欢迎！我白天是个邮递员，晚上就是个有抱负的演员。这是我的网站。我住在天朝的帝都，有条叫做Jack的狗。
python百度图片搜索API源码，一段简单的图片爬虫程序。通过输入关键词，在百度图片中搜索相关图片，并返回一张随机的图片。
代码使用Flask框架搭建了一个简单的Web应用，将用户输入的关键词作为参数传递给爬虫程序，然后从百度图片中获取相关图片的URL并随机选择一张返回给用户。
用户可以通过访问Web应用的首页，在输入框中输入关键词进行搜索。如果找到相关图片，则会跳转到图片的URL，如果未找到图片，则会显示无法正常查找的提示信息。
将代码发布到服务器上，就可以用Markdown格式![image]服务器域名/?word=关键字来显示搜索的图片。
import argparseimport osimport reimport sysimport urllibimport jsonimport socketimport urllib.requestimport urllib.parseimport urllib.errorimport random # 设置超时import time from flask import Flask, redirect, request, make_responseimport random timeout = 5socket.setdefaulttimeout(timeout) import sslssl._create_default_https_context = ssl._create_unverified_context class Crawler: # 睡眠时长 __time_sleep = 0.1 __amount = 0 __start_amount = 0 __counter = 0 headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0', 'Cookie': ''} __per_page = 30 # 获取图片url内容等 # t 下载图片时间间隔 def __init__(self, t=0.1): self.time_sleep = t # 获取后缀名 @staticmethod def get_suffix(name): m = re.search(r'\.[^\.]*$', name) if m.group(0) and len(m.group(0)) <= 5: return m.group(0) else: return '.jpeg' @staticmethod def handle_baidu_cookie(original_cookie, cookies): """ :param string original_cookie: :param list cookies: :return string: """ if not cookies: return original_cookie result = original_cookie for cookie in cookies: result += cookie.split(';')[0] + ';' result.rstrip(';') return result # 开始获取 def get_images(self, word): search = urllib.parse.quote(word) pn = self.__start_amount image_urls = [] while pn < self.__amount: url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord=%s&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=&hd=&latest=©right=&word=%s&s=&se=&tab=&width=&height=&face=0&istype=2&qc=&nc=1&fr=&expermode=&force=&pn=%s&rn=%d&gsm=1e&1594447993172=' % ( search, search, str(pn), self.__per_page) try: time.sleep(self.time_sleep) req = urllib.request.Request(url=url, headers=self.headers) page = urllib.request.urlopen(req) self.headers['Cookie'] = self.handle_baidu_cookie(self.headers['Cookie'], page.info().get_all('Set-Cookie')) rsp = page.read() page.close() except UnicodeDecodeError as e: print(e) print('-----UnicodeDecodeErrorurl:', url) except urllib.error.URLError as e: print(e) print("-----urlErrorurl:", url) except socket.timeout as e: print(e) print("-----socket timout:", url) else: rsp_data = json.loads(rsp, strict=False, object_hook=lambda d: {k: urllib.parse.unquote(v) if isinstance(v, str) else v for k, v in d.items()}) if 'data' not in rsp_data: continue else: for image_info in rsp_data['data']: if 'thumbURL' in image_info: thumb_url = image_info['thumbURL'] image_urls.append(thumb_url) pn += self.__per_page return image_urls def start(self, word): self.__per_page = 30 self.__start_amount = 0 self.__amount = self.__per_page return self.get_images(word) app = Flask(__name__) @app.route("/")def index(): word = request.args.get('word') if word: crawler = Crawler(0.1) # 抓取延迟为 0.1 image_urls = crawler.start(word) if image_urls: image_url = random.choice(image_urls) # 返回图片的 URL return redirect(image_url) return """ <!DOCTYPE html> <html> <body> <h1>无法正常查找</h1> </body> </html> """ if __name__ == '__main__': app.run()
