url1 <- c("https://m.imdb.com/search/title/?title_type=feature&release_date=2010-01-01,2023-12-31&sort=release_date,asc&num_votes=2500,&country_of_origin=TR&count=250")
url2 <- c("https://m.imdb.com/search/title/?title_type=feature&release_date=,2009-12-31&sort=release_date,asc&num_votes=2500,&country_of_origin=TR&count=250")library(tidyverse)
library(rvest)
library(stringr)
library(knitr)
convert_time <- function(time_str) {
hours <- 0
minutes <- 0
if (grepl("h", time_str)) {
time_components <- strsplit(time_str, "h|m")[[1]]
if (length(time_components) >= 1) {
hours <- as.numeric(time_components[1])
}
if (length(time_components) >= 2) {
minutes <- as.numeric(time_components[2])
}
} else {
minutes <- as.numeric(gsub("m", "", time_str))
}
total_minutes <- hours * 60 + minutes
return(total_minutes)
}
data_html <- read_html(url1)
title_names1 <- data_html %>%
html_elements(".ipc-title__text") %>%
html_text()
title_names1 <- tail(head(title_names1,-1),-1)
title_names1 <- str_split(title_names1, " ", n=2)
title_names1 <- unlist(lapply(title_names1, function(x) {x[2]}))
year1 <- data_html %>%
html_nodes(".dli-title-metadata-item:nth-child(1)") %>%
html_text() %>%
as.numeric()
duration1 <- data_html %>%
html_elements(".dli-title-metadata-item:nth-child(2)") %>%
html_text()
duration1 <- unlist(lapply(duration1, convert_time))
rating1 <- data_html %>%
html_elements(".ratingGroup--imdb-rating") %>%
html_text()
rating1 <- str_extract(rating1, "\\d+\\.\\d+") %>%
as.numeric()
votes1 <- data_html %>%
html_elements(".kRnqtn") %>%
html_text()
votes1 <- gsub("\\D", "", votes1) %>%
as.numeric()
#PART URL2
data_html <- read_html(url2)
title_names2 <- data_html %>%
html_elements(".ipc-title__text") %>%
html_text()
title_names2 <- tail(head(title_names2,-1),-1)
title_names2 <- str_split(title_names2, " ", n=2)
title_names2 <- unlist(lapply(title_names2, function(x) {x[2]}))
year2 <- data_html %>%
html_nodes(".dli-title-metadata-item:nth-child(1)") %>%
html_text() %>%
as.numeric()
duration2 <- data_html %>%
html_elements(".dli-title-metadata-item:nth-child(2)") %>%
html_text()
duration2 <- unlist(lapply(duration2, convert_time))
rating2 <- data_html %>%
html_elements(".ratingGroup--imdb-rating") %>%
html_text()
rating2 <- str_extract(rating2, "\\d+\\.\\d+") %>%
as.numeric()
votes2 <- data_html %>%
html_elements(".kRnqtn") %>%
html_text()
votes2 <- gsub("\\D", "", votes2) %>%
as.numeric()
title <- c(title_names1,title_names2)
year <- c(year1,year2)
duration <- c(duration1,duration2)
rating <- c(rating1,rating2)
votes <- c(votes1,votes2)
moviedf <- data.frame(
Title = title,
Year = year,
Duration = duration,
Rating = rating,
Votes = votes
)movies <- moviedf %>%
arrange(desc(Rating))kable(
movies %>%
arrange(desc(rating)) %>%
head(5),
format = "html",
caption = "Top 5 Movies based on Rating",
col.names = c("Title", "Year", "Duration", "Rating", "Votes")
)| Title | Year | Duration | Rating | Votes |
|---|---|---|---|---|
| Hükümet Kadin | 2013 | 99 | 6.5 | 9184 |
| Arabesk | 1989 | 92 | 8.0 | 8303 |
| Senden Bana Kalan | 2015 | 117 | 6.5 | 3403 |
| Yolun Açik Olsun | 2022 | 119 | 6.5 | 2699 |
| Aykut Eniste 2 | 2021 | 115 | 6.5 | 3597 |
kable(movies %>% tail(5), caption = "Bottom 5", col.names = c("Title", "Year", "Duration", "Rating", "Votes"))| Title | Year | Duration | Rating | Votes | |
|---|---|---|---|---|---|
| 466 | Cumali Ceber 2 | 2018 | 100 | 1.2 | 10229 |
| 467 | 15/07 Safak Vakti | 2021 | 95 | 1.2 | 20608 |
| 468 | Müjde | 2022 | 48 | 1.2 | 9920 |
| 469 | Reis | 2017 | 108 | 1.0 | 73974 |
| 470 | Cumali Ceber: Allah Seni Alsin | 2017 | 100 | 1.0 | 39268 |
kable(moviedf %>% filter(Title == "Recep Ivedik 3" | Title == "Eyyvah Eyvah" | Title == "Çok Filim Hareketler Bunlar"), caption = "My Bests", col.names = c("Title", "Year", "Duration", "Rating", "Votes"))| Title | Year | Duration | Rating | Votes |
|---|---|---|---|---|
| Recep Ivedik 3 | 2010 | 95 | 4.2 | 20792 |
| Eyyvah Eyvah | 2010 | 104 | 7.0 | 21447 |
| Çok Filim Hareketler Bunlar | 2010 | 104 | 4.5 | 5161 |
moviedf %>%
group_by(Year) %>%
summarize(avg = mean(Rating)) %>%
ggplot(aes(x = Year, y = avg)) + geom_point() +
ggtitle("Yearly Rating Averages")
The plot clearly show that ratings decrease over the years.
ggplot(moviedf, aes(x = factor(Year))) +
geom_bar(fill = "yellow", color = "black") +
ggtitle("Number of Movies Over the Years") +
labs(x = "Year", y = "Number of Movies") +
theme(legend.position = "none",
axis.text.x = element_text(angle = 60)
)
moviedf$Year <- as.factor(moviedf$Year)
ggplot(moviedf, aes(x = Year, y = Rating, fill = factor(Year))) +
geom_boxplot(color = "black",width = 0.7) +
labs(x = "Year", y = "Rating") +
ggtitle("Box Plots of Movie Ratings") +
theme(legend.position = "none",
axis.text.x = element_text(angle = 60)
)
corr <- cor(moviedf$Votes, moviedf$Rating)
cat("Correlation between Votes and Ratings:", corr)Correlation between Votes and Ratings: 0.1311088The correlation between votes and ratings.
corr <- cor(moviedf$Duration, moviedf$Rating)
cat("Correlation between Votes and Ratings:", corr)Correlation between Votes and Ratings: 0.03331057The correlation between duration and ratings.
moviedf1 = moviedf
url <- c("https://m.imdb.com/search/title/?title_type=feature&sort=release_date,asc&num_votes=2500,&groups=top_1000&country_of_origin=TR&count=250")
data_html <- read_html(url)
title_names <- data_html %>%
html_elements(".ipc-title__text") %>%
html_text()
title_names <- tail(head(title_names,-1),-1)
title_names <- str_split(title_names, " ", n=2)
title_names <- unlist(lapply(title_names, function(x) {x[2]}))
year <- data_html %>%
html_nodes(".dli-title-metadata-item:nth-child(1)") %>%
html_text() %>%
as.numeric()
bestmovies <- data.frame(
Title = title_names,
Year = year
)
kable (bestmovies, caption = "Turkish Movies in the Top 1000",format = "simple")| Title | Year |
|---|---|
| Eskiya | 1996 |
| Her Sey Çok Güzel Olacak | 1998 |
| Vizontele | 2001 |
| G.O.R.A. | 2004 |
| Babam ve Oglum | 2005 |
| Nefes: Vatan Sagolsun | 2009 |
| Bir Zamanlar Anadolu’da | 2011 |
| Kis Uykusu | 2014 |
| Ayla: The Daughter of War | 2017 |
| Ahlat Agaci | 2018 |
| Yedinci Kogustaki Mucize | 2019 |
moviedf <- moviedf %>% mutate(Year = as.numeric(Year))
bestmovies <- bestmovies %>% mutate(Year = as.numeric(Year))
bestmovies2 <- movies %>%
inner_join(bestmovies, by = c("Title", "Year")) %>%
arrange(desc(Rating))
kable(bestmovies2, caption = "Turkish Movies in the Top 1000 Full Table", col.names = c("Title", "Year", "Duration", "Rating", "Votes"))| Title | Year | Duration | Rating | Votes |
|---|---|---|---|---|
| Ayla: The Daughter of War | 2017 | 125 | 8.3 | 43005 |
| Yedinci Kogustaki Mucize | 2019 | 132 | 8.2 | 54200 |
| Babam ve Oglum | 2005 | 108 | 8.2 | 91054 |
| Eskiya | 1996 | 128 | 8.1 | 71707 |
| Her Sey Çok Güzel Olacak | 1998 | 107 | 8.1 | 27129 |
| Kis Uykusu | 2014 | 196 | 8.0 | 54664 |
| Ahlat Agaci | 2018 | 188 | 8.0 | 27029 |
| Vizontele | 2001 | 110 | 8.0 | 38412 |
| G.O.R.A. | 2004 | 127 | 8.0 | 66042 |
| Nefes: Vatan Sagolsun | 2009 | 128 | 8.0 | 35032 |
| Bir Zamanlar Anadolu’da | 2011 | 157 | 7.8 | 49380 |
moviedf1 <- arrange(moviedf1, desc(Rating))
kable(head(moviedf1, 11), caption = "Turkish Movies in the Top 11", col.names = c("Title", "Year", "Duration", "Rating", "Votes"))| Title | Year | Duration | Rating | Votes |
|---|---|---|---|---|
| Hababam Sinifi | 1975 | 87 | 9.2 | 42520 |
| CM101MMXI Fundamentals | 2013 | 139 | 9.1 | 47001 |
| Hababam Sinifi Sinifta Kaldi | 1975 | 95 | 8.9 | 24372 |
| Tosun Pasa | 1976 | 90 | 8.9 | 24331 |
| Süt Kardesler | 1976 | 80 | 8.8 | 20891 |
| Hababam Sinifi Uyaniyor | 1976 | 94 | 8.7 | 20642 |
| Saban Oglu Saban | 1977 | 90 | 8.7 | 18537 |
| Neseli Günler | 1978 | 95 | 8.7 | 11811 |
| Kibar Feyzo | 1978 | 83 | 8.7 | 17127 |
| Zügürt Aga | 1985 | 101 | 8.7 | 16141 |
| Canim Kardesim | 1973 | 85 | 8.6 | 10099 |
Upon analyzing the table, it is evident that the top 11 highest-rated movies deviate from those present in our original data frame. A significant contrast is noticeable in the release years of these films, with a conspicuous lack of older productions within the TOP 1000 IMDB list. It is likely that the criteria for inclusion in this list prioritize movies released after a certain year.