search-me 2.0

Search in Google, Searx, Rambler. Explore VK, Facebook, Telegram, Twitter, Snapchat, Instagram, Tumblr, YouTube.

ASYNC SEARCH-ME

Search

• Google
• Rambler
• Searx.

Explore

• Facebook
• Instagram
• Snapchat
• Telegram
• Tumblr
• Twitter
• VK
• YouTube.

PRE-INSTALLING

• For generating pdf files setup wkhtmltopdf
• For downloading videos from youtube setup youtube-dl

INSTALLING

pip install search-me

USAGE

import asyncio
import logging

# Import engines
from search_me import Google, Searx, Rambler

logging.basicConfig(level=logging.DEBUG)

settings = {
    "pdf_report": False,  # Export search data to pdf-documents
    "pdf_parse": False,  # Parse generated pdf-documents, when pdf_report=True
    "social_search": False,  # Activate search across socials
    "socials": [  # Names of social nets
        "vk",
        "instagram",
        "telegram",
        "twitter",
        "youtube",
        "facebook",
        "tumblr",
        "snapchat"
    ],
    "app": {
        "interactive": True,  # Activate CLI animation
        "cache": True  # Caching data in .json and .pkl files
    },
    "web": {
        "results": 10,  # Number of search results on page
        "retry": 5,  # Number of retries for one query
        "timeout": 60,  # Timeout for one request
        "wait_min": 0.0,  # Minimum time in seconds to sleep after each query
        "wait_max": 1.5  # Maximum time in seconds to sleep after each query
    },
    "pdf": {
        "timeout": 10,  # Waiting time in seconds for create pdf-document
        "summary_params": [
            "ratio",  # Type of summarizing ("ratio" or "words")
            0.2  # Value (percent of text or count of words)
        ],
        "text": True,  # Extract text from pdf
        "summary": True,  # Generate summary from extracted text
        "urls": True,  # Extract urls from pdf
        "keywords": True  # Generate keywords from extracted text
    },
    "social": {
        "posts_limit": 10,  # Number of posts
        "timeout": 100.0,  # Timeout for one mediafile
        "download_media": True,  # Download from Instagram, Tumblr, Youtube, Snapchat
        "export_data": True,  # Export posts data in file
        "export_format": "csv"  # Export file format (.csv, .xls, .html, .json)
    }
}

# Setup engine (similarly Rambler & Searx)
# Missed keys will fill auto
# If settings didn't passed, default configuration will be loaded
# search_engine = Google()
search_engine = Google(**settings)


async def main(engine):
    await engine.search(*["0x0007ee", "社會信用體系"])
    # Iterate over results until next call engine.search(...)
    # Results will save and reset before new search
    async for r in engine.results:
        if not(r is None):
            print(f"{r.q}  |   {r.rating}  |   {r.uri}")
    await engine.search("Виктор Суворов — Аквариум ", "0x0007ee")
    # await engine.test(samples=3)


loop = asyncio.get_event_loop()
loop.run_until_complete(main(search_engine))

LINKS

• Search Language Codes
• List of Google domains