亲宝软件园·资讯

展开

Python获取图片 视频

求则得之,舍则失之 人气:2

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

如何安装所需的模块:

pip install pytube3
import cv2
from collections import defaultdict

import matplotlib.pyplot as plt 
import numpy as np
import pandas as pd
import warnings
from pytube import YouTube


warnings.filterwarnings('ignore')

video = YouTube('https://www.youtube.com/watch?v=GTkU4qj6v7g')
# print(video.streams.all())
print(video.streams.filter(file_extension = "mp4").all())
# [<Stream: itag="18" mime_type="video/mp4" res="360p" fps="30fps" vcodec="avc1.42001E" acodec="mp4a.40.2" progressive="True" type="video">,
# <Stream: itag="22" mime_type="video/mp4" res="720p" fps="30fps" vcodec="avc1.64001F" acodec="mp4a.40.2" progressive="True" type="video">,
# <Stream: itag="137" mime_type="video/mp4" res="1080p" fps="30fps" vcodec="avc1.64001f" progressive="False" type="video">,
# <Stream: itag="136" mime_type="video/mp4" res="720p" fps="30fps" vcodec="avc1.4d401e" progressive="False" type="video">,
# <Stream: itag="135" mime_type="video/mp4" res="480p" fps="30fps" vcodec="avc1.4d4015" progressive="False" type="video">,
# <Stream: itag="134" mime_type="video/mp4" res="360p" fps="30fps" vcodec="avc1.4d400d" progressive="False" type="video">,
# <Stream: itag="133" mime_type="video/mp4" res="240p" fps="30fps" vcodec="avc1.4d400c" progressive="False" type="video">,
# <Stream: itag="160" mime_type="video/mp4" res="144p" fps="30fps" vcodec="avc1.4d400b" progressive="False" type="video">,
# <Stream: itag="140" mime_type="audio/mp4" abr="128kbps" acodec="mp4a.40.2" progressive="False" type="audio">]

# 为要下载的视频的分辨率使用适当的 itag。如果您需要高分辨率视频下载,
# 请在以下步骤中选择最高分辨率的 itag 进行下载
print(video.streams.get_by_itag(137).download())
# '/Users/sapnasharma/Documents/github/video_clips/Akshay Kumars Fitness Mantras for a Fit India  GOQii Play Exclusive.mp4'
video_path = video.title
print(video_path)
# "Akshay Kumar's Fitness Mantras for a Fit India | GOQii Play Exclusive"

# 视频标题在名称之间添加了一个管道,因此实际名称已损坏。我稍后会修复这个错误,
# 现在我们可以直接粘贴视频的名字来达到我们的目的。
video_path = "Akshay Kumars Fitness Mantras for a Fit India  GOQii Play Exclusive.mp4"
# Video Capture Using OpenCV
cap = cv2.VideoCapture(video_path)

frame_cnt = int(cap.get(cv2.cv2.CAP_PROP_FRAME_COUNT))
fps = cap.get(cv2.CAP_PROP_FPS)

print('Frames in video: ', frame_cnt)
print(f"Frames per sec: {fps}")
# Frames in video:  34249
# Frames per sec: 25.0
# (1)要获取整个视频的帧,请使用下面的代码块。
# Use this for accessing the entire video
index = 1

for x in range(frame_cnt):
    ret, frame = cap.read()    
    if not ret:
        break
        
    # Get frame timestamp
    frame_timestamp = cap.get(cv2.CAP_PROP_POS_MSEC)
    
    # fetch frame every sec
    if frame_timestamp >= (index * 1000.0): # change the value from 1000 to anyother value if not needed per second
        index = index + 2   # decides the freq. of frames to be saved
        print(f"++ {index}")
        cv2.imwrite(f"images/cv_{index}.png", frame)   
    if cv2.waitKey(20) & 0xFF == ord('q'):
        break
        
cap.release()
cv2.destroyAllWindows()


# (2)要获取特定持续时间之间的帧,请使用以下代码块。
# Use this in case frames are to be fetched within a certain time frame
# frame_timestamp will be calculated as fps*time*1000 and set the starting index accordingly
index = 1560

for x in range(frame_cnt):
    ret, frame = cap.read()
    
    if not ret:
        break
        
    # Get frame timestamp
    frame_timestamp = cap.get(cv2.CAP_PROP_POS_MSEC)
    if frame_timestamp >= 1560000.0 and frame_timestamp <= 1800000.0 :
        # fetch frame every sec
        if frame_timestamp >= (index * 1000.0):
            index = index + 4   # decides the freq. of frames to be saved
            print(f"++ {index}")
            
            
            cv2.imwrite(f"images/cv_{index}.png", frame)
    
    
    if cv2.waitKey(20) & 0xFF == ord('q'):
        break
        
cap.release()
cv2.destroyAllWindows()

加载全部内容

相关教程
猜你喜欢
用户评论