Created
November 8, 2017 07:04
-
-
Save tomy0000000/05c6ab312bd1c3d19819a68dc497d3da to your computer and use it in GitHub Desktop.
Grab School Datas from UAC
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
| import requests | |
| import json | |
| import bs4 | |
| import re | |
| link_List = input().split(" ") | |
| link_List | |
| Res = [] | |
| for each in link_List: | |
| item_link = each | |
| item_Page = requests.get(item_link) | |
| item_Page.encoding = "big5" | |
| item_Soup = bs4.BeautifulSoup(item_Page.text, "lxml") | |
| Item = item_Soup.title.string.split(" - ") | |
| Item.append("") | |
| Infos = list(item_Soup.find_all("td")[2].strings) | |
| for each in range(len(Infos)): | |
| Infos[each] = Infos[each].replace("\xa0","").replace("\u3000","").replace("\n","") | |
| Infos.pop() | |
| for sub in ["國文","英文","數學甲","數學乙","物理","化學"]: | |
| Added = False | |
| for info in Infos: | |
| if sub in info: | |
| Item.append(info[info.find("x")+2:]) | |
| Added = True | |
| if Added == False: | |
| Item.append("0") | |
| Item.append(item_Soup.find_all("td")[4].string.replace("\n","").replace("\u3000","").replace(" ","")) | |
| Item.append(item_Soup.find_all("td")[7].string.replace("\n","").replace("\u3000","").replace(" ","")) | |
| Item.append(item_Soup.find_all("td")[10].string.replace("\n","").replace("\u3000","").replace(" ","")) | |
| Item.append("") | |
| Item.append("") | |
| Item.append("") | |
| if item_Soup.find_all("td")[1].string == "\n---": | |
| Item.append("-") | |
| else: | |
| if item_Soup.find_all("td")[1].string is None: | |
| Temp = list(item_Soup.find_all("td")[1].strings) | |
| for sub in range(len(Temp)): | |
| Temp[sub] = Temp[sub].replace("\n","").replace("\u3000","").replace("\xa0","") | |
| Temp.pop() | |
| Item.append("ReTURN".join(Temp)) | |
| else: | |
| Item.append(item_Soup.find_all("td")[1].string.replace("\n","").replace("\u3000","").replace(" ","")) | |
| if item_Soup.find_all("td")[8].string == "---": | |
| Item.append("-") | |
| else: | |
| Item.append(item_Soup.find_all("td")[8].string.replace("\n","").replace("\u3000","").replace(" ","")) | |
| Res.append("\t".join(Item)) | |
| for each in range(len(Res)): | |
| print(Res[each]) | |
| with open("Results.txt","w") as f: | |
| f.write("\n".join(Res)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment