使用“和”查找某些关键字:

时间:2015-02-23 03:55:16

标签: python json

我有一个关于"对于"的问题功能和" json"。 我想从Twitter数据中找到非常具体的英文关键词。 在这里,我将打开JSON文件并从JSON文件中读取行。 我只想在json.load()之前过滤掉只有英文的值 我认为只有 str(" lang" +':' +" en")会返回我的目标数据,但它没有&# 39;吨

with open(filename, "r+") as fi, open(out_file_name, "a") as fo:
            for line in fi:
                if keyword in line and str("lang"+':'+"en") in line:
                    fo.write(line + "\n")

我不确定是否可以分享推文的某些部分。但以下只是样本。

{
    "created_at":"Mon Jan 05 07:31:31 +0000 2015",
    "id":552004450513346560,
    "id_str":"552004450513346560",
    "text":"RT @PhoneCasesFTB:Here We Go:https:\/\/t.co\/WwdN1a7kqG @PhoneCasesFTB  #iPhone6 #iPhone6Cases #bendgate",
    "source":"\u003ca href=\"http:\/\/twitter.com\/download\/iphone\" rel=\"nofollow\"\u003eTwitter for iPhone\u003c\/a\u003e",
    "truncated":false,
    "in_reply_to_status_id":null,
    "in_reply_to_status_id_str":null,
    "in_reply_to_user_id":null,
    "in_reply_to_user_id_str":null,
    "in_reply_to_screen_name":null,
    "user":{
        "id":23280370,
        "id_str":"23280370",
        "name":"Ron Thornton",
        "screen_name":"RonThornton",
        "location":"Plano, Texas",
        "url":"http:\/\/www.makingfilms.com",
        "description":"Working on the film @GhostOfGoodnite. Starring Billy Zane,Lacey Chabert, Matt Dallas,-New Film 2015",
        "protected":false,
        "verified":false,
        "followers_count":21349,
        "friends_count":22227,
        "listed_count":297,
        "favourites_count":144216,
        "statuses_count":174513,
        "created_at":"Sun Mar 08 05:27:25 +0000 2009",
        "utc_offset":-21600,
        "time_zone":"Central Time (US & Canada)",
        "geo_enabled":true,
        "lang":"en",
        "contributors_enabled":false,
        "is_translator":false,
        "profile_background_color":"C0DEED",
        "profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png",
        "profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png",
        "profile_background_tile":false,
        "profile_link_color":"0084B4",
        "profile_sidebar_border_color":"C0DEED",
        "profile_sidebar_fill_color":"DDEEF6",
        "profile_text_color":"333333",
        "profile_use_background_image":true,
        "profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/503419704246300672\/Vfu_xvKg_normal.jpeg",
        "profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/503419704246300672\/Vfu_xvKg_normal.jpeg",
        "profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/23280370\/1420024669",
        "default_profile":true,
        "default_profile_image":false,
        "following":null,
        "follow_request_sent":null,
        "notifications":null
    },
    "geo":null,
    "coordinates":null,
    "place":null,
    "contributors":null,
    "retweeted_status":{
        "created_at":"Thu Jan 01 16:29:27 +0000 2015",
        "id":550690275455410176,
        "id_str":"550690275455410176",
        "text":"Here We Go:https:\/\/t.co\/WwdN1a7kqG @PhoneCasesFTB  #iPhone6 #iPhone6Cases #bendgate",
        "source":"\u003ca href=\"http:\/\/twitter.com\" rel=\"nofollow\"\u003eTwitter Web Client\u003c\/a\u003e",
        "truncated":false,
        "in_reply_to_status_id":null,
        "in_reply_to_status_id_str":null,
        "in_reply_to_user_id":null,
        "in_reply_to_user_id_str":null,
        "in_reply_to_screen_name":null,
        "user":{
            "id":2891446054,
            "id_str":"2891446054",
            "name":"Phone Cases",
            "screen_name":"PhoneCasesFTB",
            "location":"",
            "url":"http:\/\/phonecasesfromthebest.com",
            "description":null,
            "protected":false,
            "verified":false,
            "followers_count":1077,
            "friends_count":1099,
            "listed_count":4,
            "favourites_count":226,
            "statuses_count":1133,
            "created_at":"Mon Nov 24 22:51:00 +0000 2014",
            "utc_offset":-28800,
            "time_zone":"Pacific Time (US & Canada)",
            "geo_enabled":true,
            "lang":"en",
            "contributors_enabled":false,
            "is_translator":false,
            "profile_background_color":"C0DEED",
            "profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png",
            "profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png",
            "profile_background_tile":false,
            "profile_link_color":"0084B4",
            "profile_sidebar_border_color":"C0DEED",
            "profile_sidebar_fill_color":"DDEEF6",
            "profile_text_color":"333333",
            "profile_use_background_image":true,
            "profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/537015762888581121\/dK5JrMX-_normal.jpeg",
            "profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/537015762888581121\/dK5JrMX-_normal.jpeg",
            "default_profile":true,
            "default_profile_image":false,
            "following":null,
            "follow_request_sent":null,
            "notifications":null
        },
        "geo":null,
        "coordinates":null,
        "place":{
            "id":"81b8dcbe189773f2",
            "url":"https:\/\/api.twitter.com\/1.1\/geo\/id\/81b8dcbe189773f2.json",
            "place_type":"country",
            "name":"Hungary",
            "full_name":"Hungary",
            "country_code":"HU",
            "country":"Magyarorsz\u00e1g",
            "bounding_box":{
                "type":"Polygon",
                "coordinates":[
                    [
                        [16.1136813, 45.737124],
                        [16.1136813, 48.585233],
                        [22.8974571, 48.585233],
                        [22.8974571, 45.737124]
                    ]
                ]
            },
            "attributes":{}
        },
        "contributors":null,
        "retweet_count":2,
        "favorite_count":1,
        "entities":{
            "hashtags":[{
                "text":"iPhone6",
                "indices":[52, 60]
            }, {
                "text":"iPhone6Cases",
                "indices":[61, 74]
            }, {
                "text":"bendgate",
                "indices":[75, 84]
            }],
            "trends":[],
            "urls":[{
                "url":"https:\/\/t.co\/WwdN1a7kqG",
                "expanded_url":"https:\/\/medium.com\/@iPhone_6_Cases",
                "display_url":"medium.com\/@iPhone_6_Cases",
                "indices":[12, 35]
            }],
            "user_mentions":[{
                "screen_name":"PhoneCasesFTB",
                "name":"Phone Cases",
                "id":2891446054,
                "id_str":"2891446054",
                "indices":[36, 50]
            }],
            "symbols":[]
        },
        "favorited":false,
        "retweeted":false,
        "possibly_sensitive":false,
        "filter_level":"low",
        "lang":"en"
    },
    "retweet_count":0,
    "favorite_count":0,
    "entities":{
        "hashtags":[{
            "text":"iPhone6",
            "indices":[71, 79]
        }, {
            "text":"iPhone6Cases",
            "indices":[80, 93]
        }, {
            "text":"bendgate",
            "indices":[94, 103]
        }],
        "trends":[],
        "urls":[{
            "url":"https:\/\/t.co\/WwdN1a7kqG",
            "expanded_url":"https:\/\/medium.com\/@iPhone_6_Cases",
            "display_url":"medium.com\/@iPhone_6_Cases",
            "indices":[31, 54]
        }],
        "user_mentions":[{
            "screen_name":"PhoneCasesFTB",
            "name":"Phone Cases",
            "id":2891446054,
            "id_str":"2891446054",
            "indices":[3, 17]
        }, {
            "screen_name":"PhoneCasesFTB",
            "name":"Phone Cases",
            "id":2891446054,
            "id_str":"2891446054",
            "indices":[55, 69]
        }],
        "symbols":[]
    },
    "favorited":false,
    "retweeted":false,
    "possibly_sensitive":false,
    "filter_level":"medium",
    "lang":"en",
    "timestamp_ms":"1420443091406"
}

{
    "created_at":"Mon Jan 05 08:57:34 +0000 2015",
    "id":552026107294523392,
    "id_str":"552026107294523392",
    "text":"Patchworks wydaje specjalne 0.4mm szk\u0142o ochronne dla iPhone 6 i 6+ maj\u0105ce zabezpiecza\u0107 przed #bendgate http:\/\/t.co\/eHh3tjSfE5",
    "source":"\u003ca href=\"http:\/\/twitter.com\/download\/android\" rel=\"nofollow\"\u003eTwitter for Android\u003c\/a\u003e",
    "truncated":false,
    "in_reply_to_status_id":null,
    "in_reply_to_status_id_str":null,
    "in_reply_to_user_id":null,
    "in_reply_to_user_id_str":null,
    "in_reply_to_screen_name":null,
    "user":{
        "id":435219617,
        "id_str":"435219617",
        "name":"Tomasz Dunia",
        "screen_name":"theto3k",
        "location":"Lublin, Poland",
        "url":"http:\/\/theto3k.tk",
        "description":"Student of Mechatronics at University of Technology in Lublin. New technologies, movies, books, series and games enthusiast.\n~\nMo\u017cna mnie poczyta\u0107 na theto3k.tk",
        "protected":false,
        "verified":false,
        "followers_count":75,
        "friends_count":120,
        "listed_count":2,
        "favourites_count":1608,
        "statuses_count":6775,
        "created_at":"Mon Dec 12 20:21:08 +0000 2011",
        "utc_offset":3600,
        "time_zone":"Warsaw",
        "geo_enabled":false,
        "lang":"pl",
        "contributors_enabled":false,
        "is_translator":false,
        "profile_background_color":"000000",
        "profile_background_image_url":"http:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png",
        "profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme1\/bg.png",
        "profile_background_tile":false,
        "profile_link_color":"4A913C",
        "profile_sidebar_border_color":"000000",
        "profile_sidebar_fill_color":"000000",
        "profile_text_color":"000000",
        "profile_use_background_image":false,
        "profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/524604116752809985\/nI3P7q03_normal.jpeg",
        "profile_image_url_https":"https:\/\/pbs.twimg.com\/profile_images\/524604116752809985\/nI3P7q03_normal.jpeg",
        "profile_banner_url":"https:\/\/pbs.twimg.com\/profile_banners\/435219617\/1411995456",
        "default_profile":false,
        "default_profile_image":false,
        "following":null,
        "follow_request_sent":null,
        "notifications":null
    },
    "geo":null,
    "coordinates":null,
    "place":null,
    "contributors":null,
    "retweet_count":0,
    "favorite_count":0,
    "entities":{
        "hashtags":[{
            "text":"bendgate",
            "indices":[93, 102]
        }],
        "trends":[],
        "urls":[{
            "url":"http:\/\/t.co\/eHh3tjSfE5",
            "expanded_url":"http:\/\/www.theverge.com\/2015\/1\/4\/7491685\/patchworks-itg-edge-iphone-screen-protector-ces-2015",
            "display_url":"theverge.com\/2015\/1\/4\/74916\u2026",
            "indices":[103, 125]
        }],
        "user_mentions":[],
        "symbols":[]
    },
    "favorited":false,
    "retweeted":false,
    "possibly_sensitive":false,
    "filter_level":"medium",
    "lang":"pl",
    "timestamp_ms":"1420448254785"
}

1 个答案:

答案 0 :(得分:2)

看起来你需要的条件是

if keyword in line and '"lang":"en"' in line:

你只是简单地拼写了第二部分,而且不正确。