Created
April 14, 2019 13:03
-
-
Save K-Wu/35423b4d806e318d811420bdead2c13f to your computer and use it in GitHub Desktop.
Extract Intel Compiler Options and Sort Out to Xlsx
This file contains hidden or 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 bs4 import BeautifulSoup | |
import requests | |
import xlsxwriter | |
import bs4 | |
def get_options_url(): | |
BASEURL = "https://software.intel.com" | |
URL = "https://software.intel.com/en-us/cpp-compiler-developer-guide-and-reference-alphabetical-list-of-compiler-options" | |
response = requests.get(URL) | |
soup = BeautifulSoup(response.content, 'html.parser') | |
entries = soup.find_all("tr") | |
options_descriptions_urls = [[item.text for item in entry.children if type(item)!=bs4.element.NavigableString]+[BASEURL+list(entry.children)[0].find_all("a")[0].attrs["href"]] for entry in entries] | |
#csv_lines = [["linux", "windows", "default", "default description"]] | |
csv_lines = [["linux", "windows"]] | |
for option_description_url in options_descriptions_urls: | |
linux_options, windows_options, defualt_option, default_description = get_windows_linux_available_single_option(option_description_url[2]) | |
#for idx in range(len(linux_options)): | |
# if idx <len(linux_options): | |
# csv_lines.append([linux_options[idx], windows_options[idx]]) | |
linux_options=linux_options+['None' for idx in range(len(windows_options)-len(linux_options))] | |
windows_options=windows_options+['None' for idx in range(len(linux_options)-len(windows_options))] | |
csv_lines.extend([list(item) for item in list(zip(linux_options,windows_options))]) | |
workbook = xlsxwriter.Workbook('options.xlsx') | |
worksheet = workbook.add_worksheet() | |
for row_idx, line in enumerate(csv_lines): | |
for col_idx, item in enumerate(line): | |
worksheet.write(row_idx, col_idx, item) | |
workbook.close() | |
pass | |
def get_windows_linux_available_single_option(url): | |
response = requests.get(url) | |
soup = BeautifulSoup(response.content, 'html.parser') | |
entries=soup.find_all("td", class_="noborder") | |
options = [[item.text for item in entry.children if type(item)!=bs4.element.NavigableString] for entry in entries] | |
if len(entries)!=6: | |
print("FUCK! Length != 6") | |
print(url) | |
#return | |
linux_idx = -1 | |
windows_idx = -1 | |
for idx,entry in enumerate(options): | |
if len(entry)==0: | |
continue | |
if entry[0]=="Linux and macOS:" or entry[0]=="Linux:": | |
linux_idx = idx | |
if entry[0]=="Windows:": | |
windows_idx = idx | |
if linux_idx ==-1 or windows_idx == -1: | |
print("FUCKFUCK! cannot extract linux windows table") | |
return ["-1"],["-1"],["-1"],["-1"] | |
return options[linux_idx+1],options[windows_idx+1],options[-1],options[-2] | |
pass | |
if __name__ == "__main__": | |
#get_windows_linux_available_single_option("https://software.intel.com/node/a897f631-3e3e-4c6b-9a32-763d62b82cf9") | |
get_options_url() | |
pass |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment