[PyMemos - WEB Scratching] #python #memo #web #requests

beautiful_soup4.py

import bs4

res = requests.get('https://www.amazon.com/Automate-Boring-Stuff-Python-Programming/dp/1593275994')
res = requests.get('https://www.google.com')
res.raise_for_status()

soup = bs4.BeautifulSoup(res.text, 'html.parser')
elems = soup.select('#gbw > div > div > div.gb_oe.gb_R.gb_Lg.gb_Bg > div:nth-child(2) > a')
# print(elems[0].text.strip())
print(elems)

selenium_webdriver.py

from selenium import webdriver
# chromepath = r'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe'
# browser = webdriver.Chrome(chromepath)
browser = webdriver.Firefox()
browser.get('https://automatetheboringstuff.com/')
elem = browser.find_element_by_css_selector('.main > div:nth-child(1) > h1:nth-child(1)')
print(elem.text)
# elem.click() #simulate clicking on lement
# elems = browser.find_elements_by_css_selector('p')
# searchElem = browser.find_element_by_css_selector('.search-field')
# searchElem.send_keys('zophie')
# searchElem.submit()
# browser.back()
# browser.forward()
# browser.refresh()
# browser.quit()

simple_request.py

import requests

res = requests.get('https://automatetheboringstuff.com/files/rj.txt')
# badres = requests.get('https://automatetheboringstuff.com/files/jkhbvwabf')
# print(res.status_code) #200=OK
# print(res.text[:500])
# badres.raise_for_status()

playFile = open('RomeAndJuliet.txt', 'wb')
for chunk in res.iter_content(100000):
    playFile.write(chunk)
playFile.close()