Python获取网络图片和视频的示例代码

2024-10-01 22:38:09

1.网络获取Google图像

1.1 google_images_download

Python 是一种多用途语言，广泛用于脚本编写。我们可以编写 Python 脚本来自动化日常事务。假设我们要下载具有多个搜索查询的谷歌图片。我们可以自动化该过程，而不是手动进行。

如何安装所需的模块：

pip install google_images_download

让我们看看如何编写 Python 脚本以使用 Python google_images_download 模块下载 Google 图像。

# importing google_images_download module
from google_images_download import google_images_download

# creating object
response = google_images_download.googleimagesdownload()

search_queries =
[
'The smartphone also features an in display fingerprint sensor.',
'The pop up selfie camera is placed aligning with the rear cameras.',
'''In terms of storage Vivo V15 Pro could offer
up to 6GB of RAM and 128GB of onboard storage.''',
'The smartphone could be fuelled by a 3 700mAh battery.',
]

def downloadimages(query):
	# keywords is the search query
	# format is the image file format
	# limit is the number of images to be downloaded
	# print urs is to print the image file url
	# size is the image size which can
	# be specified manually ("large, medium, icon")
	# aspect ratio denotes the height width ratio
	# of images to download. ("tall, square, wide, panoramic")
	arguments = {"keywords": query,
				"format": "jpg",
				"limit":4,
				"print_urls":True,
				"size": "medium",
				"aspect_ratio":"panoramic"}
	try:
		response.download(arguments)

	# Handling File NotFound Error
	except FileNotFoundError:
		arguments = {"keywords": query,
					"format": "jpg",
					"limit":4,
					"print_urls":True,
					"size": "medium"}

		# Providing arguments for the searched query
		try:
			# Downloading the photos based
			# on the given arguments
			response.download(arguments)
		except:
			pass

# Driver Code
for query in search_queries:
	downloadimages(query)
	print()

输出

注意：由于下载错误，部分图片无法打开。

1.2 BeautifulSoup

import re
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse
import os
f = open("images_flowers.txt", "w")
res=[]
def download_google(url):
    #url = 'https://www.google.com/search?q=flowers&sxsrf=ALeKk00uvzQYZFJo03cukIcMS-pcmmbuRQ:1589501547816&source=lnms&tbm=isch&sa=X&ved=2ahUKEwjEm4LZyrTpAhWjhHIEHewPD1MQ_AUoAXoECBAQAw&biw=1440&bih=740'
    page = requests.get(url).text
    soup = BeautifulSoup(page, 'html.parser')

    for raw_img in soup.find_all('img'):
        link = raw_img.get('src')
        res.append(link)
        if link:
            f.write(link +"\n")

download_google('https://www.google.com/search?q=flowers&sxsrf=ALeKk00uvzQYZFJo03cukIcMS-pcmmbuRQ:1589501547816&source=lnms&tbm=isch&sa=X&ved=2ahUKEwjEm4LZyrTpAhWjhHIEHewPD1MQ_AUoAXoECBAQAw&biw=1440&bih=740')

f.close()

1.3 pyimagesearch

感谢 Adrian Rosebrock 编写此代码并将其公开。

# USAGE
# python download_images.py --urls urls.txt --output images/santa

# import the necessary packages
from imutils import paths
import argparse
import requests
import cv2
import os

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-u", "--urls", required=True,
	help="path to file containing image URLs")
ap.add_argument("-o", "--output", required=True,
	help="path to output directory of images")
args = vars(ap.parse_args())

# grab the list of URLs from the input file, then initialize the
# total number of images downloaded thus far
rows = open(args["urls"]).read().strip().split("\n")
total = 0

# loop the URLs
for url in rows:
	try:
		# try to download the image
		r = requests.get(url, timeout=60)

		# save the image to disk
		p = os.path.sep.join([args["output"], "{}.jpg".format(
			str(total).zfill(8))])
		f = open(p, "wb")
		f.write(r.content)
		f.close()

		# update the counter
		print("[INFO] downloaded: {}".format(p))
		total += 1

	# handle if any exceptions are thrown during the download process
	except:
		print("[INFO] error downloading {}...skipping".format(p))

# loop over the image paths we just downloaded
for imagePath in paths.list_images(args["output"]):
	# initialize if the image should be deleted or not
	delete = False

	# try to load the image
	try:
		image = cv2.imread(imagePath)

		# if the image is `None` then we could not properly load it
		# from disk, so delete it
		if image is None:
			print("None")
			delete = True

	# if OpenCV cannot load the image then the image is likely
	# corrupt so we should delete it
	except:
		print("Except")
		delete = True

	# check to see if the image should be deleted
	if delete:
		print("[INFO] deleting {}".format(imagePath))
		os.remove(imagePath)

2.网络获取Youtube视频