update 2023-05-02 for preprints posted up until 2023-04-30. Dataset archived on Figshare.

Author: bmkramer

covid19_preprints.Rmd

@@ -47,7 +47,7 @@ Note: run update from previous sample date (inclusive) to ensure no records are
 ```{r}
 
 sample_date_until <- Sys.Date()
-#sample_data_until <- as.Date("2022-11-03")
+#sample_data_until <- as.Date("2023-04-30")
 
 posted_date_until <-floor_date(sample_date_until, "week") #set to last Sunday prior to sample date
 
@@ -276,6 +276,7 @@ rm(covid_preprints_previous)
 
 #crawl SSRN to retrieve posted dates
 cr_ssrn_covid <- cr_ssrn_covid %>%
+ filter(is.na(posted_date)) %>%
  # Retrieve 'real' posted dates from the SSRN website. Warning: slow
  mutate(posted_date = ymd(map_chr(identifier, getSSRNPublicationDate)),
  source = "SSRN") %>%
@@ -284,6 +285,7 @@ cr_ssrn_covid <- cr_ssrn_covid %>%
 
 rm(cr_ssrn_df)
 
+
 ```
 
 The datasets derived from "posted-content" and from SSRN are merged to a final Crossref dataset
@@ -475,7 +477,7 @@ dc_covid <- dc_preprints_df %>%
  # Select only relevant fields with unique values
  distinct(source, identifier, identifier_type, posted_date, title, abstract)
 
-rm(dc_preprints_df)
+rrm(dc_preprints_df)
 
 ```
 

data/metadata.json

@@ -1,7 +1,7 @@
 {
-"release_date": "2023-04-30",
-"sample_date": "2023-03-02",
-"posted_date": "2023-02-26",
+"release_date": "2023-05-02",
+"sample_date": "2023-04-30",
+"posted_date": "2023-04-30",
 "url_data": "https://doi.org/10.6084/m9.figshare.22707346",
 "url_repository": "https://github.com/nicholasmfraser/covid19_preprints"
 }