, 23]}]}, "description": {"urls": []}}, "profile_sidebar_fill_color": "DDEEF6", "default_profile_image": false, "listed_count": 69, "profile_banner_url": "", "following": false,"utc_offset": 7200, "protected": false, "verified": false, "name": "Documento", "profile_background_image_url": null, "time_zone": "Athens", "lang": "en", "contributors_enabled": false, "location": "Greece"},"metadata": {"result_type": "recent", "iso_language_code": "el"}, "id": 967369433864863744, "in_reply_to_screen_name": null, "created_at": "Sat Feb 24 12:03:40 +0000 2018", "display_text_range": [0, 162],"retweeted": false, "in_reply_to_user_id_str": null, "lang": "el", "coordinates": null, "entities": {"hashtags": [{"text": "Novartis_gate", "indices": [0, 14]}], "user_mentions": [], "symbols": [], "urls": [{"url": "", "display_url": "Documentonews.gr", "expanded_url": "", "indices": [115, 138]}, {"url": "", "display_url":"documentonews.gr/article/apokal\u2026", "expanded_url": "", "indices": [139, 162]}]}, "possibly_sensitive": false, "retweet_count": 10}, "entities": {"hashtags": [{"text": "Novartis_gate", "indices": [19, 33]}], "user_mentions": [{"name": "Documento", "id": 795738344906952705,"screen_name": "documentonews", "id_str": "795738344906952705", "indices": [3, 17]}], "symbols": [], "urls": []}, "possibly_sensitive": false, "retweet_count": 10}

文件的其余部分包含此类记录。

Answer 1

这很可能是因为您尝试仅解析文件的第一行（因为您在json.loads()上调用了f.readline()）。听起来更可能的是，你的整个文件是JSON - 在这种情况下你想要一次性传递整个东西。

with open('grtwe.json.json', 'r') as f:
    tweet = json.loads(f.read())
    print(json.dumps(tweet, indent=4))

但是，我显然无法在没有文件的情况下进行检查！

Answer 2

loads（）触发了错误！
所以问题出在似乎不在json中的json文件中格式。

您需要确保json文件的格式正确json
您可以转到https://jsonlint.com并在其中传递json字符串
它将告诉您格式是否正确。

json.decoder.JSONDecodeError：期望值：第2行第1列（字符2）

2 个答案: