-
python入门教程之Python妹子图爬虫实战项目【新手必学】(2)
本站最新发布 Python从入门到精通|Python基础教程
试听地址 https://www.xin3721.com/eschool/pythonxin3721/
= webdriver.Chrome(chrome_path, chrome_options=chrome_options) for girl_url in self.girl_urls: driver.get(girl_url) time.sleep(3) driver.find_element_by_xpath('//em[@class="ch all"]').click() time.sleep(3) html = driver.page_source selector = etree.HTML(html) self.girl_name = selector.xpath('//div[@class="article"]/h2/text()')[0] self.pic_urls = selector.xpath('//div[@id="content"]/img/@data-img') try: self.download_pic() except Exception as e: print("{}保存失败".format(self.girl_name) + str(e)) # 下载图片的方法 def download_pic(self): try: os.mkdir(PICTURES_PATH) except: pass girl_path = PICTURES_PATH + self.girl_name try: os.mkdir(girl_path) except Exception as e: print("{}已存在".format(self.girl_name)) img_name = 0 for pic_url in self.pic_urls: img_name += 1 img_data = requests.get(pic_url, headers=headers) pic_path = girl_path + '/' + str(img_name)+'.jpg' if os.path.isfile(pic_path): print("{}第{}张已存在".format(self.girl_name, img_name)) pass else: with open(pic_path, 'wb')as f: f.write(img_data.content) print("正在保存{}第{}张".format(self.girl_name, img_name)) f.close() return # 爬虫的启动方法，按照爬虫逻辑依次调用方法 def start(self): self.get_page_urls() self.get_girl_urls() self.get_pic_urls() # main函数 if __name__ == '__main__': page_num = input("请输入页码:") mmjpg_spider = Spider(page_num) mmjpg_spider.start()
试听地址 https://www.xin3721.com/eschool/pythonxin3721/
= webdriver.Chrome(chrome_path, chrome_options=chrome_options) for girl_url in self.girl_urls: driver.get(girl_url) time.sleep(3) driver.find_element_by_xpath('//em[@class="ch all"]').click() time.sleep(3) html = driver.page_source selector = etree.HTML(html) self.girl_name = selector.xpath('//div[@class="article"]/h2/text()')[0] self.pic_urls = selector.xpath('//div[@id="content"]/img/@data-img') try: self.download_pic() except Exception as e: print("{}保存失败".format(self.girl_name) + str(e)) # 下载图片的方法 def download_pic(self): try: os.mkdir(PICTURES_PATH) except: pass girl_path = PICTURES_PATH + self.girl_name try: os.mkdir(girl_path) except Exception as e: print("{}已存在".format(self.girl_name)) img_name = 0 for pic_url in self.pic_urls: img_name += 1 img_data = requests.get(pic_url, headers=headers) pic_path = girl_path + '/' + str(img_name)+'.jpg' if os.path.isfile(pic_path): print("{}第{}张已存在".format(self.girl_name, img_name)) pass else: with open(pic_path, 'wb')as f: f.write(img_data.content) print("正在保存{}第{}张".format(self.girl_name, img_name)) f.close() return # 爬虫的启动方法，按照爬虫逻辑依次调用方法 def start(self): self.get_page_urls() self.get_girl_urls() self.get_pic_urls() # main函数 if __name__ == '__main__': page_num = input("请输入页码:") mmjpg_spider = Spider(page_num) mmjpg_spider.start()
现在你就可以慢慢爬妹子图了，注意最好在请求的时候time.sleep()几秒钟，请求太频繁的话，也有一定的概率被识别为爬虫的，虽然我并没有实验，但是我也建议你这么做，因为，过于频繁的请求还是会让服务器吃不消，看在人家的图片这么良心的情况下，爬慢点......另外要注意：很多人学Python过程中会遇到各种烦恼问题，没有人解答容易放弃。
