utils/fic-header.py

import requests, datetime, os, re
from bs4 import BeautifulSoup

# presumably needed for nsfw content
login_url = "https://www.archiveofourown.org/users/login"
data = {
    "user": "translinkni",
    "password": "notreallyanapi"
}

if os.path.exists("ficheader.html"):
    os.remove("ficheader.html")

thefile = open("ficheader.html", "a")    

with requests.Session() as s:
    response = s.post(login_url , data)
    print("Work ID:")
    id = input()
    print("Use title? (y/n)")
    thetitle = input()
    url = "https://archiveofourown.org/works/" + str(id)
    ficpage = s.get(url)
    ficsoup = BeautifulSoup(ficpage.content, "html.parser")
    rating = ficsoup.find("dd", class_="rating").text.strip()
    if str(rating) == "General Audiences":
        prazerating = "g"
    elif str(rating) == "Teen And Up Audiences":
        prazerating = "t"
    elif str(rating) == "Mature":
        prazerating = "m"
    elif str(rating) == "Explicit":
        prazerating = "e"
    warningheader = ficsoup.find("dd", {"class":["warning", "warnings"]})
    rawwarnings = warningheader.find_all("li")
    warnings = []
    for c in rawwarnings:
        warning = c.text
        warnings.append(str(warning))
    prazewarnings = []
    if "No Archive Warnings Apply" in warnings:
        prazewarn = 0
    elif "Creator Chose Not To Use Archive Warnings" in warnings:
        prazewarn = 1
        prazewarnings.append("miscellaneous")
    else:
        prazewarn = 1
        if "Major Character Death" in warnings:
            prazewarnings.append("character death")
        if "Underage" in warnings:
            prazewarnings.append("underage")    
    categoryheader = ficsoup.find("dd", {"class":["category", "categories"]})
    rawcategories = categoryheader.find_all("li")
    categories = []
    for c in rawcategories:
        category = c.text
        categories.append(str(category))
    prazegenre = []
    if "Gen" in categories:
        prazegenre.append("gen")
    if "M/M" in categories:
        prazegenre.append("slash")
    if "F/M" in categories:
        prazegenre.append("het")
    if "F/F" in categories:
        prazegenre.append("femslash")
    if "Multi" in categories:
        prazegenre.append("poly")
    fandomheader = ficsoup.find("dd", {"class":["fandom", "fandoms"]})
    rawfandoms = fandomheader.find_all("li")
    fandoms = []
    for c in rawfandoms:
        rawfandom = str(c.text)
        if rawfandom == "Final Fantasy VI":
            fandom = "FF6"
        elif rawfandom == "Compilation of Final Fantasy VII":
            fandom = "FF7"
        elif rawfandom == "Crisis Core: Final Fantasy VII":
            fandom = "FF7 Crisis Core"
        elif rawfandom == "Final Fantasy VII (Video Game 1997)":
            fandom = "FF7"
        elif rawfandom == "Final Fantasy VII Remake (Video Game 2020)":
            fandom = "FF7R"
        elif rawfandom == "Final Fantasy X":
            fandom = "FFX"
        elif rawfandom == "Final Fantasy X Series":
            fandom = "FFX"
        elif rawfandom == "Final Fantasy X-2":
            fandom = "FFX-2"
        elif rawfandom == "Final Fantasy IX":
            fandom = "FF9"
        else:
            fandom = rawfandom
        fandoms.append(fandom)
    characterheader = ficsoup.find("dd", {"class":["character", "characters"]})
    rawcharacters = characterheader.find_all("li")
    characters = []
    for c in rawcharacters:
        rawcharacter = str(c.text)
        cleancharacter = re.sub(r" \(.*\)","",rawcharacter)
        if cleancharacter == "Locke Cole":
            character = "Locke"
        elif cleancharacter == "Macías \"Mash\" Rene Figaro | Sabin Rene Figaro":
            character = "Sabin"
        elif cleancharacter == "Celes Chere":
            character = "Celes"
        elif cleancharacter == "Edgar Roni Figaro":
            character = "Edgar"
        elif cleancharacter == "Tina Branford | Terra Branford":
            character = "Terra"
        elif cleancharacter == "Original Characters":
            character = "OCs"
        elif cleancharacter == "Original Male Character":
            character = "OMC"
        elif cleancharacter == "Original Female Character":
            character = "OFC"
        else:
            character = cleancharacter
        characters.append(str(character))
    date = ficsoup.find("dd", class_="published").text
    prazedate = datetime.datetime.strptime(str(date), "%Y-%m-%d").strftime("%-d %B %Y")
    words = ficsoup.find("dd", class_="words").text
    title = ficsoup.find("h2", class_="title").text.strip()
    summaryheader = ficsoup.find("div", class_="summary")
    summary = summaryheader.find("blockquote")
    notesheader = ficsoup.find("div", class_="notes")
    try:
        rawnotes = str(notesheader.find("blockquote"))
    except:
        rawnotes = 0
    if rawnotes:
        notesa = re.sub(r" rel=\"nofollow\"","",rawnotes)
        notesb = re.sub(r"alt=\"\[community profile\]\"","alt=\"[community profile]\" style=\"vertical-align: text-bottom; border: 0; padding-right: 1px;\"",notesa)
        notesc = re.sub(r"alt=\"\[personal profile\]\"","alt=\"[personal profile]\" style=\"vertical-align: text-bottom; border: 0; padding-right: 1px;\"",notesb)
        notesd = re.sub(r"</p><p>\n<small><b>Standard note for 3sf fills:</b> I’m aware that some AO3 users may not consider prompt fills “gifts”, and will take no offence if the gift is refused!</small>","",notesc)
        notes = re.sub(r"\n</p>","</p>",notesd)
    else:
        notes = 0
    masterlist = s.get("https://tre.praze.net/fic/master.html")
    mastersoup = BeautifulSoup(masterlist.content, "html.parser")
    ficno = int(mastersoup.find("span", class_="ficno").text.strip()) + 1
    thefile.write("<div class=\"fic\" id=\"fic" + str(ficno) + "\">\n")
    if thetitle == "y":
        thefile.write("  <h1><span class=\"ficno\">" + str(ficno) + "</span> <span class=\"fictitle\">" + title + "</span></h1>\n")
    else:
        thefile.write("  <h1><span class=\"ficno\">" + str(ficno) + "</span></h1>\n")
    thefile.write("  <ul class=\"ficmeta\">\n")
    thefile.write("    <li class=\"ficdate\">" + prazedate + "</li>\n")
    thefile.write("    <li class=\"wordcount\">" + str(words) + "</li>\n")
    if prazerating == "g":
        thefile.write("    <li class=\"rating\"><span class=\"" + prazerating + "\"/></li>\n")
    else:
        thefile.write("    <li class=\"rating\"><span class=\"" + prazerating + "\"/> ()</li>\n")
    thefile.write("    <li class=\"fandom\">" + "/".join(fandoms) + "</li>\n")
    thefile.write("    <li class=\"characters\">" + ", ".join(characters) + "</li>\n")
    thefile.write("    <li class=\"genre\">" + ", ".join(prazegenre) + "</li>\n")
    if prazewarn:
        thefile.write("    <li class=\"warnings\">" + ", ".join(prazewarnings) + "</li>\n")
    thefile.write("  </ul>\n")
    thefile.write("  <p class=\"summary\">" + str(summary)[34:-18] + "</p>\n")
    if notes:
        thefile.write("  <p class=\"note\">" + str(notes)[34:-18] + "</p>\n")
    thefile.write("  <ul class=\"ficlinks\">\n")
    thefile.write("    <li class=\"ao3link\"><a href=\"https://archiveofourown.org/works/" + str(id) + "\">AO3</a></li>\n")
    thefile.write("    <li class=\"prazelink\"><a href=\"files/" + str(ficno)  + ".html\">HTML</a></li>\n")
    thefile.write("    <li class=\"prazelink\"><a href=\"files/" + str(ficno)  + ".pdf\">PDF</a></li>\n")
    thefile.write("    <li class=\"prazelink\"><a href=\"files/" + str(ficno)  + ".epub\">EPUB</a></li>\n")
    thefile.write("  </ul>\n")
    thefile.write("</div>\n")
    print("File saved to " + str(os.path.abspath("ficheader.html")))