Created
July 31, 2022 12:11
-
-
Save skypenguins/020bec509325cb5692fcc7c09b597db5 to your computer and use it in GitHub Desktop.
Download media that an authorized user has RTed
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| using Twitter | |
| using JSON, OAuth | |
| using Dates | |
| using TimeZones | |
| using Downloads | |
| using ProgressBars | |
| # set debugging | |
| ENV["JULIA_DEBUG"] = Twitter | |
| # ~/.julia/config/startup.jl | |
| twitterauth(ENV["CONSUMER_KEY"], ENV["CONSUMER_SECRET"], ENV["ACCESS_TOKEN"], ENV["ACCESS_TOKEN_SECRET"]) | |
| @info "Loaded creds" | |
| function convert_to_jst(origin_dt) | |
| t2 = ZonedDateTime(origin_dt, dateformat"e u d H:M:S zzzz y") | |
| zdt = astimezone(t2, tz"Asia/Tokyo") | |
| dt = DateTime(zdt) | |
| end | |
| function get_rt_list() | |
| rts = [] | |
| @info "starting to get retweets..." | |
| tl = get_user_timeline(screen_name="zyuer", count=400, include_rts=true) | |
| # get retweets | |
| for status in tl | |
| if typeof(status.retweeted_status) != Nothing | |
| push!(rts, status) # push "RT" tweet | |
| end | |
| end | |
| @info "RTs: $(length(rts))" | |
| @info "oldest RT date: $(convert_to_jst(rts[end].created_at))" | |
| @info "getting RTs finished" | |
| rts | |
| end | |
| function get_media_urls_from_tl(retweets) | |
| urls = [] | |
| iter = ProgressBar(retweets) | |
| for status in iter | |
| rted_status = status.retweeted_status | |
| rted_dt = convert_to_jst(status.created_at) | |
| orig_dt = convert_to_jst(rted_status["created_at"]) | |
| orig_user = Users(rted_status["user"]) | |
| println( | |
| iter, | |
| """ RTed: $(rted_dt), orig: $(orig_dt) | |
| $(orig_user.name) @$(orig_user.screen_name) | |
| $(rted_status["text"])""" | |
| ) | |
| if haskey(rted_status, "extended_entities") | |
| media_list = rted_status["extended_entities"]["media"] | |
| for media in media_list | |
| # get multiple image urls | |
| if media["type"] == "photo" | |
| push!(urls, media["media_url_https"]) | |
| println(iter, "image url: $(media["media_url_https"])") | |
| # get videos urls | |
| else | |
| videos = [] | |
| bitrates = [] | |
| if haskey(media, "video_info") | |
| for variant in media["video_info"]["variants"] | |
| if haskey(variant, "bitrate") | |
| push!(bitrates, Int(variant["bitrate"])) | |
| push!(videos, variant) | |
| end | |
| end | |
| # select best quality | |
| best_bitrate = maximum(bitrates) | |
| for video in videos | |
| if best_bitrate == video["bitrate"] | |
| push!(urls, video["url"]) | |
| @info "video url: $(video["url"])" | |
| end | |
| end | |
| end | |
| end | |
| end | |
| else | |
| println(iter, "no media") | |
| end | |
| end | |
| @info "extracted media: $(length(urls))" | |
| urls | |
| end | |
| function dl_media(url_list) | |
| downloader = Downloader() | |
| n_files = length(url_list) | |
| fails = 0 | |
| time = @elapsed for (idx, url) in enumerate(url_list) | |
| file_name = basename(url) | |
| file_name = replace(file_name, r"\?.*" => "") | |
| if occursin(".mp4", file_name) == false | |
| url *= "?name=large" | |
| end | |
| headers = Dict( | |
| "User-Agent" => "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:92.0) Gecko/20100101 Firefox/92.0" | |
| ) | |
| try | |
| Downloads.download(url, pwd() * "/dl_RTed_media/media2/" * file_name; headers=headers, timeout=Inf, downloader=downloader) | |
| println("downloaded $file_name ... ($idx / $n_files)") | |
| catch e | |
| fails += 1 | |
| @error "止まるんじゃねぇぞ… $file_name ($idx)\n$(e)" | |
| end | |
| end | |
| @info """elapsed time: $time (s) / $n_files file(s) | |
| failed download(s): $(fails) """ | |
| end | |
| dl_media(get_media_urls_from_tl(get_rt_list())) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment