| Here because I don't want the gist to be titled .gitignore lol |
| chromedriver.exe | |
| *.jpeg | |
| *.png | |
| *.jpg |
| Service | Status |
|---|---|
| Netflix | Implemented |
| Hulu | Partially* |
| Amazon | Implemented |
syntax:
py -3 <service>.py <url>
ie
py -3 netflix.py https://www.netflix.com/title/80217478
which downloads this background and this logo
*Cannot Download Hulu Backgrounds, and certain metadata for TV Shows are unavailable.
| #Created by davFaithid on Friday 5/29/2020 | |
| #Please credit me if you use this in another project | |
| #Thank you | |
| import sys, os, time | |
| from urllib.request import urlopen, urlretrieve, Request | |
| import re | |
| from bs4 import BeautifulSoup | |
| from selenium import webdriver | |
| from os import path | |
| if path.exists("chromedriver.exe") == False: | |
| print("chromedriver needed in folder with scripts") | |
| import webbrowser | |
| webbrowser.open("https://sites.google.com/a/chromium.org/chromedriver/downloads") | |
| sys.exit() | |
| else: | |
| pass | |
| url = str(sys.argv[1]).strip() | |
| options = webdriver.ChromeOptions() | |
| options.add_argument('--ignore-certificate-errors') | |
| #Causes the site to crash | |
| #options.add_argument('--incognito') | |
| #options.add_argument('--headless') | |
| driver = webdriver.Chrome(options=options) | |
| driver.get(url) | |
| html_page = driver.page_source | |
| soup = BeautifulSoup(html_page, features="html.parser") | |
| year = str(soup.find("span", {"data-automation-id":"release-year-badge"}).text) | |
| rating = str(soup.find("span", {"data-automation-id":"rating-badge"}).text).replace('<span class="">','').replace('</span>','') | |
| description = str(soup.find("div", {"class":"_3qsVvm _1wxob_"}).text) | |
| name = str(soup.find("h1", {"data-automation-id":"title"}).text) | |
| print(""" | |
| Title: """,name,""" | |
| Rating: """,rating,""" | |
| Year: """,year,""" | |
| Description: | |
| """+description,""" | |
| """) | |
| name = re.sub('[^A-Za-z0-9 ]+', '', name) | |
| burl = str(soup.find("img", {"class":"_1fk85K"}).get("src")) | |
| print("Downloading background @",burl) | |
| background = str(str(name) + "-landscape.jpeg") | |
| urlretrieve(burl, background) | |
| driver.close() | |
| driver.quit() | |
| sys.exit() |
| #Created by davFaithid on Sunday 5/31/2020 | |
| #Please credit me if you use this in another project | |
| #Thank you | |
| import sys, os, time | |
| from urllib.request import urlopen, urlretrieve, Request | |
| import re | |
| from bs4 import BeautifulSoup | |
| url = str(sys.argv[1]).strip() | |
| req = Request( | |
| url, | |
| data=None, | |
| headers={ | |
| 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0' | |
| } | |
| ) | |
| html_page = urlopen(req) | |
| soup = BeautifulSoup(html_page, features="html.parser") | |
| details = str(soup.find("div", {"class":"DetailEntityMasthead__tags"}).text) | |
| description = str(soup.find("p", {"class":"DetailEntityMasthead__description"}).text) | |
| #name = str(soup.find("img", {"role":"presentation"}).get("alt")) | |
| try: | |
| name = str(soup.find("span", {"class":"DetailEntityMasthead__title__text"}).text) | |
| except AttributeError: | |
| name = "Name is unavailable" | |
| print(""" | |
| Title: """,name,""" | |
| Details: """,details,""" | |
| Description: | |
| """+description,""" | |
| """) | |
| name = re.sub('[^A-Za-z0-9 ]+', '', name) | |
| """ | |
| Need to find how to get background | |
| print("Downloading background @",burl) | |
| background = str(str(name) + "-landscape.jpeg") | |
| urlretrieve(burl, background) | |
| """ | |
| poster = str(str(name) + "-poster.jpeg") | |
| purl = soup.find("img", {"class":"DetailEntityMasthead__vertical-tile-img"}).get("src") | |
| print("Downloading poster @",purl) | |
| urlretrieve(purl, poster) | |
| logo = str(str(name) + "-logo.png") | |
| try: | |
| lurl = soup.find("img", {"role":"presentation","srcset":re.compile('&size=690x138|max&format=png 2x')}).get("src") | |
| print("Downloading logo @",lurl) | |
| urlretrieve(lurl, logo) | |
| except AttributeError: | |
| print("Logo not available") | |
| """ | |
| ###This also works =) | |
| script = soup.find("script", {"type":"application/ld+json"}) | |
| print(script) | |
| if script: | |
| import json | |
| jsondata = json.loads(script.text) | |
| url2 = jsondata["image"] | |
| urlretrieve(url2, 'pic.jpg') | |
| """ |
| #Created by davFaithid on Saturday 5/23/2020 | |
| #Please credit me if you use this in another project | |
| #Thank you | |
| import sys, os, time | |
| from urllib.request import urlopen, urlretrieve, Request | |
| import re | |
| from bs4 import BeautifulSoup | |
| url = str(sys.argv[1]).strip() | |
| req = Request( | |
| url, | |
| data=None, | |
| headers={ | |
| 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0' | |
| } | |
| ) | |
| html_page = urlopen(req) | |
| links = [] | |
| soup = BeautifulSoup(html_page, features="html.parser") | |
| year = str(soup.find("span", {"class":"title-info-metadata-item item-year"}).text) | |
| rating = str(soup.find("span", {"class":"maturity-number"}).text) | |
| description = str(soup.find("div", {"class":"title-info-synopsis"}).text) | |
| name = str(soup.find("h1", {"class":"title-title"}).text) | |
| print(""" | |
| Title: """,name,""" | |
| Rating: """,rating,""" | |
| Year: """,year,""" | |
| Description: | |
| """+description,""" | |
| """) | |
| name = re.sub('[^A-Za-z0-9 ]+', '', name) | |
| for mydivs in soup.findAll("div", {"class": "hero-image hero-image-desktop"}): | |
| links.append(mydivs.get('style')) | |
| burl = str(links[0]).replace('display:none;background-image:url("', '').replace('")','') | |
| print("Downloading background @",burl) | |
| background = str(str(name) + "-landscape.jpeg") | |
| urlretrieve(burl, background) | |
| logo = str(str(name) + "-logo.jpeg") | |
| lurl = soup.find("img", {"class":"logo", "data-uia":"title-logo"}).get("src") | |
| print("Downloading logo @",lurl) | |
| urlretrieve(lurl, logo) | |
| """ | |
| ###This also works =) | |
| script = soup.find("script", {"type":"application/ld+json"}) | |
| print(script) | |
| if script: | |
| import json | |
| jsondata = json.loads(script.text) | |
| url2 = jsondata["image"] | |
| urlretrieve(url2, 'pic.jpg') | |
| """ |
Hey. I think the netflix one is no longer working sadly.
~\Code\ninx> py -3 n.py https://www.netflix.com/title/80217478
Traceback (most recent call last):
File "C:\Users\Robyn\Code\ninx\n.py", line 21, in <module>
year = str(soup.find("span", {"class":"title-info-metadata-item item-year"}).text)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'text'
~\Code\ninx> ```
Example: