utils/promptscrape.py

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

# needed for nsfw content
login_url = "https://www.dreamwidth.org/login?ret=1"
data = {
    "user": "fakeapi",
    "password": "thisap1isfalse"
}

if os.path.exists("prompts.org"):
    os.remove("prompts.org")

thefile = open("prompts.org", "a")

cent = "https://100words.dreamwidth.org/tag/!prompt?style=light&tag=%21prompt"
centpage = requests.get(cent)
centsoup = BeautifulSoup(centpage.content, "html.parser")
centprompts = centsoup.find_all("h3", string=lambda text: "prompt:" in text.lower())
centsubsoup = BeautifulSoup(str(centprompts[0]), "html.parser")
centurl = centsubsoup.find("a")
centprompt = (centurl["href"])
centpromptnew = (centurl["href"] + "?style=light")
centpromptpage = requests.get(centpromptnew)
centpromptsoup = BeautifulSoup(centpromptpage.content, "html.parser")
centprompttext = centpromptsoup.find(class_="entry-content")
centtheprompt = centprompttext.find("strong")
print("100words (100 words): \033[1m" + centtheprompt.text.lower() + "\033[0m (" + centprompt + ")\n")
thefile.write("- [[" + centprompt + "][100words]] (100 words): *" + centtheprompt.text.lower() + "*\n")

# for this one we need to extract the right entry from a list, which may be an <ol> but may not be. also, need to use the right month, as next month’s prompts are posted in advance
today = int(date.today().strftime("%d"))
month = str(date.today().strftime("%B"))
monthstring = ".*" + month + ".*"
thirtyone = "https://31-days.dreamwidth.org/tag/!prompts?style=light&tag=%21prompts"
thirtyonepage = requests.get(thirtyone)
thirtyonesoup = BeautifulSoup(thirtyonepage.content, "html.parser")
thirtyoneprompts = thirtyonesoup.find_all("h3", string = re.compile(monthstring))
thirtyonesubsoup = BeautifulSoup(str(thirtyoneprompts[0]), "html.parser")
thirtyoneurl = thirtyonesubsoup.find("a")
thirtyoneprompt = (thirtyoneurl["href"])
thirtyonepromptnew = (thirtyoneurl["href"] + "?style=light")
thirtyonepromptpage = requests.get(thirtyonepromptnew)
thirtyonepromptsoup = BeautifulSoup(thirtyonepromptpage.content, "html.parser")
thirtyoneprompttext = thirtyonepromptsoup.find(class_="entry-content")
if "<ol>" in str(thirtyoneprompttext):
    thirtyonetheprompt = thirtyoneprompttext.select("ol > li")[today - 1].get_text(strip=True)
else:
    interprompt = list(thirtyoneprompttext.stripped_strings)
    thirtyonelist = []
    for prompt in interprompt:
        if len(prompt) < 5:
            promptnum = interprompt.index(prompt)
            newnum = promptnum + 1
            thirtyonelist.append(prompt + interprompt[newnum])
        else:
            thirtyonelist.append(prompt)
    intsearch = str(today) + "."
    thirtyonetheprompt = str([item for item in thirtyonelist if item.startswith(intsearch)])[2:-2]
print("31-days (any): \033[1m" + thirtyonetheprompt.lower() + "\033[0m (" + thirtyoneprompt + ")\n")
thefile.write("- [[" + thirtyoneprompt + "][31-days]] (any): *" + thirtyonetheprompt.lower() + "*\n")


ad = "https://anythingdrabble.dreamwidth.org/tag/mod!+post?style=light&tag=mod%21+post"
adpage = requests.get(ad)
adsoup = BeautifulSoup(adpage.content, "html.parser")
adprompts = adsoup.find_all("h3", string=lambda text: "prompt post" in text.lower())
adsubsoup = BeautifulSoup(str(adprompts[0]), "html.parser")
adurl = adsubsoup.find("a")
adprompt = (adurl["href"])
adpromptnew = (adurl["href"] + "?style=light")
adpromptpage = requests.get(adpromptnew)
adpromptsoup = BeautifulSoup(adpromptpage.content, "html.parser")
adprompttext = adpromptsoup.find(class_="entry-content")
adtheprompt = adprompttext.find("center")
adstrippable = str(adtheprompt.text)
while adstrippable[-1] == " ":
    adstrippable = adstrippable[:-1]
print("anythingdrabble (100, 200, 300, 400, or 500 words): \033[1m" + adstrippable.lower() + "\033[0m (" + adprompt + ")\n")
thefile.write("- [[" + adprompt + "][anythingdrabble]] (100, 200, 300, 400, or 500 words): *" + adstrippable.lower() + "*\n")

dove = "https://dove-drabbles.dreamwidth.org/?style=light"
dovepage = requests.get(dove)
dovesoup = BeautifulSoup(dovepage.content, "html.parser")
doveprompts = dovesoup.find_all("h3", string=lambda text: "prompt post" in text.lower())
dovesubsoup = BeautifulSoup(str(doveprompts[0]), "html.parser")
doveurl = dovesubsoup.find("a")
doveprompt = (doveurl["href"])
dovepromptnew = (doveurl["href"] + "?style=light")
dovepromptpage = requests.get(dovepromptnew)
dovepromptsoup = BeautifulSoup(dovepromptpage.content, "html.parser")
doveprompttext = dovepromptsoup.find(class_="entry-content")
dovetheprompt = doveprompttext.find("i")
print("dove-drabbles (any): \033[1m" + dovetheprompt.text.lower() + "\033[0m (" + doveprompt + ")\n")
thefile.write("- [[" + doveprompt + "][dove-drabbles]] (any): *" + dovetheprompt.text.lower() + "*\n")

with requests.Session() as s:
    response = s.post(login_url , data)
    zone = "https://drabble-zone.dreamwidth.org/tag/mod-post?style=light&tag=mod-post"
    zonepage = s.get(zone)
    zonesoup = BeautifulSoup(zonepage.content, "html.parser")
    zoneprompts = zonesoup.find_all("h3", string=lambda text: "challenge" in text.lower())
    zonesubsoup = BeautifulSoup(str(zoneprompts[0]), "html.parser")
    zoneurl = zonesubsoup.find("a")
    zoneprompt = (zoneurl["href"])
    zonepromptnew = (zoneurl["href"] + "?style=light")
    zonepromptpage = s.get(zonepromptnew)
    zonepromptsoup = BeautifulSoup(zonepromptpage.content, "html.parser")
    zoneprompttext = zonepromptsoup.find(class_="entry-content")
    zonetheprompt = zoneprompttext.find("strong")
    print("drabble-zone (100 or 200 words): \033[1m" + zonetheprompt.text.lower() + "\033[0m (" + zoneprompt + ")\n")
    thefile.write("- [[" + zoneprompt + "][drabble-zone]] (100 or 200 words): *" + zonetheprompt.text.lower() + "*\n")
    emotion = "https://emotion100.dreamwidth.org/tag/*modpost?style=light&tag=%2Amodpost"
    emotionpage = s.get(emotion)
    emotionsoup = BeautifulSoup(emotionpage.content, "html.parser")
    emotionprompts = emotionsoup.find_all("h3", string=lambda text: "prompt" in text.lower())
    emotionsubsoup = BeautifulSoup(str(emotionprompts[0]), "html.parser")
    emotionurl = emotionsubsoup.find("a")
    emotionprompt = (emotionurl["href"])
    emotionpromptnew = (emotionurl["href"] + "?style=light")
    emotionpromptpage = s.get(emotionpromptnew)
    emotionpromptsoup = BeautifulSoup(emotionpromptpage.content, "html.parser")
    emotionprompttext = emotionpromptsoup.find(class_="entry-content")
    emotiontheprompt = emotionprompttext.find_all("span")[-1]
    print("emotion100 (100 words or a multiple of 100): \033[1m" + emotiontheprompt.text.lower() + "\033[0m (" + emotionprompt + ")\n")
    thefile.write("- [[" + emotionprompt + "][emotion100]] (100 words or a multiple of 100): *" + emotiontheprompt.text.lower() + "*\n")

# for this one, have to get prompts from comments
ffa = "https://fail-fandomanon.dreamwidth.org/?style=light"
ffapage = requests.get(ffa)
ffasoup = BeautifulSoup(ffapage.content, "html.parser")
ffaprompts = ffasoup.find_all("h3", string=lambda text: "ffa dw post" in text.lower())
ffapromptstrim = [x for x in ffaprompts if "Placeholder" not in str(x)]
ffasubsoup = BeautifulSoup(str(ffapromptstrim[0]), "html.parser")
ffaurl = ffasubsoup.find("a")
ffaprompt = (ffaurl["href"])
ffapromptnew = (ffaprompt + "?style=light")
ffapromptpage = requests.get(ffapromptnew)
ffapromptsoup = BeautifulSoup(ffapromptpage.content, "html.parser")
ffaprompttext = ffapromptsoup.find(id="comments")
ffaresoup = BeautifulSoup(str(ffaprompttext), "html.parser")
ffatheprompt = ffaresoup.find_all("h4",text=True)
ffacent = []
i = 1
while i < 8:
    ffapromptnew = (ffaprompt + "?page=" + str(i) + "&style=light")
    ffapromptpage = requests.get(ffapromptnew)
    ffapromptsoup = BeautifulSoup(ffapromptpage.content, "html.parser")
    ffaprompttext = ffapromptsoup.find(id="comments")
    ffaresoup = BeautifulSoup(str(ffaprompttext), "html.parser")
    ffatheprompt = ffaresoup.find_all("h4",text=True)
    for each in ffatheprompt:
        if "100 words of" in (str(each.get_text())) or "100 Words of" in (str(each.get_text())) or "100 Words Of" in (str(each.get_text())):
            if "Re:" not in (str(each.get_text())) and "catch-up" not in (str(each.get_text())) and "Catch-Up" not in (str(each.get_text())):
                ffacent.append(str(each.get_text()))
    i += 1
if ffacent:
    ffacent = list(dict.fromkeys(ffacent))
    ffacentnew = []
    for x in ffacent:
        x = x[13:]
        if x != "" and not x.startswith(" Fills"):
            ffacentnew.append(x)
            ffaformat = "; ".join(ffacentnew)
    print("fail-fandomanon (any): \033[1m" + ffaformat.lower() + "\033[0m (" + ffaprompt + ")\n")
    thefile.write("- [[" + ffaprompt + "][fail-fandomanon]] (any): *" + ffaformat.lower() + "*\n")

    
# for this one, prompts are unavailable on tuesdays and wednesdays
weekprogress = datetime.now().weekday()
if not 0 < weekprogress < 3:
    fandom = "https://fandomweekly.dreamwidth.org/?style=light&tag=%23challenge"
    fandompage = requests.get(fandom)
    fandomsoup = BeautifulSoup(fandompage.content, "html.parser")
    fandomprompts = fandomsoup.find_all("h3", string=lambda text: "challenge post" in text.lower())
    fandomsubsoup = BeautifulSoup(str(fandomprompts[0]), "html.parser")
    fandomurl = fandomsubsoup.find("a")
    fandomprompt = (fandomurl["href"])
    fandompromptnew = (fandomurl["href"] + "?style=light")
    fandompromptpage = requests.get(fandompromptnew)
    fandompromptsoup = BeautifulSoup(fandompromptpage.content, "html.parser")
    fandomprompttext = fandompromptsoup.find(class_="entry-content")
    fandomtheprompt = fandomprompttext.find("td")
    print("fandomweekly (any, competitive): \033[1m" + fandomtheprompt.text.lower() + "\033[0m (" + fandomprompt + ")\n")
    thefile.write("- [[" + fandomprompt + "][fandomweekly]] (any, competitive): *" + fandomtheprompt.text.lower() + "*\n")

flash = "https://fan-flashworks.dreamwidth.org/?style=light&tag=admin"
flashpage = requests.get(flash)
flashsoup = BeautifulSoup(flashpage.content, "html.parser")
flashprompts = flashsoup.find_all("h3", string=lambda text: "challenge" in text.lower())
flashsubsoup = BeautifulSoup(str(flashprompts[0]), "html.parser")
flashurl = flashsubsoup.find("a")
flashprompt = (flashurl["href"])
flashpromptnew = (flashurl["href"] + "?style=light")
flashpromptpage = requests.get(flashpromptnew)
flashpromptsoup = BeautifulSoup(flashpromptpage.content, "html.parser")
flashprompttext = flashpromptsoup.find(class_="entry-content")
flashtheprompt = flashprompttext.find("center")
print("fan-flashworks (any, can’t post elsewhere until round is closed): \033[1m" + flashtheprompt.text.lower() + "\033[0m (" + flashprompt + ")\n")
thefile.write("- [[" + flashprompt + "][fan-flashworks]] (any, can’t post elsewhere until round is closed): *" + flashtheprompt.text.lower() + "*\n")

femslash = "https://femslashficlets.dreamwidth.org/tag/challenges?style=light&tag=challenges"
femslashpage = requests.get(femslash)
femslashsoup = BeautifulSoup(femslashpage.content, "html.parser")
femslashprompts = femslashsoup.find_all("h3", string=lambda text: "challenge" in text.lower())
femslashsubsoup = BeautifulSoup(str(femslashprompts[0]), "html.parser")
femslashurl = femslashsubsoup.find("a")
femslashprompt = (femslashurl["href"])
femslashpromptnew = (femslashurl["href"] + "?style=light")
femslashpromptpage = requests.get(femslashpromptnew)
femslashpromptsoup = BeautifulSoup(femslashpromptpage.content, "html.parser")
femslashprompttext = femslashpromptsoup.find(class_="entry-content")
femslashtheprompt = femslashprompttext.find("i")
if femslashtheprompt is not None:
    print("femslash-ficlets (100–1000 words, F/F): \033[1m" + femslashtheprompt.text.lower() + "\033[0m (" + femslashprompt + ")\n")
    thefile.write("- [[" + femslashprompt + "][femslashficlets]] (100 words or a multiple of 100): *" + femslashtheprompt.text.lower() + "*\n")

with requests.Session() as s:
    response = s.post(login_url , data)
    fffc = "https://fffc.dreamwidth.org/tag/!challenges?style=light&tag=%21challenges"
    fffcpage = s.get(fffc)
    fffcsoup = BeautifulSoup(fffcpage.content, "html.parser")
    fffcmadnessprompts = fffcsoup.find_all("h3", string=lambda text: "froday madness" in text.lower())
    fffcmadnesssubsoup = BeautifulSoup(str(fffcmadnessprompts[0]), "html.parser")
    fffcmadnessurl = fffcmadnesssubsoup.find("a")
    fffcmadnessprompt = (fffcmadnessurl["href"])
    fffcmadnesspromptnew = (fffcmadnessurl["href"] + "?style=light")
    fffcmadnesspromptpage = s.get(fffcmadnesspromptnew)
    fffcmadnesspromptsoup = BeautifulSoup(fffcmadnesspromptpage.content, "html.parser")
    fffcmadnessprompttext = fffcmadnesspromptsoup.find(class_="entry-content")
    fffcmadnesstheprompt = fffcmadnessprompttext.find("b")
    print("fffc madness (at least 2000 words): \033[1m" + fffcmadnesstheprompt.text.lower() + "\033[0m (" + fffcmadnessprompt + ")\n")
    thefile.write("- [[" + fffcmadnessprompt + "][fffc madness]] (at least 2000 words): *" + fffcmadnesstheprompt.text.lower() + "*\n")
    fffcregularprompts = fffcsoup.find_all("h3", string=lambda text: "regular challenge" in text.lower())
    fffcregularsubsoup = BeautifulSoup(str(fffcregularprompts[0]), "html.parser")
    fffcregularurl = fffcregularsubsoup.find("a")
    fffcregularprompt = (fffcregularurl["href"])
    fffcregularpromptnew = (fffcregularurl["href"] + "?style=light")
    fffcregularpromptpage = s.get(fffcregularpromptnew)
    fffcregularpromptsoup = BeautifulSoup(fffcregularpromptpage.content, "html.parser")
    fffcregularprompttext = fffcregularpromptsoup.find(class_="entry-content")
    fffcregulartheprompt = fffcregularprompttext.find("b")
    print("fffc regular challenge (at least 100 words): \033[1m" + fffcregulartheprompt.text.lower() + "\033[0m (" + fffcregularprompt + ")\n")
    thefile.write("- [[" + fffcregularprompt + "][fffc regular challenge]] (at least 100 words): *" + fffcregulartheprompt.text.lower() + "*\n")

ficlet = "https://ficlet-zone.dreamwidth.org/tag/challenge+post?style=light&tag=challenge+post"
ficletpage = requests.get(ficlet)
ficletsoup = BeautifulSoup(ficletpage.content, "html.parser")
ficletprompts = ficletsoup.find_all("h3", string=lambda text: "challenge" in text.lower())
ficletsubsoup = BeautifulSoup(str(ficletprompts[0]), "html.parser")
ficleturl = ficletsubsoup.find("a")
ficletprompt = (ficleturl["href"])
ficletpromptnew = (ficleturl["href"] + "?style=light")
ficletpromptpage = requests.get(ficletpromptnew)
ficletpromptsoup = BeautifulSoup(ficletpromptpage.content, "html.parser")
ficletprompttext = ficletpromptsoup.find(class_="entry-content")
ficlettheprompt = ficletprompttext.find("a")
print("ficlet-zone (any): \033[1m" + ficlettheprompt.text.lower() + "\033[0m (" + ficletprompt + ")\n")
thefile.write("- [[" + ficletprompt + "][ficlet-zone]] (any): *" + ficlettheprompt.text.lower() + "*\n")

# grabbing two different instances of the same tag within the post
vocab = "https://vocab-drabbles.dreamwidth.org/?style=light&tag=challenge"
vocabpage = requests.get(vocab)
vocabsoup = BeautifulSoup(vocabpage.content, "html.parser")
vocabprompts = vocabsoup.find_all("h3")
vocabsubsoup = BeautifulSoup(str(vocabprompts[0]), "html.parser")
vocaburl = vocabsubsoup.find("a")
vocabprompt = (vocaburl["href"])
vocabpromptnew = (vocaburl["href"] + "?style=light")
vocabpromptpage = requests.get(vocabpromptnew)
vocabpromptsoup = BeautifulSoup(vocabpromptpage.content, "html.parser")
vocablist = []
for listitem in vocabpromptsoup.find_all("strong"):
    vocablist.append(listitem.text.lower())
vocabformat = "; ".join(vocablist)
print("vocab-drabbles (50–500 words): \033[1m" + vocabformat + "\033[0m (" + vocabprompt + ")\n")
thefile.write("- [[" + vocabprompt + "][vocab-drabbles]] (50–500 words): *" + vocabformat + "*\n")