【Twitter 舆论分析】Twitter 实时推文爬虫

0x00 前言

继续探索Twitter API的使用，这次获取一下Twitter的实时推文。

0x01 具体步骤

1、sample-steam 样本流

这是Twitter提供的代码，比较简单，只需要更改一下"bearer_token"即可使用，相对获得的数据单一，满足不了需求，下文讲解如何设定搜索规则

# -*- codeing =utf-8 -*-
# @Time : 2021/11/22 10:47
# @Author:yuchuan
# @File : twitter-sample-steam.py
# @Software : PyCharm
import requests
import os
import json

# To set your environment variables in your terminal run the following line:
# export 'BEARER_TOKEN'='<your_bearer_token>'
bearer_token = 'your bearer_token'#look like "AAAAAAAAAAAAAAAAAAAAOHKRwEAAAAAXF5NOvPXXUPATBLLo*********"

def create_url():
    return "https://api.twitter.com/2/tweets/sample/stream"

def bearer_oauth(r):
    """
    Method required by bearer token authentication.
    """

    r.headers["Authorization"] = f"Bearer {bearer_token}"
    r.headers["User-Agent"] = "v2SampledStreamPython"
    return r

def connect_to_endpoint(url):
    response = requests.request("GET", url, auth=bearer_oauth, stream=True)
    print(response.status_code)
    for response_line in response.iter_lines():
        if response_line:
            json_response = json.loads(response_line)
            print(json.dumps(json_response, indent=4, sort_keys=True))
    if response.status_code != 200:
        raise Exception(
            "Request returned an error: {} {}".format(
                response.status_code, response.text
            )
        )

def main():
    url = create_url()
    timeout = 0
    while True:
        connect_to_endpoint(url)
        timeout += 1

if __name__ == "__main__":
    main()

简单更改过BEARER_TOKEN后，就可以得到下面这样的数据啦

{
    "data": {
        "id": "1462613720471900162",
        "text": "RT @shinslighterr: nao mas e essa official art de shingeki eu to me mijando https://t.co/m63s6sFGsJ"
    }
}
{
    "data": {
        "id": "1462613720442581000",
        "text": "RT @Corinthians: SE BUSCA RIVAL EN AMERICA \nSE BUSCA RIVAL EN AMERICA\nSE BUSCA RIVAL EN AMERICA\nSE BUSCA RIVAL EN AMERICA\nSE BUSCA RIVAL EN\u2026"
    }
}
{
    "data": {
        "id": "1462613720463331328",
        "text": "@kimkai_kggk yuk, gwe jaga lilin yh loe muter\ud83d\ude0d"
    }
}

这个样本得到的只有单纯的id，text，如果你需要其他元数据就需要进阶版的Stream Tweets了，下面就开始进阶讲解

2、Stream Tweets in real-time

1、首先讲解一下搜索内容的添加规则

详细规则可参考：

https://developer.twitter.com/en/docs/twitter-api/tweets/filtered-stream/integrate/build-a-rule

{"value": "dog has:images", "tag": "dog pictures"},
{"value": "cat has:images -grumpy", "tag": "cat pictures"}

Example :

"cat has:images“：关键词”cat"且有图片

“tag":“cat images”:分配的标签

lang:en 仅过滤英语推文

def set_rules(delete):
    # You can adjust the rules if needed
    sample_rules = [
        {"value": "dog has:images", "tag": "dog pictures"},
        {"value": "cat has:images -grumpy", "tag": "cat pictures"},
    ]
    payload = {"add": sample_rules}
    response = requests.post(
        "https://api.twitter.com/2/tweets/search/stream/rules",
        auth=bearer_oauth,
        json=payload,
    )

   2、搜索内容的返回字段设定

成功连接到流之后，默认响应Tweet字段：id、text,如果要获取这之外的内容，可以通过设置fields和扩展参数来指定

https://developer.twitter.com/en/docs/twitter-api/data-dictionary/object-model/tweet

这是Twitter给出的参考文件，关于field 和 expansion的说明，可以根据需要自己组合

比如我需要的内容有，author.id , tweets , entities ( hashtags , urls , mentions ) , public_metrics ( like , reply , retweet )

Key	Value	Returned fields
tweet.fields	public_metrics	like,reply,retweet
expansions	author_id	includes.users.id, includes.users.name, includes.users.username
tweet.fields	entities	hashtags,urls,mentions

根据需要的扩展部分参数设定url，就可以获得相应的返回字段。

tweet_fields = "tweet.fields=public_metrics,entities"
"https://api.twitter.com/2/tweets/search/stream?{}&expansions=author_id".format(tweet_fields)

def get_stream(set):
    tweet_fields = "tweet.fields=public_metrics,entities"
    url = "https://api.twitter.com/2/tweets/search/stream?{}&expansions=author_id".format(tweet_fields)

    response = requests.get(
        url, auth=bearer_oauth, stream=True,
    )
    print(response.status_code)
    if response.status_code != 200:
        raise Exception(
            "Cannot get stream (HTTP {}): {}".format(
                response.status_code, response.text
            )
        )
    for response_line in response.iter_lines():
        if response_line:
            json_response = json.loads(response_line)
            print(json.dumps(json_response, indent=4, sort_keys=True))

3.总结一下

①set_rules(request.post)设定搜索内容

②get_stream(request.get)设定获取内容

0x02 实现代码：

发现了一个问题，因为我在设计搜索规则的时候debug了好几次，每一次我更改规则后，都是在原来关键词的stream中增加入新关键词的stream， 我查了一下应该是因为request.post的原因。总之，爬出的内容要进行过滤保存，过滤时精确一点即可，这个搜索出来的内容应该是不占用Twitter api中每月限制爬取数额的。

# -*- codeing =utf-8 -*-
# @Time : 2021/11/22 15:28
# @Author:yuchuan
# @File : twitter_stream_tweets.py
# @Software : PyCharm
import requests
import os
import json

# To set your enviornment variables in your terminal run the following line:
# export 'BEARER_TOKEN'='<your_bearer_token>'
bearer_token ='<your_bearer_token>'#same as'AAAAAAAAAAAAAAAAAAAAAOHKRwEA**********'

def bearer_oauth(r):
    """
    Method required by bearer token authentication.
    """

    r.headers["Authorization"] = f"Bearer {bearer_token}"
    r.headers["User-Agent"] = "v2FilteredStreamPython"
    return r

#
# def get_rules():
#     response = requests.get(
#         "https://api.twitter.com/2/tweets/search/stream/rules", auth=bearer_oauth
#     )
#     if response.status_code != 200:
#         raise Exception(
#             "Cannot get rules (HTTP {}): {}".format(response.status_code, response.text)
#         )
#     print(json.dumps(response.json()))
#     return response.json()
#
#
# def delete_all_rules(rules):
#     if rules is None or "data" not in rules:
#         return None
#
#     ids = list(map(lambda rule: rule["id"], rules["data"]))
#     payload = {"delete": {"ids": ids}}
#     response = requests.post(
#         "https://api.twitter.com/2/tweets/search/stream/rules",
#         auth=bearer_oauth,
#         json=payload
#     )
#     if response.status_code != 200:
#         raise Exception(
#             "Cannot delete rules (HTTP {}): {}".format(
#                 response.status_code, response.text
#             )
#         )
#     print(json.dumps(response.json()))
#
#
def set_rules():
    # You can adjust the rules if needed
    sample_rules = [
        {"value": "Russia",},
    ]
    payload = {"add": sample_rules}
    response = requests.post(
        "https://api.twitter.com/2/tweets/search/stream/rules",
        auth=bearer_oauth,
        json=payload,
    )
    if response.status_code != 201:
        raise Exception(
            "Cannot add rules (HTTP {}): {}".format(response.status_code, response.text)
        )
    print(json.dumps(response.json()))

def get_stream(set):
    tweet_fields = "tweet.fields=public_metrics,entities"
    url = "https://api.twitter.com/2/tweets/search/stream?{}&expansions=author_id".format(tweet_fields)

    response = requests.get(
        url, auth=bearer_oauth, stream=True,
    )
    print(response.status_code)
    if response.status_code != 200:
        raise Exception(
            "Cannot get stream (HTTP {}): {}".format(
                response.status_code, response.text
            )
        )
    for response_line in response.iter_lines():
        if response_line:
            json_response = json.loads(response_line)
            print(json.dumps(json_response, indent=4, sort_keys=True))

def main():
    # rules = get_rules()
    # delete = delete_all_rules(rules)
    set = set_rules()
    get_stream(set)

if __name__ == "__main__":
    main()

0x03 一些闲话

本人创建了一个公众号，分享科研路上的小问题，新发现，欢迎关注公众号，给我留言！！！
一起奋发向上，攻克难题吧~~