File size: 3,618 Bytes
f43107a 633bcd8 f43107a 633bcd8 f1594cf f43107a 633bcd8 f43107a 633bcd8 f43107a 633bcd8 f43107a 011d0ba f43107a 2213246 633bcd8 f43107a 633bcd8 011d0ba f43107a 2213246 f43107a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
import re
from json import loads
from uuid import uuid4
from fake_useragent import UserAgent
from tls_client import Session
class Completion:
@staticmethod
def create(
prompt: str,
page: int = 1,
count: int = 10,
safe_search: str = 'Moderate',
on_shopping_page: bool = False,
mkt: str = '',
response_filter: str = 'WebPages,Translations,TimeZone,Computation,RelatedSearches',
domain: str = 'youchat',
query_trace_id: str = None,
chat: list = None,
include_links: bool = False,
detailed: bool = False,
debug: bool = False,
) -> dict:
if chat is None:
chat = []
client = Session(client_identifier='chrome_108')
client.headers = Completion.__get_headers()
response = client.get(
f'https://you.com/api/streamingSearch',
params={
'q': prompt,
'page': page,
'count': count,
'safeSearch': safe_search,
'onShoppingPage': on_shopping_page,
'mkt': mkt,
'responseFilter': response_filter,
'domain': domain,
'queryTraceId': str(uuid4()) if query_trace_id is None else query_trace_id,
'chat': str(chat), # {'question':'','answer':' ''}
},
)
if debug:
print('\n\n------------------\n\n')
print(response.text)
print('\n\n------------------\n\n')
if 'youChatToken' not in response.text:
return Completion.__get_failure_response()
you_chat_serp_results = re.search(
r'(?<=event: youChatSerpResults\ndata:)(.*\n)*?(?=event: )', response.text
).group()
third_party_search_results = re.search(
r'(?<=event: thirdPartySearchResults\ndata:)(.*\n)*?(?=event: )', response.text).group()
# slots = findall(r"slots\ndata: (.*)\n\nevent", response.text)[0]
text = ''.join(re.findall(r'{\"youChatToken\": \"(.*?)\"}', response.text))
extra = {
'youChatSerpResults': loads(you_chat_serp_results),
# 'slots' : loads(slots)
}
return {
'response': text.replace('\\n', '\n').replace('\\\\', '\\').replace('\\"', '"'),
'links': loads(third_party_search_results)['search']['third_party_search_results']
if include_links
else None,
'extra': extra if detailed else None,
}
@classmethod
def __get_headers(cls) -> dict:
return {
'authority': 'you.com',
'accept': 'text/event-stream',
'accept-language': 'en,fr-FR;q=0.9,fr;q=0.8,es-ES;q=0.7,es;q=0.6,en-US;q=0.5,am;q=0.4,de;q=0.3',
'cache-control': 'no-cache',
'referer': 'https://you.com/search?q=who+are+you&tbm=youchat',
'sec-ch-ua': '"Not_A Brand";v="99", "Google Chrome";v="109", "Chromium";v="109"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'sec-fetch-dest': 'empty',
'sec-fetch-mode': 'cors',
'sec-fetch-site': 'same-origin',
'cookie': f'safesearch_guest=Moderate; uuid_guest={str(uuid4())}',
'user-agent': UserAgent().random,
}
@classmethod
def __get_failure_response(cls) -> dict:
return dict(response='Unable to fetch the response, Please try again.', links=[], extra={})
|