From 72bf7bcd3787ffbda4ec2c47204896483e8069c9 Mon Sep 17 00:00:00 2001 From: Benjamin Mako Hill Date: Tue, 31 Mar 2020 08:35:23 -0700 Subject: [PATCH 1/2] stop writing writing header to one-column list This feels like it's asking for trouble. Description of the contents of the list is in the filename. --- wikipedia_views/scripts/fetch_daily_views.py | 1 - wikipedia_views/scripts/wikiproject_scraper.py | 1 - 2 files changed, 2 deletions(-) diff --git a/wikipedia_views/scripts/fetch_daily_views.py b/wikipedia_views/scripts/fetch_daily_views.py index 4f496fe..e3a2ff4 100755 --- a/wikipedia_views/scripts/fetch_daily_views.py +++ b/wikipedia_views/scripts/fetch_daily_views.py @@ -79,7 +79,6 @@ def main(): t_Out = f"{outputPath}dailyviews{queryDate}.tsv" with open(articleFile, 'r') as infile: - next(infile) #skip header articleList = list(infile) j = [] diff --git a/wikipedia_views/scripts/wikiproject_scraper.py b/wikipedia_views/scripts/wikiproject_scraper.py index 2ee3742..9d209a9 100755 --- a/wikipedia_views/scripts/wikiproject_scraper.py +++ b/wikipedia_views/scripts/wikiproject_scraper.py @@ -109,7 +109,6 @@ def main(): #3 Saves the list to a file with open(outputFile, 'w') as f: - f.write("Article\n") f.write('\n'.join(articleNames)+'\n') logging.debug(f"Finished scrape and made a new article file at {datetime.datetime.now()}") From 20ad09d15575bc9e54877f61c3c8f0ae5866be17 Mon Sep 17 00:00:00 2001 From: Aaron Shaw Date: Tue, 31 Mar 2020 17:09:58 -0500 Subject: [PATCH 2/2] Update README.md linking to project pages more fully --- README.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 10a868b..3848b4f 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,7 @@ # COVID-19 Digital Observatory -The COVID-19 Digital Observatory collects, aggregates, and distributes data from social media, search engine results, and Wikipedia to support immediate public health response and social and data science research related to the pandemic. +The [COVID-19 Digital Observatory](https://covid19.communitydata.science "Covid-19 Digital Observatory homepage") collects, aggregates, and distributes data from social media, search engine results, and Wikipedia to support immediate public health response and social and data science research related to the pandemic. -The [community data science collective](https://wiki.communitydata.science/Main_Page "The community data science collective wiki") is the early stages of building this project. We expect to make rapid progess and to begin releasing code and data soon. +The [community data science collective](https://wiki.communitydata.science/Main_Page "The community data science collective wiki") is working with [Pushshift](https://pushshift.io) and others to build this project. We expect to make rapid progess and to release additional code and data soon. -We eagerly welcome contributors! Please get in touch. -Contributors are held to the [code of conduct](code_of_conduct.md "link to code of conduct.md"). +We eagerly welcome contributors! Please get in touch, submit pull requests, and visit the [project homepage](https://covid19.communitydata.science "Covid-19 Digital Observatory homepage") for more info. Also, please note that contributors are held to the [code of conduct](code_of_conduct.md "link to code of conduct.md").