Skip to content

Adding date field #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tuxo wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Adding date field #7

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion imgur_scraper/imgur_scraper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import argparse
import csv
import datetime
from datetime import date, timedelta
import json
import os

Expand All @@ -26,6 +27,7 @@ def get_viral_posts_from(start_date: str, end_date: str) -> json:
"Grabbing "
+ " ".join(r.html.find(".images-header-main")[0].full_text.split())
)
date_img = date.today() - timedelta(days=days_ago)
while not r.html.find("#nomore"):
for entries in r.html.find(".post"):
yield {
Expand All @@ -37,6 +39,7 @@ def get_viral_posts_from(start_date: str, end_date: str) -> json:
.rstrip(),
"type": entries.find(".post-info")[0].full_text.strip().split()[0],
"views": entries.find(".post-info")[0].full_text.strip().split()[2],
"date": date_img.strftime('%Y-%m-%d')
}
counter += 1
r = HTMLSession().get(
Expand Down Expand Up @@ -96,7 +99,7 @@ def main():
try:
file_name = os.path.join(path, f"{start_date}_to_{end_date}_imgur_data.csv")
with open(file_name, "x", newline="", encoding="utf-8") as csvfile:
fieldnames = ["title", "url", "points", "tags", "type", "views"]
fieldnames = ["title", "url", "points", "tags", "type", "views", "date"]
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(get_viral_posts_from(start_date, end_date))
Expand Down