如何使用 python（最好是 BS4）从 Google Images（或 bing）中找到图像的 url？

Question

我试过在 google chrome 上使用检查元素来查找图像链接，我看到以下内容：

<img class="mimg rms_img" style="color: rgb(192, 54, 11);" height="185" width="297" alt="Image result for pizza" id="emb48403F0A" src="https://th.bing.com/th/id/OIP.uEcdCNY9nFhqWqbz4B0mFQHaEo?w=297&amp;h=185&amp;c=7&amp;o=5&amp;dpr=1.5&amp;pid=1.7" data-thhnrepbd="1" data-bm="186">

当我尝试使用以下方法搜索此元素和其他类似元素时：soup.findAll("img",{"class": "mimg rms_img"}) 我什么也没得到。

我做错了什么，还是这不是最好的解决方法？

Answer 1

要提取缩略图和原始大小URL 的图像 URL，您需要：

1. 查找所有<script>标签。
2. 通过regex匹配和提取图像 URL。
3. 迭代找到的匹配项并解码它们。

在线IDE中的代码和完整示例（很简单，慢慢看）：

import requests, lxml, re, json
from bs4 import BeautifulSoup

headers = {
    "User-Agent":
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
}

params = {
    "q": "pexels cat",
    "tbm": "isch", 
    "hl": "en",
    "ijn": "0",
}

html = requests.get("https://www.google.com/search", params=params, headers=headers)
soup = BeautifulSoup(html.text, 'lxml')


def get_images_data():

    # this steps could be refactored to a more compact
    all_script_tags = soup.select('script')

    # # https://regex101.com/r/48UZhY/4
    matched_images_data = ''.join(re.findall(r"AF_initDataCallback\(([^<]+)\);", str(all_script_tags)))
    
    # https://kodlogs.com/34776/json-decoder-jsondecodeerror-expecting-property-name-enclosed-in-double-quotes
    # if you try to json.loads() without json.dumps it will throw an error:
    # "Expecting property name enclosed in double quotes"
    matched_images_data_fix = json.dumps(matched_images_data)
    matched_images_data_json = json.loads(matched_images_data_fix)

    # https://regex101.com/r/pdZOnW/3
    matched_google_image_data = re.findall(r'\[\"GRID_STATE0\",null,\[\[1,\[0,\".*?\",(.*),\"All\",', matched_images_data_json)

    # https://regex101.com/r/NnRg27/1
    matched_google_images_thumbnails = ', '.join(
        re.findall(r'\[\"(https\:\/\/encrypted-tbn0\.gstatic\.com\/images\?.*?)\",\d+,\d+\]',
                   str(matched_google_image_data))).split(', ')

    print('Google Image Thumbnails:')  # in order
    for fixed_google_image_thumbnail in matched_google_images_thumbnails:
        # https://stackoverflow.com/a/4004439/15164646 comment by Frédéric Hamidi
        google_image_thumbnail_not_fixed = bytes(fixed_google_image_thumbnail, 'ascii').decode('unicode-escape')

        # after first decoding, Unicode characters are still present. After the second iteration, they were decoded.
        google_image_thumbnail = bytes(google_image_thumbnail_not_fixed, 'ascii').decode('unicode-escape')
        print(google_image_thumbnail)

    # removing previously matched thumbnails for easier full resolution image matches.
    removed_matched_google_images_thumbnails = re.sub(
        r'\[\"(https\:\/\/encrypted-tbn0\.gstatic\.com\/images\?.*?)\",\d+,\d+\]', '', str(matched_google_image_data))

    # https://regex101.com/r/fXjfb1/4
    # https://stackoverflow.com/a/19821774/15164646
    matched_google_full_resolution_images = re.findall(r"(?:'|,),\[\"(https:|http.*?)\",\d+,\d+\]",
                                                       removed_matched_google_images_thumbnails)

    print('\nGoogle Full Resolution Images:')  # in order
    for fixed_full_res_image in matched_google_full_resolution_images:
        # https://stackoverflow.com/a/4004439/15164646 comment by Frédéric Hamidi
        original_size_img_not_fixed = bytes(fixed_full_res_image, 'ascii').decode('unicode-escape')
        original_size_img = bytes(original_size_img_not_fixed, 'ascii').decode('unicode-escape')
        print(original_size_img)

get_images_data()

--------------
'''
Google Image Thumbnails:
https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSb48h3zks_bf6y7HnZGyGPn3s2TAHKKm_7kzxufi5nzbouJcQderHqoEoOZ4SpOuPDjfw&usqp=CAU
...

Google Full Resolution Images:
https://images.pexels.com/photos/1170986/pexels-photo-1170986.jpeg?auto=compress&cs=tinysrgb&dpr=1&w=500
...
'''

---

或者，您也可以使用 SerpApi 的Google Images API来实现。 这是一个带有免费计划的付费 API。

从本质上讲，主要区别之一是您不需要深入研究页面的源代码并通过regex提取某些内容，所需要做的就是遍历结构化 JSON 字符串并获取您想要的数据。 看看操场。

集成代码：

import os, json # json for pretty output
from serpapi import GoogleSearch


def get_google_images():
    params = {
      "api_key": os.getenv("API_KEY"),
      "engine": "google",
      "q": "pexels cat",
      "tbm": "isch"
    }

    search = GoogleSearch(params)
    results = search.get_dict()

    print(json.dumps(results['images_results'], indent=2, ensure_ascii=False))

get_google_images()

----------
'''
...
  {
    "position": 60, # img number
    "thumbnail": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcRt-tXSZMBNLLX8MhavbBNkKmjJ7wNXxtdr5Q&usqp=CAU",
    "source": "pexels.com",
    "title": "1,000+ Best Cats Videos · 100% Free Download · Pexels Stock Videos",
    "link": "https://www.pexels.com/search/videos/cats/",
    "original": "https://images.pexels.com/videos/855282/free-video-855282.jpg?auto=compress&cs=tinysrgb&dpr=1&w=500",
    "is_product": false
  }
...
'''

PS - 我写了一篇更深入的博客文章，里面有关于如何抓取Google 图片的GIF 和屏幕截图。

免责声明，我为 SerpApi 工作。

Answer 2

以下是您如何在另一个搜索引擎DuckDuckGo 中执行此操作：

search_query = 'what you want to find'
num_images = 10
driver_location = '/put/location/of/your/driver/here'

# setting up the driver
ser = Service(driver_location)
op = webdriver.ChromeOptions()
driver = webdriver.Chrome(service=ser, options=op)

# searching the query
driver.get(f'https://duckduckgo.com/?q={search_query}&kl=us-en&ia=web')

# going to Images Section
ba = driver.find_element(By.XPATH, "//a[@class='zcm__link  js-zci-link  js-zci-link--images']")
ba.click()

# getting the images URLs
for result in driver.find_elements(By.CSS_SELECTOR, '.js-images-link')[0:0+num_images]:
    imageURL = result.get_attribute('data-id')

    print(f'{imageURL}\n')

driver.quit()