Anri/mobilismScrap
Archived
1
0
Fork 0
Code Issues Pull requests Projects Releases 6 Wiki Activity

adding parser

Browse source
This commit is contained in:
Mylloon 2021-08-23 18:19:04 +02:00
parent 82b261104c
commit 3956b4d686
1 changed files with 30 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
main.py
View file

@ -2,6 +2,7 @@ from sys import argv
from os import environ from os import environ
from dotenv import load_dotenv from dotenv import load_dotenv
from cloudscraper import CloudScraper, create_scraper from cloudscraper import CloudScraper, create_scraper
from re import findall
class Scraper: class Scraper:
def __init__(self, pseudo, password, app, debug = False): def __init__(self, pseudo, password, app, debug = False):
@ -43,13 +44,38 @@ class Scraper:
def search(self, session) -> str: def search(self, session) -> str:
if self.debug: print("Going to search page...", end = " ") if self.debug: print("Going to search page...", end = " ")
reponse = session.get(f"{self.url}/search.php", params = {"keywords": self.requested_app, "sr": "topics", "sf": "titleonly"}) reponse = session.get(f"{self.url}/search.php", params = {"keywords": self.requested_app, "sr": "topics", "sf": "titleonly"})
if self.debug: print(reponse.status_code, reponse.url)
with open("temp.html", "w") as f: # debug if self.debug: print("Results retrieval...", end = " ")
f.writelines(reponse.text) linkList = self.parse(reponse.text)
# if self.debug: print(reponse.status_code, reponse.url)
# with open("temp2.log", "w") as f: # debug
# f.writelines(res)
link = "No link for your application was found." link = "No link for your application was found."
return link return link
def parse(self, htmlPage: str) -> list:
elements = htmlPage.split("<tr>\n<td>")[1:]
elements[-1] = elements[-1].split("</td>\n</tr>")[0]
for i in range(0, len(elements)):
try:
_title = findall(r"class=\"topictitle\">(.*)<\/a>", elements[i])[0]
except:
_title = None
try:
_author = findall(r"<br />\n<i class=\"icon-user\"></i> by <a href=\"\./memberlist\.php\?mode=viewprofile&amp;u=\d+\"( style=\"color: #.*;\" class=\"username-coloured\")?>(.*)</a>", elements[i])[0][-1]
except:
_author = None
print(elements[i])
try:
_link = findall(r"\./viewtopic\.php\?f=(\d*)&amp;t=(\d*)&amp", elements[i])[0]
_link = {"f": _link[0], "t": _link[1]}
except:
_link = None
elements[i] = {"title": _title, "author": _author, "linkParams": _link}
return elements
def work(self) -> str: def work(self) -> str:
session = self.connect() session = self.connect()
link = self.search(session) link = self.search(session)
@ -58,7 +84,7 @@ class Scraper:
if __name__ == "__main__": if __name__ == "__main__":
argv = argv[1:] argv = argv[1:]
if len(argv) == 3: if len(argv) >= 3 and len(argv) <= 4:
print(Scraper(*argv).work()) print(Scraper(*argv).work())
else: else:
try: try: