python | parse yandex images | requests | json | params | search by image | search by word

gistfile1.txt

#!/usr/bin/env python
# -*- coding: utf-8 -*-
import requests
import json
import sys
from pprint import pprint
from html_to_json import convert as cnv
from random import randint
from lxml.html.clean import Cleaner
import lxml
import re
from bs4 import BeautifulSoup as bs
from timeit import timeit
import os
from  glob import glob
headers = {
    'authority': 'yandex.ru',
    'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="96", "Google Chrome";v="96"',
    'device-memory': '8',
    'rtt': '150',
    'sec-ch-ua-mobile': '?0',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36',
    'viewport-width': '575',
    'dpr': '1',
    'downlink': '4.15',
    'ect': '4g',
    'sec-ch-ua-platform': '"Windows"',
    'accept': 'application/json',
    'sec-fetch-site': 'same-origin',
    'sec-fetch-mode': 'cors',
    'sec-fetch-dest': 'empty',
    'accept-language': 'ru-RU,ru;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6,zh;q=0.5'
}
 
 
def info(id):
    params = (
        ('docid', f'{id}'),
        ('lang', 'ru'),
        ('mt', '1'),
        ('family', '0'),
        ('pornowhitelist', '1'),
        ('ipnd', '1'),
    )
 
    response = requests.get('https://yandex.ru/images-apphost/rim',
                            headers=headers, params=params).json()
    return response
 
 
def load_image(byte):
    headers = {
        'authority': 'yandex.ru',
        'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="96", "Google Chrome";v="96"',
        'device-memory': '8',
        'rtt': '200',
        'sec-ch-ua-mobile': '?0',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36',
        'viewport-width': '794',
        'content-type': 'image/jpeg',
        'dpr': '1',
        'downlink': '2.65',
        'ect': '4g',
        'sec-ch-ua-platform': '"Windows"',
        'accept': '*/*',
        'origin': 'https://yandex.ru',
        'sec-fetch-site': 'same-origin',
        'sec-fetch-mode': 'cors',
        'sec-fetch-dest': 'empty',
        'accept-language': 'ru-RU,ru;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6,zh;q=0.5'
    }
 
    params = (
        ('cbird', '37'),
        ('images_avatars_size', 'preview'),
        ('images_avatars_namespace', 'images-cbir')
    )
 
    data = byte
    response = requests.post('https://yandex.ru/images-apphost/image-download',
                             headers=headers, params=params, data=data).json()
    print(response)
    return response
 
 
def getInfoImage(url):
    headers = {
        'authority': 'yandex.ru',
        'cache-control': 'max-age=0',
        'device-memory': '8',
        'dpr': '1',
        'viewport-width': '1280',
        'rtt': '200',
        'downlink': '2.2',
        'ect': '4g',
        'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="96", "Google Chrome";v="96"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'upgrade-insecure-requests': '1',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36',
        'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
        'sec-fetch-site': 'same-origin',
        'sec-fetch-mode': 'navigate',
        'sec-fetch-user': '?1',
        'sec-fetch-dest': 'document',
        'accept-language': 'ru-RU,ru;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6,zh;q=0.5'
        }
    if isinstance(dict, type(url)):
        params = (
            ('url', "".join(url['url'].split("/")[:-2]) + "orig"),
            ('cbir_id', url['url'].split("get-images-cbir/")
             [-1].split("/preview")[0]),
            ('cbir_page', 'similar'),
            ('rpt', 'imageview'),
            ('family', '0'),
            ('pornowhitelist', '1'),
            ('ipnd', '1'),
        )
    elif not url.startswith("http"):
        params = (
        ('text', url),
        ('from', 'tabbar'),
        ('family', '0'),
        ('pornowhitelist', '1'),
        ('ipnd', '1'),
        )  
    else:
        params = (
            ('url', url),
            ('cbir_page', 'similar'),
            ('rpt', 'imageview'),
            ('family', '0'),
            ('pornowhitelist', '1'),
            ('ipnd', '1'),
        )
    response = requests.get('https://yandex.ru/images/search',
                            headers=headers, params=params)
    print(response.url)
    root = lxml.html.fromstring(response.content)
    data = list(root.xpath('//*[@id]/@data-bem'))
    for i in data:
        i = json.loads(i)
        if "serp-item" in i:
            if "rimId" in i["serp-item"]:
                yield i["serp-item"]["rimId"]
 
 
def sJson(response, name):
    with open(f"{name}.html", "w", encoding="utf-8")as f:
        cleaner = Cleaner(style=True, scripts=True, javascript=True, inline_style=True, links=True, add_nofollow=False,
                          page_structure=True, safe_attrs_only=False)
        f.write(cleaner.clean_html(response))
 
 
all_links = []
 
 
def vldc(elem):
    try:
        requests.get(elem)
    except:
        return False
 
 
def map_append(elem):
    all_links.append(elem["iu"])
 
 
def get_from_dict(all_links, response):
    for num, i in enumerate(response["rld"]):
        infos = i["s"]
        map(map_append, infos)
 
 
def Glob_matching(src):
    prt = glob("*.*")
    if src in prt:
        return True
 
def links_yd(uri):
    if isinstance(str, type(uri)) and uri.startswith("C:") or Glob_matching(uri):
        with open(uri, "rb") as image:
            f = image.read()
            try:
                response = info(getInfoImage(load_image(f)))
                for l in response:
                    for num, i in enumerate(response["rld"]):
                        infos = i["s"]
                        for i in infos:
                            all_links.append(i["iu"])
                        if "id" in i:
                            get_from_dict(all_links, info(i["id"]))
 
                return all_links
            except:
                return None
    elif isinstance(bytes, type(uri)):
        f = uri
 
        response = info(getInfoImage(load_image(f)))
        for l in response:
            for num, i in enumerate(response["rld"]):
                infos = i["s"]
                for i in infos:
                    all_links.append(i["iu"])
                if "id" in i:
                    get_from_dict(all_links, info(i["id"]))
 
        return all_links
    else:
        response = map(info,getInfoImage(uri))
        for l in response:
            for num, i in enumerate(l["rld"]):
                infos = i["s"]
                for i in infos:
                    all_links.append(i["iu"])
                if "id" in i:
                    get_from_dict(all_links, info(i["id"]))
 
        return all_links
 
 
print(links_yd("cats"))

спасибо, очень помогло разобраться с пост запросом яндекса

спасибо, очень помогло разобраться с пост запросом яндекса

Пожалуйста