Created
July 15, 2021 16:57
-
-
Save tperrelli/947fb0594c58076c0baec02248dc1d68 to your computer and use it in GitHub Desktop.
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 os | |
| import glob | |
| import json | |
| import pprint | |
| from os import path | |
| from os import listdir | |
| import requests | |
| from bs4 import BeautifulSoup | |
| links = [] | |
| linksWithAlerts = [] | |
| URL = "https://platformspfizerdocs-test.dev.pfizerstatic.io" | |
| def getPages(soup): | |
| links = [] | |
| for link in soup.findAll('a', {}): | |
| if (link.get('target') is None): | |
| title = link.get_text(strip=True) | |
| full_link = URL + link["href"] | |
| htmlFile = os.path.join('./pages', title + ".html") | |
| if (path.exists("./pages/" + title + ".html") == False): | |
| try: | |
| f = open(htmlFile, "wb") | |
| print(full_link) | |
| f.write(session.get(full_link).content) | |
| f.close() | |
| break | |
| except ValueError: | |
| print("Oops!") | |
| continue | |
| links.append(link.get('href')) | |
| return links | |
| def scrapyPages(): | |
| htmlFiles = glob.glob("./pages/*.html") | |
| print("Total pages: " + str(len(htmlFiles))) | |
| for htmlFile in htmlFiles: | |
| with open(htmlFile) as fp: | |
| soup = BeautifulSoup(fp, "html.parser") | |
| items = searchItems(soup) | |
| if (len(items) > 0): | |
| pos = htmlFile.rfind('/') | |
| item = { | |
| 'page' : htmlFile[pos:], | |
| 'alerts': len(items) | |
| } | |
| linksWithAlerts.append(item) | |
| def searchItems(soup, tag = "div", filters = {"class" : "alert"}): | |
| results = soup.find_all(tag, filters) | |
| return results | |
| urls = [] | |
| status = [] | |
| edison = [] | |
| newton = [] | |
| def scrape(site, item=None): | |
| # getting the request from url | |
| r = requests.get(site) | |
| # converting the text | |
| s = BeautifulSoup(r.text,"html.parser") | |
| if (item is not None): | |
| item['alerts'] = len(searchItems(s)) | |
| return item | |
| for i in s.find_all("a"): | |
| if ('href' in i.attrs): | |
| href = i.attrs['href'] | |
| if href.startswith("/") and href.startswith("/cdn-cgi") == False: | |
| site = URL + href | |
| if site not in urls: | |
| item = { | |
| 'url': site, | |
| 'alerts': [] | |
| } | |
| if (href.startswith("/stratus")): | |
| status.append(item) | |
| if (href.startswith("/edison")): | |
| edison.append(item) | |
| if (href.startswith("/newton")): | |
| newton.append(item) | |
| print(site) | |
| # calling it self | |
| scrape(site, item) | |
| newUrl = "https://platformspfizerdocs-test.dev.pfizerstatic.io/edison/docs" | |
| scrape(newUrl) | |
| print(edison) | |
| exit(0) | |
| # response = requests.get(URL + "/edison/docs") | |
| with requests.Session() as session : | |
| soup = BeautifulSoup(session.get(URL + "/edison/docs").content, "html.parser") | |
| getPages(soup) | |
| scrapyPages() | |
| print(linksWithAlerts) | |
| exit(0) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment