-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
9 changed files
with
737 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,194 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"## 헬멧 300~400개 " | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 2, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"from selenium import webdriver\n", | ||
"from selenium.webdriver.common.keys import Keys\n", | ||
"import time\n", | ||
"import urllib.request\n", | ||
"\n", | ||
"driver = webdriver.Chrome('C:/Temp/chromedriver')\n", | ||
"driver.get(\"https://www.google.co.kr/imghp?hl=ko&ogbl\")\n", | ||
"elem = driver.find_element_by_name(\"q\")\n", | ||
"elem.send_keys(\"자전거 헬멧 사이트\")\n", | ||
"elem.send_keys(Keys.RETURN)\n", | ||
" \n", | ||
"SCROLL_PAUSE_TIME = 1\n", | ||
" \n", | ||
"last_height = driver.execute_script(\"return document.body.scrollHeight\")\n", | ||
" \n", | ||
"while True:\n", | ||
" driver.execute_script(\"window.scrollTo(0, document.body.scrollHeight);\")\n", | ||
" \n", | ||
" time.sleep(SCROLL_PAUSE_TIME)\n", | ||
" \n", | ||
" new_height = driver.execute_script(\"return document.body.scrollHeight\")\n", | ||
" if new_height == last_height:\n", | ||
" try:\n", | ||
" driver.find_element_by_css_selector(\".mye4qd\").click()\n", | ||
" except:\n", | ||
" break\n", | ||
" last_height = new_height\n", | ||
" \n", | ||
"images = driver.find_elements_by_css_selector(\".rg_i.Q4LuWd\")\n", | ||
"count = 1\n", | ||
"for image in images:\n", | ||
" try: \n", | ||
" image.click()\n", | ||
" time.sleep(2)\n", | ||
" imgUrl = driver.find_element_by_xpath('/html/body/div[2]/c-wiz/div[3]/div[2]/div[3]/div/div/div[3]/div[2]/c-wiz/div/div[1]/div[1]/div/div[2]/a/img').get_attribute(\"src\")\n", | ||
" urllib.request.urlretrieve(imgUrl, str(count) + \".jpg\")\n", | ||
" count = count + 1\n", | ||
" except:\n", | ||
" pass\n", | ||
" \n", | ||
"driver.close()" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 3, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"from selenium import webdriver\n", | ||
"from selenium.webdriver.common.keys import Keys\n", | ||
"import time\n", | ||
"import urllib.request\n", | ||
"\n", | ||
"driver = webdriver.Chrome('C:/Temp/chromedriver')\n", | ||
"driver.get(\"https://www.google.co.kr/imghp?hl=ko&ogbl\")\n", | ||
"elem = driver.find_element_by_name(\"q\")\n", | ||
"elem.send_keys(\"wearing bicycle helmet\")\n", | ||
"elem.send_keys(Keys.RETURN)\n", | ||
" \n", | ||
"SCROLL_PAUSE_TIME = 1\n", | ||
" \n", | ||
"last_height = driver.execute_script(\"return document.body.scrollHeight\")\n", | ||
" \n", | ||
"while True:\n", | ||
" driver.execute_script(\"window.scrollTo(0, document.body.scrollHeight);\")\n", | ||
" \n", | ||
" time.sleep(SCROLL_PAUSE_TIME)\n", | ||
" \n", | ||
" new_height = driver.execute_script(\"return document.body.scrollHeight\")\n", | ||
" if new_height == last_height:\n", | ||
" try:\n", | ||
" driver.find_element_by_css_selector(\".mye4qd\").click()\n", | ||
" except:\n", | ||
" break\n", | ||
" last_height = new_height\n", | ||
" \n", | ||
"images = driver.find_elements_by_css_selector(\".rg_i.Q4LuWd\")\n", | ||
"count = 156\n", | ||
"for image in images:\n", | ||
" try: \n", | ||
" image.click()\n", | ||
" time.sleep(2)\n", | ||
" imgUrl = driver.find_element_by_xpath('/html/body/div[2]/c-wiz/div[3]/div[2]/div[3]/div/div/div[3]/div[2]/c-wiz/div/div[1]/div[1]/div/div[2]/a/img').get_attribute(\"src\")\n", | ||
" urllib.request.urlretrieve(imgUrl, str(count) + \".jpg\")\n", | ||
" count = count + 1\n", | ||
" except:\n", | ||
" pass\n", | ||
" \n", | ||
"driver.close()" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 5, | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"ename": "NoSuchWindowException", | ||
"evalue": "Message: no such window: target window already closed\nfrom unknown error: web view not found\n (Session info: chrome=90.0.4430.93)\n", | ||
"output_type": "error", | ||
"traceback": [ | ||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", | ||
"\u001b[1;31mNoSuchWindowException\u001b[0m Traceback (most recent call last)", | ||
"\u001b[1;32m<ipython-input-5-8f98a753c94d>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 39\u001b[0m \u001b[1;32mpass\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 40\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 41\u001b[1;33m \u001b[0mdriver\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", | ||
"\u001b[1;32m~\\anaconda3\\envs\\pydatavenv\\lib\\site-packages\\selenium\\webdriver\\remote\\webdriver.py\u001b[0m in \u001b[0;36mclose\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 686\u001b[0m \u001b[0mdriver\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 687\u001b[0m \"\"\"\n\u001b[1;32m--> 688\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mCommand\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mCLOSE\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 689\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 690\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mquit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", | ||
"\u001b[1;32m~\\anaconda3\\envs\\pydatavenv\\lib\\site-packages\\selenium\\webdriver\\remote\\webdriver.py\u001b[0m in \u001b[0;36mexecute\u001b[1;34m(self, driver_command, params)\u001b[0m\n\u001b[0;32m 319\u001b[0m \u001b[0mresponse\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcommand_executor\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mexecute\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdriver_command\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 320\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mresponse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 321\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0merror_handler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcheck_response\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 322\u001b[0m response['value'] = self._unwrap_value(\n\u001b[0;32m 323\u001b[0m response.get('value', None))\n", | ||
"\u001b[1;32m~\\anaconda3\\envs\\pydatavenv\\lib\\site-packages\\selenium\\webdriver\\remote\\errorhandler.py\u001b[0m in \u001b[0;36mcheck_response\u001b[1;34m(self, response)\u001b[0m\n\u001b[0;32m 240\u001b[0m \u001b[0malert_text\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'alert'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'text'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 241\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0malert_text\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 242\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mexception_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmessage\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mscreen\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstacktrace\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 243\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 244\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_value_or_default\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdefault\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", | ||
"\u001b[1;31mNoSuchWindowException\u001b[0m: Message: no such window: target window already closed\nfrom unknown error: web view not found\n (Session info: chrome=90.0.4430.93)\n" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"from selenium import webdriver\n", | ||
"from selenium.webdriver.common.keys import Keys\n", | ||
"import time\n", | ||
"import urllib.request\n", | ||
"\n", | ||
"driver = webdriver.Chrome('C:/Temp/chromedriver')\n", | ||
"driver.get(\"https://www.google.co.kr/imghp?hl=ko&ogbl\")\n", | ||
"elem = driver.find_element_by_name(\"q\")\n", | ||
"elem.send_keys(\"bike helmet\")\n", | ||
"elem.send_keys(Keys.RETURN)\n", | ||
" \n", | ||
"SCROLL_PAUSE_TIME = 1\n", | ||
" \n", | ||
"last_height = driver.execute_script(\"return document.body.scrollHeight\")\n", | ||
" \n", | ||
"while True:\n", | ||
" driver.execute_script(\"window.scrollTo(0, document.body.scrollHeight);\")\n", | ||
" \n", | ||
" time.sleep(SCROLL_PAUSE_TIME)\n", | ||
" \n", | ||
" new_height = driver.execute_script(\"return document.body.scrollHeight\")\n", | ||
" if new_height == last_height:\n", | ||
" try:\n", | ||
" driver.find_element_by_css_selector(\".mye4qd\").click()\n", | ||
" except:\n", | ||
" break\n", | ||
" last_height = new_height\n", | ||
" \n", | ||
"images = driver.find_elements_by_css_selector(\".rg_i.Q4LuWd\")\n", | ||
"count = 609\n", | ||
"for image in images:\n", | ||
" try: \n", | ||
" image.click()\n", | ||
" time.sleep(2)\n", | ||
" imgUrl = driver.find_element_by_xpath('/html/body/div[2]/c-wiz/div[3]/div[2]/div[3]/div/div/div[3]/div[2]/c-wiz/div/div[1]/div[1]/div/div[2]/a/img').get_attribute(\"src\")\n", | ||
" urllib.request.urlretrieve(imgUrl, str(count) + \".jpg\")\n", | ||
" count = count + 1\n", | ||
" except:\n", | ||
" pass\n", | ||
" \n", | ||
"driver.close()" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"kernelspec": { | ||
"display_name": "pydatavenv", | ||
"language": "python", | ||
"name": "pydatavenv" | ||
}, | ||
"language_info": { | ||
"codemirror_mode": { | ||
"name": "ipython", | ||
"version": 3 | ||
}, | ||
"file_extension": ".py", | ||
"mimetype": "text/x-python", | ||
"name": "python", | ||
"nbconvert_exporter": "python", | ||
"pygments_lexer": "ipython3", | ||
"version": "3.8.8" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 4 | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.