turtlebasket
/
JobSpy
mirror of https://github.com/Bunsly/JobSpy
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

filter by hours old works! next is by filed column

pull/231/head
Yariv Menachem 2024-12-16 20:49:04 +02:00
parent bbe3d6df35
commit 7926356233
2 changed files with 14 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/jobspy/scrapers/goozali/__init__.py
View File

@ -59,9 +59,9 @@ class GoozaliScraper(Scraper):
return GoozaliResponse(**data) return GoozaliResponse(**data)
# Function to filter GoozaliRows based on hours old # Function to filter GoozaliRows based on hours old
def filter_rows_by_hours(rows: list[GoozaliRow], hours: int) -> list[GoozaliRow]: def filter_rows_by_hours(self, rows: list[GoozaliRow], hours: int) -> list[GoozaliRow]:
# Current time # Current time
now = datetime.utcnow() now = datetime.datetime.now()
# Calculate the time delta for the given hours # Calculate the time delta for the given hours
time_delta = datetime.timedelta(hours=hours) time_delta = datetime.timedelta(hours=hours)
@ -69,7 +69,7 @@ class GoozaliScraper(Scraper):
# Filter rows # Filter rows
filtered_rows = [ filtered_rows = [
row for row in rows row for row in rows
if now - datetime.strptime(row.createdTime, "%Y-%m-%dT%H:%M:%S.%fZ") <= time_delta if now - row.createdTime <= time_delta
] ]
return filtered_rows return filtered_rows
@ -78,17 +78,13 @@ class GoozaliScraper(Scraper):
for column in columns: for column in columns:
if (column.name == column_name): if (column.name == column_name):
return column return column
# def filter_rows_by_field_column(rows: list[GoozaliRow], field_column: Column) -> list[GoozaliRow]:
# # Current time
# now = datetime.utcnow()
# # Calculate the time delta for the given hours # def filter_rows_by_column(rows: list[GoozaliRow], goozali_column: GoozaliColumn) -> list[GoozaliRow]:
# time_delta = datetime.timedelta(hours=hours)
# # Filter rows # # Filter rows
# filtered_rows = [ # filtered_rows = [
# row for row in rows # row for row in rows
# if now - datetime.strptime(row.createdTime, "%Y-%m-%dT%H:%M:%S.%fZ") <= time_delta # if row.cellValuesByColumnId[goozali_column.id] == goozali_column.
# ] # ]
# return filtered_rows # return filtered_rows
@ -122,15 +118,12 @@ class GoozaliScraper(Scraper):
# model the response with models # model the response with models
goozali_response = self.mapper.map_response_to_goozali_response( goozali_response = self.mapper.map_response_to_goozali_response(
response=response) response=response)
# goozali_response: GoozaliResponse = self.map_respone_to_goozali_response(
# response)
# create map columnId to Column object
field = self.find_column(
goozali_response.data.columns, "Field")
# filter result by Field like the web
# filter by date # filter by date
# filtered_rows_by_age = filter_rows_by_hours( filtered_rows_by_age = self.filter_rows_by_hours(
# goozali_response.data.table.rows, scraper_input.hours_old) goozali_response.data.rows, scraper_input.hours_old)
# filter result by Field like the web
field_cloumn = self.find_column(
goozali_response.data.columns, "Field")
# map to JobResponse Object # map to JobResponse Object
return JobResponse(jobs=job_list) return JobResponse(jobs=job_list)

4
src/jobspy/scrapers/goozali/model/GoozaliRow.py
View File

@ -1,8 +1,10 @@
from datetime import datetime
from typing import Dict, List from typing import Dict, List
class GoozaliRow: class GoozaliRow:
def __init__(self, id: str, createdTime: str, cellValuesByColumnId: Dict[str, List[str]]): def __init__(self, id: str, createdTime: str, cellValuesByColumnId: Dict[str, List[str]]):
self.id = id self.id = id
self.createdTime = createdTime self.createdTime = datetime.strptime(
createdTime, '%Y-%m-%dT%H:%M:%S.%fZ')
self.cellValuesByColumnId = cellValuesByColumnId self.cellValuesByColumnId = cellValuesByColumnId