ruby/twitter-scraper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Get authenticated scraping working

Browse Source
This commit is contained in:
Ruby
2025-01-26 00:19:53 +13:00
parent 278d0a56c4
commit a81a461da2
4 changed files with 205 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -1 +1,2 @@
venv/
.env

55
README.md
View File

@ -1,15 +1,60 @@
## Twitter scraper
Scrape user's tweets :D
### Usage:
## Usage:
`tweets = TweetsScraper().get_tweets_anonymous("<user_id>")`
### Unauthenticated
Example:
```
scraper = TweetScraper()
tweets = scraper.get_tweets_anonymous("<user_id>")
```
returns a list of tweets from the user as viewed from a logged-out session. Will only return 100 tweets (not necessarily the most recent)
This will only allow use of the anonymous user tweets method, other methods will fail.
`tweets = TweetsScraper().get_tweets("<user_id>")`
The anonymous method returns a list of tweets from the user as viewed from a logged-out session. It will only return 100 tweets (not necessarily the most recent)
not implemented yet, will get tweets as a logged in user
### Authenticated
Example:
```
dotenv.load_dotenv()
auth_token = os.environ["AUTH_TOKEN"]
csrf_token = os.environ["CSRF_TOKEN"]
scraper = TweetsScraper(auth_token, csrf_token)
user_id = scraper.get_id_from_screen_name("pobnellion")
user_tweets = scraper.get_tweets(user_id, 100)
```
Allows you to get tweets as a logged in user. Twitter only makes the 2000 ish most recent tweets available, but that should be more than enough.
You can either directly pass in the user id to `get_tweets()`, or use `get_id_from_screen_name()` to get the id if you don't have it.
To use dotenv, include a `.env` file in the directory with the following contents (no quotes around the values):
```
AUTH_TOKEN=<auth token>
CSRF_TOKEN=<csrf token>
```
You can find your auth and csrf tokens in twitter's cookies (F12 in your browser > storage tab > cookies)
The auth token cookie is called `auth_token` and the csrf token is called `ct0`
### Tweet object
Contains the text of the tweet, along with the timestamp and some stats (like count, repost count, views, etc)
#### Fields:
- id : tweet id
- views : view count
- text : tweet content
- likes : like count
- replies : reply count
- retweets : retweet count
- quotes : quite tweet count
- date : post date
Printing a tweet object results in an overview:
`L:52 RT:2 Q:1 R:3 V:1032 2025-01-20T01:53:57+00:00 Example tweet text`

1
requirements.txt
View File

@ -1,3 +1,4 @@
pytz==2024.2
requests==2.32.3
zstd==1.5.6.1
python-dotenv==1.0.1

280
scraper.py
View File

@ -1,132 +1,8 @@
import requests, re, json, pytz, zstd
import requests, re, json, pytz, zstd, dotenv, os
from datetime import datetime
class TweetsScraper:
_GET_TWEETS_URL = 'https://api.x.com/graphql/MpOINUGH_YVb2BKjYZOPaQ/UserTweets'
# public non-logged-in access token (same for everyone, doesn't expire)
_AUTHORIZATION_TOKEN = 'AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA'
_HEADERS = {
"Host": "api.x.com",
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:133.0) Gecko/20100101 Firefox/133.0",
"Accept": "*/*",
"Accept-Language": "en-US,en;q=0.5",
"Accept-Encoding": "gzip, deflate, br, zstd",
"content-type": "application/json",
"authorization": f"Bearer {_AUTHORIZATION_TOKEN}",
"x-twitter-client-language": "en",
"x-twitter-active-user": "yes",
"Origin": "https://x.com",
"Sec-GPC": "1",
"Connection": "keep-alive",
"Referer": "https://x.com/",
"Sec-Fetch-Dest": "empty",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-site",
"TE": "trailers",
}
_FEATURES_USER_TWEETS = '{"profile_label_improvements_pcf_label_in_post_enabled":true,"rweb_tipjar_consumption_enabled":true,"responsive_web_graphql_exclude_directive_enabled":true,"verified_phone_label_enabled":false,"creator_subscriptions_tweet_preview_api_enabled":true,"responsive_web_graphql_timeline_navigation_enabled":true,"responsive_web_graphql_skip_user_profile_image_extensions_enabled":false,"premium_content_api_read_enabled":false,"communities_web_enable_tweet_community_results_fetch":true,"c9s_tweet_anatomy_moderator_badge_enabled":true,"responsive_web_grok_analyze_button_fetch_trends_enabled":false,"responsive_web_grok_analyze_post_followups_enabled":false,"responsive_web_jetfuel_frame":false,"responsive_web_grok_share_attachment_enabled":true,"articles_preview_enabled":true,"responsive_web_edit_tweet_api_enabled":true,"graphql_is_translatable_rweb_tweet_is_translatable_enabled":true,"view_counts_everywhere_api_enabled":true,"longform_notetweets_consumption_enabled":true,"responsive_web_twitter_article_tweet_consumption_enabled":true,"tweet_awards_web_tipping_enabled":false,"creator_subscriptions_quote_tweet_preview_enabled":false,"freedom_of_speech_not_reach_fetch_enabled":true,"standardized_nudges_misinfo":true,"tweet_with_visibility_results_prefer_gql_limited_actions_policy_enabled":true,"rweb_video_timestamps_enabled":true,"longform_notetweets_rich_text_read_enabled":true,"longform_notetweets_inline_media_enabled":true,"responsive_web_grok_image_annotation_enabled":false,"responsive_web_enhance_cards_enabled":false}'
_FIELD_TOGGLES_USER_TWEETS = '{"withArticlePlainText":false}'
def __init__(self):
self._session = requests.Session()
def _get_guest_token(self):
# Get guest token from x.com request
if "x-guest-token" in self._HEADERS.keys():
return
# Different headers necessary so we dont get a 400 response
headers = {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Encoding": "gzip, deflate, br, zstd",
"Accept-Language": "en-US,en;q=0.5",
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"Host": "x.com",
"Pragma": "no-cache",
"Priority": "u=0, i",
"Sec-Fetch-Dest": "document",
"Sec-Fetch-Mode": "navigate",
"Sec-Fetch-Site": "none",
"Sec-Fetch-User": "?1",
"Sec-GPC": "1",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:134.0) Gecko/20100101 Firefox/134.0",
"x-client-transaction-id": "78k0T6XnCiJK2f5fZ5RwmyeKmiOHk8HFfWovTa6JQF4DRfIkyjpARHxQzi0pWxKPtzks0ezFLICv4xuxmIyokH1EBEWe7A",
"x-guest-token": "1881289785240932544"
}
res = self._session.get("https://x.com/?mx=2", headers=headers)
# find the guest token in the response
self._HEADERS["x-guest-token"] = res.text.split("gt=")[1].split(";")[0]
def get_tweets_anonymous(self, user):
self._get_guest_token()
variables = {
"userId": user,
"count": 100,
"includePromotedContent": True,
"withQuickPromoteEligibilityTweetFields": True,
"withVoice": True,
"withV2Timeline": True
}
res = self._session.get(self._GET_TWEETS_URL, params={"variables": json.dumps(variables, separators=(',', ':')), "features": self._FEATURES_USER_TWEETS, "fieldToggles": self._FIELD_TOGGLES_USER_TWEETS}, headers=self._HEADERS)
res_json = None
try:
res_json = json.loads(zstd.decompress(res.content))
except:
res_json = json.loads(res.text)
entries = [i for i in res_json['data']['user']['result']['timeline_v2']['timeline']['instructions'] if i['type'] == "TimelineAddEntries"][0]['entries']
return [Tweet(entry) for entry in entries if "tweet" in entry['entryId']]
def get_tweets(self, user, count=100):
return
# self._get_guest_token()
# user_id = self._get_user_by_screen_name(user)
tweets = []
variables = {
"userId": user,
"count": min(count, 100),
"includePromotedContent": True,
"withQuickPromoteEligibilityTweetFields": True,
"withVoice": True,
"withV2Timeline": True
}
last_len = 0
while len(tweets) < count:
res = requests.get(self._GET_TWEETS_URL, params={"variables": json.dumps(variables, separators=(',', ':')), "features": self._FEATURES_USER_TWEETS, "fieldToggles": self._FIELD_TOGGLES_USER_TWEETS}, headers=self._HEADERS)
res_json = None
try:
res_json = json.loads(zstd.decompress(res.content))
except:
res_json = json.loads(res.text)
entries = [i for i in res_json['data']['user']['result']['timeline_v2']['timeline']['instructions'] if i['type'] == "TimelineAddEntries"][0]['entries']
tweets.extend([Tweet(entry) for entry in entries if "tweet" in entry['entryId']])
# variables['cursor'] = [entry for entry in entries if "cursor-bottom" in entry['entryId']][0]['content']['value']
break
if len(tweets) == last_len:
break
print(f"Got {len(tweets)} tweets")
last_len = len(tweets)
return tweets
class Tweet():
class Tweet:
def __init__(self, tweet_object):
tweet = tweet_object['content']['itemContent']['tweet_results']['result']
self.id = tweet['rest_id']
@ -148,8 +24,158 @@ class Tweet():
return datetime.now().astimezone(pytz.utc) - self.date
class TweetsScraper:
_GET_TWEETS_URL = 'https://api.x.com/graphql/MpOINUGH_YVb2BKjYZOPaQ/UserTweets'
_GET_ID_BY_SCREEN_NAME_URL = "https://x.com/i/api/graphql/32pL5BWe9WKeSK1MoPvFQQ/UserByScreenName"
# public non-logged-in access token (same for everyone, doesn't expire)
_PUBLIC_AUTHORIZATION_TOKEN = 'AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA'
_COMMON_HEADERS = {
"Accept": "*/*",
"Accept-Encoding": "gzip, deflate, br, zstd",
"Accept-Language": "en-US,en;q=0.5",
"authorization": f"Bearer {_PUBLIC_AUTHORIZATION_TOKEN}",
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"content-type": "application/json",
"Pragma": "no-cache",
"Sec-GPC": "1",
"TE": "trailers",
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:134.0) Gecko/20100101 Firefox/134.0",
}
_FEATURES_USER_TWEETS = '{"profile_label_improvements_pcf_label_in_post_enabled":true,"rweb_tipjar_consumption_enabled":true,"responsive_web_graphql_exclude_directive_enabled":true,"verified_phone_label_enabled":false,"creator_subscriptions_tweet_preview_api_enabled":true,"responsive_web_graphql_timeline_navigation_enabled":true,"responsive_web_graphql_skip_user_profile_image_extensions_enabled":false,"premium_content_api_read_enabled":false,"communities_web_enable_tweet_community_results_fetch":true,"c9s_tweet_anatomy_moderator_badge_enabled":true,"responsive_web_grok_analyze_button_fetch_trends_enabled":false,"responsive_web_grok_analyze_post_followups_enabled":false,"responsive_web_jetfuel_frame":false,"responsive_web_grok_share_attachment_enabled":true,"articles_preview_enabled":true,"responsive_web_edit_tweet_api_enabled":true,"graphql_is_translatable_rweb_tweet_is_translatable_enabled":true,"view_counts_everywhere_api_enabled":true,"longform_notetweets_consumption_enabled":true,"responsive_web_twitter_article_tweet_consumption_enabled":true,"tweet_awards_web_tipping_enabled":false,"creator_subscriptions_quote_tweet_preview_enabled":false,"freedom_of_speech_not_reach_fetch_enabled":true,"standardized_nudges_misinfo":true,"tweet_with_visibility_results_prefer_gql_limited_actions_policy_enabled":true,"rweb_video_timestamps_enabled":true,"longform_notetweets_rich_text_read_enabled":true,"longform_notetweets_inline_media_enabled":true,"responsive_web_grok_image_annotation_enabled":false,"responsive_web_enhance_cards_enabled":false}'
_FIELD_TOGGLES_USER_TWEETS = '{"withArticlePlainText":false}'
_FEATURES_SCREEN_NAME = '{"hidden_profile_subscriptions_enabled":true,"profile_label_improvements_pcf_label_in_post_enabled":true,"rweb_tipjar_consumption_enabled":true,"responsive_web_graphql_exclude_directive_enabled":true,"verified_phone_label_enabled":false,"subscriptions_verification_info_is_identity_verified_enabled":true,"subscriptions_verification_info_verified_since_enabled":true,"highlights_tweets_tab_ui_enabled":true,"responsive_web_twitter_article_notes_tab_enabled":true,"subscriptions_feature_can_gift_premium":true,"creator_subscriptions_tweet_preview_api_enabled":true,"responsive_web_graphql_skip_user_profile_image_extensions_enabled":false,"responsive_web_graphql_timeline_navigation_enabled":true}'
_FIELD_TOGGLES_SCREEN_NAME = '{"withAuxiliaryUserLabels":false}'
def __init__(self, auth_token: str = None, csrf_token: str = None):
self._session = requests.Session()
self._session.headers.update(self._COMMON_HEADERS)
if auth_token is not None and csrf_token is not None:
self._session.cookies.set("auth_token", auth_token)
self._session.cookies.set("ct0", csrf_token)
self._session.headers.update({ "x-csrf-token": csrf_token })
def _get_guest_token(self):
# Get guest token from x.com request
if "x-guest-token" in self._session.headers.keys():
return
# Different headers necessary so we dont get a 400 response
headers = {
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Encoding": "gzip, deflate, br, zstd",
"Accept-Language": "en-US,en;q=0.5",
"Cache-Control": "no-cache",
"Connection": "keep-alive",
"Pragma": "no-cache",
"Sec-Fetch-Dest": "document",
"Sec-Fetch-Mode": "navigate",
"Sec-Fetch-Site": "none",
"Sec-Fetch-User": "?1",
"Sec-GPC": "1",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:134.0) Gecko/20100101 Firefox/134.0",
}
res = requests.get("https://x.com/?mx=2", headers=headers)
# find the guest token in the response
self._session.headers.update({ "x-guest-token": res.text.split("gt=")[1].split(";")[0] })
def get_tweets_anonymous(self, user_id: str) -> list[Tweet]:
self._get_guest_token()
variables = {
"userId": user_id,
"count": 100,
"includePromotedContent": True,
"withQuickPromoteEligibilityTweetFields": True,
"withVoice": True,
"withV2Timeline": True
}
res = self._session.get(self._GET_TWEETS_URL, params={"variables": json.dumps(variables, separators=(',', ':')), "features": self._FEATURES_USER_TWEETS, "fieldToggles": self._FIELD_TOGGLES_USER_TWEETS})
res_json = None
try:
res_json = json.loads(zstd.decompress(res.content))
except:
res_json = json.loads(res.text)
entries = [i for i in res_json['data']['user']['result']['timeline_v2']['timeline']['instructions'] if i['type'] == "TimelineAddEntries"][0]['entries']
return [Tweet(entry) for entry in entries if "tweet" in entry['entryId']]
def get_tweets(self, user_id: str, count: int=100) -> list[Tweet]:
tweets = []
variables = {
"userId": user_id,
"count": min(count, 100),
"includePromotedContent": True,
"withQuickPromoteEligibilityTweetFields": True,
"withVoice": True,
"withV2Timeline": True
}
last_len = 0
while len(tweets) < count:
res = self._session.get(self._GET_TWEETS_URL, params={"variables": json.dumps(variables, separators=(',', ':')), "features": self._FEATURES_USER_TWEETS, "fieldToggles": self._FIELD_TOGGLES_USER_TWEETS})
res_json = None
try:
res_json = json.loads(zstd.decompress(res.content))
except:
res_json = json.loads(res.text)
entries = [i for i in res_json['data']['user']['result']['timeline_v2']['timeline']['instructions'] if i['type'] == "TimelineAddEntries"][0]['entries']
tweets.extend([Tweet(entry) for entry in entries if "tweet" in entry['entryId']])
# get cursor for next page
variables['cursor'] = [entry for entry in entries if "cursor-bottom" in entry['entryId']][0]['content']['value']
if len(tweets) == last_len:
break
print(f"Got {len(tweets)} tweets")
last_len = len(tweets)
return tweets
def get_id_from_screen_name(self, name: str) -> str:
variables = {
"screen_name": name
}
res = self._session.get(self._GET_ID_BY_SCREEN_NAME_URL, params={"variables": json.dumps(variables, separators=(',', ':')), "features": self._FEATURES_SCREEN_NAME, "fieldToggles": self._FIELD_TOGGLES_SCREEN_NAME})
res_json = None
try:
res_json = json.loads(zstd.decompress(res.content))
except:
res_json = json.loads(res.text)
return res_json['data']['user']['result']['rest_id']
if __name__ == "__main__":
user_tweets = TweetsScraper().get_tweets_anonymous("1279948441968246785") # pobnellion
dotenv.load_dotenv()
auth_token = os.environ["AUTH_TOKEN"]
csrf_token = os.environ["CSRF_TOKEN"]
scraper = TweetsScraper(auth_token, csrf_token)
user_id = scraper.get_id_from_screen_name("pobnellion")
user_tweets = scraper.get_tweets(user_id, 100)
for t in user_tweets:
print(t)