Created
March 30, 2022 18:31
-
-
Save thisismattmiller/9849181e08e068a59013d25e5bba9403 to your computer and use it in GitHub Desktop.
Code for https://youtu.be/pwnIcJ9p2C4 Web scraping with selenium
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
import glob | |
from bs4 import BeautifulSoup | |
import json | |
all_files = list(glob.glob('html/*.html')) | |
all_data = [] | |
for file_name in all_files: | |
with open(file_name) as infile: | |
html = infile.read() | |
print(file_name) | |
soup = BeautifulSoup(html,'html.parser') | |
for row in range(0,12): | |
for left_or_right in ['Left', 'Right']: | |
data = {} | |
for field in ['CommonNameRow', 'TypeRow','ZoneRow','HeightRow','SynonymRow']: | |
use_id = f"MainContentPlaceHolder_SearchResultsList_SearchResultControl{left_or_right}_{row}_{field}_{row}" | |
element = soup.find('div', {'id': use_id}) | |
if element != None: | |
data[field] = element.get_text().strip() | |
use_id = f"MainContentPlaceHolder_SearchResultsList_SearchResultControl{left_or_right}_{row}_TaxonHTMLName_{row}" | |
element = soup.find('a', {'id': use_id}) | |
data['plant_link'] = 'https://www.missouribotanicalgarden.org' + element['href'] | |
data['taxon_name']= element.get_text().strip() | |
all_data.append(data) | |
json.dump(all_data,open('all_data.json','w'),indent=2) | |
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
from selenium import webdriver | |
import glob | |
all_existing_html_files = list(glob.glob('html/*.html')) | |
driver = webdriver.Chrome(executable_path="./chromedriver") | |
driver.get('https://www.missouribotanicalgarden.org/PlantFinder/PlantFinderProfileResults.aspx') | |
js_command = """ | |
document.getElementById('MainContentPlaceHolder_pagingUserControlTop_RecordsPerPage').value = 24; | |
document.getElementById('MainContentPlaceHolder_pagingUserControlTop_RecordsPerPage').dispatchEvent( new Event('change') ); | |
""" | |
driver.execute_script(js_command) | |
for page in range(1,357): | |
filename = f'html/source_{page}.html' | |
if filename in all_existing_html_files: | |
print('Skipping page:',page) | |
continue | |
print('Doing page',page) | |
js_command = f""" | |
document.getElementById('MainContentPlaceHolder_pagingUserControlTop_pageTextBox').value = {page}; | |
document.getElementById('MainContentPlaceHolder_pagingUserControlTop_pageTextBox').dispatchEvent( new KeyboardEvent('keypress', {{ key: 'Enter', code: 'Enter', keyCode: 13 }} ) ) | |
""" | |
driver.execute_script(js_command) | |
html_source_code = driver.page_source | |
with open(filename,'w') as outfile: | |
outfile.write(html_source_code) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment