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

better comments

Browse source
This commit is contained in:
Mylloon 2021-08-24 13:00:28 +02:00
parent c5ea9e4f39
commit 5d4ac14044
1 changed files with 11 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
main.py
View file

@ -5,7 +5,7 @@ from cloudscraper import CloudScraper, create_scraper
from re import findall, sub
class Scraper:
def __init__(self, pseudo, password, app, debug = False):
def __init__(self, pseudo: str, password: str, app: str, debug: bool = False):
self.debug = debug
self.url = "https://forum.mobilism.org"
self.requested_app = app
@ -32,7 +32,7 @@ class Scraper:
return session
def search(self, session) -> tuple[list[dict], list[dict]]:
def search(self, session: CloudScraper) -> tuple[list[dict], list[dict]]:
"""Do the research."""
if self.debug: print("Going to search page and check connection...", end = " ")
reponse = session.get(f"{self.url}/search.php", params = {"keywords": self.requested_app, "sr": "topics", "sf": "titleonly"}) # fetch results page
@ -80,7 +80,7 @@ class Scraper:
return elements
def getInfos(self, session, elements: list) -> list:
def getInfos(self, session: CloudScraper, elements: list) -> list:
"""Go to the first n pages and get a lot of infos"""
page = 3
if self.debug: print(f"Going to the {page} first pages...", end = " ")
@ -118,14 +118,14 @@ class Scraper:
_downloadLinks = findall(r"Download Instructions:</span> ?<br />(.*|[\s\S]*)</a></div>", elements[i])[0]
except:
_downloadLinks = None
_downloadLinks = sub(r"\n|<a class=\"postlink\" href=\"|\(Closed Filehost\) ?|<span style=\"font-weight: bold\">|</span>|\">(\S*)</a>", "", _downloadLinks)
_downloadLinks = sub(r"<br />\n?", "\n", _downloadLinks)
_downloadLinks = sub(r"Mirrors(?!:)|Mirror(?!s)(?!:)", "Mirror:", _downloadLinks)
_downloadLinks = sub(r"\n|<a class=\"postlink\" href=\"|\(Closed Filehost\) ?|<span style=\"font-weight: bold\">|</span>|\">(\S*)</a>", "", _downloadLinks) # remove html garbage
_downloadLinks = sub(r"<br />\n?", "\n", _downloadLinks) # convert newline html to \n
_downloadLinks = sub(r"Mirrors(?!:)|Mirror(?!s)(?!:)", "Mirror:", _downloadLinks) # add ":"
elements[i] = {"changelogs": _changelogs, "downloadLinks": _downloadLinks}
return elements
def prettyPrint(self, topics: tuple[list[dict], list[dict]]):
def prettyPrint(self, topics: tuple[list[dict], list[dict]]) -> list:
"""Show a pretty message with all the specialized infos"""
topics, topicsInfos = topics
print("\n")
@ -147,15 +147,15 @@ class Scraper:
return result
def work(self) -> str:
def work(self) -> list:
"""Call all the others methods."""
return self.prettyPrint(self.search(self.connect()))
def save(self, elements):
def save(self, elements: list) -> None:
"""Save all the results parsed to a CSV file."""
taille = len(elements)
if taille == 0:
print("Aucun élément n'a été trouvé avec la recherche.")
print("No elements were found with the search.")
return
filename = "results.csv"
with open(filename, "w") as f:
@ -167,7 +167,7 @@ class Scraper:
if element != "linkParams":
f.write(";".join(str(e) for e in list(element.values())[:-1]))
f.write("\n")
print(f"{taille} éléments ont étés enrengistés dans le fichier {filename}.")
print(f"{taille} elements have been registered in the {filename} file.")
if __name__ == "__main__":
argv = argv[1:]