Skip to content
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

Corrigé l'erreur avec intervention_count #24

Merged
merged 5 commits into from
Apr 6, 2023
Merged

Corrigé l'erreur avec intervention_count #24

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
3506812
Corrigé l'erreur avec intervention_count
ClementCadieux Apr 4, 2023
4d8edc1
Retour à l'état initial
ClementCadieux Apr 4, 2023
de9f3c5
Tentative de solutions
ClementCadieux Apr 4, 2023
e58d711
Added a log at the end
ClementCadieux Apr 6, 2023
187d758
Comptes les interventions skippées
ClementCadieux Apr 6, 2023
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
19 changes: 14 additions & 5 deletions scrapers/parliament-mash/quebec-debates.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
library(dplyr)
status <<- 0
debate_count <<- 0
intervention_count <<- 0
total_intervention_count <<- 0
final_message <<- ""


Expand Down Expand Up @@ -158,6 +158,8 @@ list_urls <- doc_urls[grep("assemblee-nationale/4\\d-\\d/journal-debats", doc_ur
#
for (i in 1:length(list_urls)) {

intervention_count <<- 0
skipped_intervention <- 0
#if (opt$hub_mode != "skip") clessnhub::refresh_token(configuration$token, configuration$url)
if (opt$hub_mode != "skip") clessnhub::connect_with_token(Sys.getenv('HUB_TOKEN'))

Expand Down Expand Up @@ -400,6 +402,7 @@ for (i in 1:length(list_urls)) {
event_sentence_count <- clessnverse::countVecSentences(doc_text) - 1
speech_paragraph_count <- 0

skipped_intervention <- 0
for (j in 1:length(doc_text)) {
#cat(j, intervention_count, "\r")
cat(intervention_count, "\r")
Expand Down Expand Up @@ -468,6 +471,7 @@ for (i in 1:length(list_urls)) {
intervention_text <- gsub("(?<=[\\s])\\s*|^\\s+|\\s+$", "", intervention_text, perl=TRUE)
matching_row <- NULL
intervention_count <<- intervention_count - 1
skipped_intervention <<- skipped_intervention + 1
next
}

Expand Down Expand Up @@ -885,15 +889,20 @@ for (i in 1:length(list_urls)) {
} # version finale

} #if (grepl("actualites-salle-presse", event_url))

if (intervention_count > 1) debate_count <- debate_count + 1
clessnverse::logit(scriptname, paste("intervention_count: ", intervention_count), logger)
clessnverse::logit(scriptname, paste("Skipped: ", skipped_intervention), logger)

if (intervention_count > 1) {
debate_count <- debate_count + 1
total_intervention_count <<- total_intervention_count + intervention_count
}

} #for (i in 1:nrow(result))

if (intervention_count < 0) intervention_count <- 0
if (total_intervention_count < 0) total_intervention_count <- 0

clessnverse::logit(scriptname, final_message, logger)
clessnverse::logit(scriptname, paste(debate_count, "debates were added to the hub totalling", intervention_count, "interventions"), logger)
clessnverse::logit(scriptname, paste(debate_count, "debates were added to the hub totalling", total_intervention_count, "interventions"), logger)
clessnverse::logit(scriptname, paste("reaching end of", scriptname, "script"), logger = logger)
logger <- clessnverse::logclose(logger)
quit(save="no", status = status)