tre/utils
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update prompt communities

Browse source
This commit is contained in:
trémeur 2023-03-22 14:53:40 +00:00
parent 2c546a38fe
commit b87e0fbfbc
1 changed files with 162 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

199
promptscrape.py
View file

@ -14,6 +14,10 @@ if os.path.exists("prompts.org"):
thefile = open("prompts.org", "a") thefile = open("prompts.org", "a")
today = int(date.today().strftime("%d"))
month = str(date.today().strftime("%B"))
monthstring = ".*" + month + ".*"
cent = "https://100words.dreamwidth.org/tag/!prompt?style=light&tag=%21prompt" cent = "https://100words.dreamwidth.org/tag/!prompt?style=light&tag=%21prompt"
centpage = requests.get(cent) centpage = requests.get(cent)
centsoup = BeautifulSoup(centpage.content, "html.parser") centsoup = BeautifulSoup(centpage.content, "html.parser")
@ -30,36 +34,35 @@ print("100words (100 words): \033[1m" + centtheprompt.text.lower() + "\033[0m ("
thefile.write("- [[" + centprompt + "][100words]] (100 words): *" + centtheprompt.text.lower() + "*\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 # 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")) # now defunct??
month = str(date.today().strftime("%B")) # monthstring = ".*" + month + ".*"
monthstring = ".*" + month + ".*" # thirtyone = "https://31-days.dreamwidth.org/tag/!prompts?style=light&tag=%21prompts"
thirtyone = "https://31-days.dreamwidth.org/tag/!prompts?style=light&tag=%21prompts" # thirtyonepage = requests.get(thirtyone)
thirtyonepage = requests.get(thirtyone) # thirtyonesoup = BeautifulSoup(thirtyonepage.content, "html.parser")
thirtyonesoup = BeautifulSoup(thirtyonepage.content, "html.parser") # thirtyoneprompts = thirtyonesoup.find_all("h3", string = re.compile(monthstring))
thirtyoneprompts = thirtyonesoup.find_all("h3", string = re.compile(monthstring)) # thirtyonesubsoup = BeautifulSoup(str(thirtyoneprompts[0]), "html.parser")
thirtyonesubsoup = BeautifulSoup(str(thirtyoneprompts[0]), "html.parser") # thirtyoneurl = thirtyonesubsoup.find("a")
thirtyoneurl = thirtyonesubsoup.find("a") # thirtyoneprompt = (thirtyoneurl["href"])
thirtyoneprompt = (thirtyoneurl["href"]) # thirtyonepromptnew = (thirtyoneurl["href"] + "?style=light")
thirtyonepromptnew = (thirtyoneurl["href"] + "?style=light") # thirtyonepromptpage = requests.get(thirtyonepromptnew)
thirtyonepromptpage = requests.get(thirtyonepromptnew) # thirtyonepromptsoup = BeautifulSoup(thirtyonepromptpage.content, "html.parser")
thirtyonepromptsoup = BeautifulSoup(thirtyonepromptpage.content, "html.parser") # thirtyoneprompttext = thirtyonepromptsoup.find(class_="entry-content")
thirtyoneprompttext = thirtyonepromptsoup.find(class_="entry-content") # if "<ol>" in str(thirtyoneprompttext):
if "<ol>" in str(thirtyoneprompttext): # thirtyonetheprompt = thirtyoneprompttext.select("ol > li")[today - 1].get_text(strip=True)
thirtyonetheprompt = thirtyoneprompttext.select("ol > li")[today - 1].get_text(strip=True) # else:
else: # interprompt = list(thirtyoneprompttext.stripped_strings)
interprompt = list(thirtyoneprompttext.stripped_strings) # thirtyonelist = []
thirtyonelist = [] # for prompt in interprompt:
for prompt in interprompt: # if len(prompt) < 5:
if len(prompt) < 5: # promptnum = interprompt.index(prompt)
promptnum = interprompt.index(prompt) # newnum = promptnum + 1
newnum = promptnum + 1 # thirtyonelist.append(prompt + interprompt[newnum])
thirtyonelist.append(prompt + interprompt[newnum]) # else:
else: # thirtyonelist.append(prompt)
thirtyonelist.append(prompt) # intsearch = str(today) + "."
intsearch = str(today) + "." # thirtyonetheprompt = str([item for item in thirtyonelist if item.startswith(intsearch)])[2:-2]
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")
print("31-days (any): \033[1m" + thirtyonetheprompt.lower() + "\033[0m (" + thirtyoneprompt + ")\n") # thefile.write("- [[" + thirtyoneprompt + "][31-days]] (any): *" + thirtyonetheprompt.lower() + "*\n")
thefile.write("- [[" + thirtyoneprompt + "][31-days]] (any): *" + thirtyonetheprompt.lower() + "*\n")
ad = "https://anythingdrabble.dreamwidth.org/tag/mod!+post?style=light&tag=mod%21+post" ad = "https://anythingdrabble.dreamwidth.org/tag/mod!+post?style=light&tag=mod%21+post"
@ -221,6 +224,17 @@ with requests.Session() as s:
fffc = "https://fffc.dreamwidth.org/tag/!challenges?style=light&tag=%21challenges" fffc = "https://fffc.dreamwidth.org/tag/!challenges?style=light&tag=%21challenges"
fffcpage = s.get(fffc) fffcpage = s.get(fffc)
fffcsoup = BeautifulSoup(fffcpage.content, "html.parser") fffcsoup = BeautifulSoup(fffcpage.content, "html.parser")
if 18 > today > 9:
fffclittleprompts = fffcsoup.find_all("h3", string=lambda text: "little special" in text.lower())
fffclittlesubsoup = BeautifulSoup(str(fffclittleprompts[0]), "html.parser")
fffclittleurl = fffclittlesubsoup.find("a")
fffclittleprompt = (fffclittleurl["href"])
fffclittlepromptnew = (fffclittleurl["href"] + "?style=light")
fffclittlepromptpage = s.get(fffclittlepromptnew)
fffclittlepromptsoup = BeautifulSoup(fffclittlepromptpage.content, "html.parser")
fffclittleprompttext = fffclittlepromptsoup.find("h3")
print("fffc little special (at least 100 words): \033[1m" + fffclittleprompttext.text.lower() + "\033[0m (" + fffclittleprompt + ")\n")
thefile.write("- [[" + fffclittleprompt + "][fffc little special]] (at least 100 words): *" + fffclittleprompttext.text.lower() + "*\n")
fffcmadnessprompts = fffcsoup.find_all("h3", string=lambda text: "froday madness" in text.lower()) fffcmadnessprompts = fffcsoup.find_all("h3", string=lambda text: "froday madness" in text.lower())
fffcmadnesssubsoup = BeautifulSoup(str(fffcmadnessprompts[0]), "html.parser") fffcmadnesssubsoup = BeautifulSoup(str(fffcmadnessprompts[0]), "html.parser")
fffcmadnessurl = fffcmadnesssubsoup.find("a") fffcmadnessurl = fffcmadnesssubsoup.find("a")
@ -232,6 +246,16 @@ with requests.Session() as s:
fffcmadnesstheprompt = fffcmadnessprompttext.find("b") fffcmadnesstheprompt = fffcmadnessprompttext.find("b")
print("fffc madness (at least 2000 words): \033[1m" + fffcmadnesstheprompt.text.lower() + "\033[0m (" + fffcmadnessprompt + ")\n") 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") thefile.write("- [[" + fffcmadnessprompt + "][fffc madness]] (at least 2000 words): *" + fffcmadnesstheprompt.text.lower() + "*\n")
fffcmonthlyprompts = fffcsoup.find_all("h3", string=re.compile(monthstring))
fffcmonthlysubsoup = BeautifulSoup(str(fffcmonthlyprompts[0]), "html.parser")
fffcmonthlyurl = fffcmonthlysubsoup.find("a")
fffcmonthlyprompt = (fffcmonthlyurl["href"])
fffcmonthlypromptnew = (fffcmonthlyurl["href"] + "?style=light")
fffcmonthlypromptpage = s.get(fffcmonthlypromptnew)
fffcmonthlypromptsoup = BeautifulSoup(fffcmonthlypromptpage.content, "html.parser")
fffcmonthlyprompttext = fffcmonthlypromptsoup.find("h3")
print("fffc monthly special (usually at least 500 words): \033[1m" + fffcmonthlyprompttext.text.lower() + "\033[0m (" + fffcmonthlyprompt + ")\n")
thefile.write("- [[" + fffcmonthlyprompt + "][fffc monthly special]] (usually at least 500 words): *" + fffcmonthlyprompttext.text.lower() + "*\n")
fffcregularprompts = fffcsoup.find_all("h3", string=lambda text: "regular challenge" in text.lower()) fffcregularprompts = fffcsoup.find_all("h3", string=lambda text: "regular challenge" in text.lower())
fffcregularsubsoup = BeautifulSoup(str(fffcregularprompts[0]), "html.parser") fffcregularsubsoup = BeautifulSoup(str(fffcregularprompts[0]), "html.parser")
fffcregularurl = fffcregularsubsoup.find("a") fffcregularurl = fffcregularsubsoup.find("a")
@ -259,7 +283,110 @@ ficlettheprompt = ficletprompttext.find("a")
print("ficlet-zone (any): \033[1m" + ficlettheprompt.text.lower() + "\033[0m (" + ficletprompt + ")\n") print("ficlet-zone (any): \033[1m" + ficlettheprompt.text.lower() + "\033[0m (" + ficletprompt + ")\n")
thefile.write("- [[" + ficletprompt + "][ficlet-zone]] (any): *" + ficlettheprompt.text.lower() + "*\n") thefile.write("- [[" + ficletprompt + "][ficlet-zone]] (any): *" + ficlettheprompt.text.lower() + "*\n")
# grabbing two different instances of the same tag within the post # first calculate the hour of the month …
hourselapsed = (today - 1) * 24
hourstoday = int(datetime.now().strftime("%H"))
currenthour = (hourselapsed + hourstoday)
with requests.Session() as s:
response = s.post(login_url , data)
hourly = "https://hourlyprompts.dreamwidth.org/?style=light"
hourlypage = s.get(hourly)
hourlysoup = BeautifulSoup(hourlypage.content, "html.parser")
hourlyprompts = hourlysoup.find_all("h3", string=re.compile(monthstring))
hourlysubsoup = BeautifulSoup(str(hourlyprompts[0]), "html.parser")
hourlyurl = hourlysubsoup.find("a")
hourlyprompt = (hourlyurl["href"])
hourlypromptnew = (hourlyurl["href"] + "?style=light")
hourlypromptpage = s.get(hourlypromptnew)
hourlypromptsoup = BeautifulSoup(hourlypromptpage.content, "html.parser")
hourlyprompttext = hourlypromptsoup.find(class_="entry-content")
searchstring = r"<br/>" + re.escape(str(currenthour)) + r"\. .*?<br/>"
hourlypromptmedian = re.findall(searchstring, str(hourlyprompttext))
hourlypromptthishour = str(hourlypromptmedian[0])[5:-5]
print("hourlyprompts (any): \033[1m" + hourlypromptthishour.lower() + "\033[0m (" + hourlyprompt + ")\n")
thefile.write("- [[" + hourlyprompt + "][hourlyprompts]] (any): *" + hourlypromptthishour.lower() + "*\n")
if 30 > today > 21:
ssbingo = "https://sweetandshort.dreamwidth.org/tag/challenge:+bingo?style=light&tag=challenge:+bingo"
ssbingopage = requests.get(ssbingo)
ssbingosoup = BeautifulSoup(ssbingopage.content, "html.parser")
ssbingoprompts = ssbingosoup.find_all("h3")
ssbingosubsoup = BeautifulSoup(str(ssbingoprompts[0]), "html.parser")
ssbingourl = ssbingosubsoup.find("a")
ssbingoprompt = (ssbingourl["href"])
ssbingopromptnew = (ssbingourl["href"] + "?style=light")
ssbingopromptpage = requests.get(ssbingopromptnew)
ssbingopromptsoup = BeautifulSoup(ssbingopromptpage.content, "html.parser")
ssbingoprompttext = ssbingopromptsoup.find(class_="entry-content")
ssbingotheprompt = ssbingoprompttext.find_all("td")
ssbingoclean = []
for prompt in ssbingotheprompt:
newprompt = re.sub("<.*?>","",str(prompt))
ssbingoclean.append(newprompt)
ssbingofinal = "; ".join(ssbingoclean).lower()
print("sweet and short bingo (up to 300 words for two prompts, up to 600 words for four prompts): \033[1m" + ssbingofinal + "\033[0m (" + ssbingoprompt + ")\n")
thefile.write("- [[" + ssbingoprompt + "][sweet and short bingo]] (up to 300 words for two prompts, up to 600 words for four prompts): *" + ssbingofinal + "*\n")
if 16 > today > 7:
ssquicky = "https://sweetandshort.dreamwidth.org/tag/!new+challenge,challenge:+comment+quicky?mode=and&style=light&tag=%21new+challenge,challenge:+comment+quicky"
ssquickypage = requests.get(ssquicky)
ssquickysoup = BeautifulSoup(ssquickypage.content, "html.parser")
ssquickyprompts = ssquickysoup.find_all("h3")
ssquickysubsoup = BeautifulSoup(str(ssquickyprompts[0]), "html.parser")
ssquickyurl = ssquickysubsoup.find("a")
ssquickyprompt = (ssquickyurl["href"])
# deliberately not using style=light here so we can get at the comment contents
ssquickypromptnew = (ssquickyurl["href"])
ssquickypromptpage = requests.get(ssquickypromptnew)
ssquickypromptsoup = BeautifulSoup(ssquickypromptpage.content, "html.parser")
promptcatch = ".*New Prompts Here"
# ssquickytheprompt = ssquickypromptsoup.find_all("h4",string = re.compile(promptcatch))
ssquickytheprompt = ssquickypromptsoup.find_all(class_="comment")
ssquickycomments = []
for comment in ssquickytheprompt:
if re.search("New Prompts Here",str(comment)):
commenttext = re.findall(r"<div class=\"comment-content\".*?</div>",str(comment))
commentprompt = re.sub("<.*?>","",str(commenttext))
ssquickycomments.append(str(commentprompt)[2:-2])
ssquickycprompt = "; ".join(ssquickycomments)
print("sweet and short comment quicky (up to 99 words): \033[1m" + ssquickycprompt.lower() + "\033[0m (" + ssquickyprompt + ")\n")
thefile.write("- [[" + ssquickyprompt + "][sweet and short comment quicky]] (up to 99 words): *" + ssquickycprompt.lower() + "*\n")
ssmonthly = "https://sweetandshort.dreamwidth.org/tag/!new+challenge,challenge:+10+out+of+20?mode=and&style=light&tag=%21new+challenge,challenge:+10+out+of+20"
ssmonthlypage = requests.get(ssmonthly)
ssmonthlysoup = BeautifulSoup(ssmonthlypage.content, "html.parser")
ssmonthlyprompts = ssmonthlysoup.find_all("h3")
ssmonthlysubsoup = BeautifulSoup(str(ssmonthlyprompts[0]), "html.parser")
ssmonthlyurl = ssmonthlysubsoup.find("a")
ssmonthlyprompt = (ssmonthlyurl["href"])
ssmonthlypromptnew = (ssmonthlyurl["href"] + "?style=light")
ssmonthlypromptpage = requests.get(ssmonthlypromptnew)
ssmonthlypromptsoup = BeautifulSoup(ssmonthlypromptpage.content, "html.parser")
ssmonthlyprompttext = ssmonthlypromptsoup.find(class_="entry-content")
ssmonthlypromptmedian = re.findall(r"<a name=\"cutid1\">.*", str(ssmonthlyprompttext))
ssmonthlypromptstripone = re.sub("<.*?>","",str(ssmonthlypromptmedian))
ssmonthlypromptstriptwo = re.sub("([a-z])- ","\\1; ",str(ssmonthlypromptstripone))
ssmonthlypromptstripthree = re.sub("- ","",str(ssmonthlypromptstriptwo))
ssmonthlypromptfinal = str(ssmonthlypromptstripthree)[2:-2]
print("sweet and short monthly prompts (up to 300 words [0–9 prompts], up to 900 words [10–19 prompts], any [20 prompts]): \033[1m" + ssmonthlypromptfinal + "\033[0m (" + ssmonthlyprompt + ")\n")
thefile.write("- [[" + ssmonthlyprompt + "][sweet and short monthly prompts]] (up to 300 words [0–9 prompts], up to 900 words [10–19 prompts], any [20 prompts]): *" + ssmonthlypromptfinal + "*\n")
if today > 14:
sspicture = "https://sweetandshort.dreamwidth.org/tag/!new+challenge,challenge:+picture+prompt+fun?mode=and&style=light&tag=%21new+challenge,challenge:+picture+prompt+fun"
sspicturepage = requests.get(sspicture)
sspicturesoup = BeautifulSoup(sspicturepage.content, "html.parser")
monthstring = ".*" + month + ".*"
sspictureprompts = sspicturesoup.find_all("h3", string=re.compile(monthstring))
sspicturesubsoup = BeautifulSoup(str(sspictureprompts[0]), "html.parser")
sspictureurl = sspicturesubsoup.find("a")
sspictureprompt = (sspictureurl["href"])
sspicturepromptnew = (sspictureurl["href"] + "?style=light")
sspicturepromptpage = requests.get(sspicturepromptnew)
sspicturepromptsoup = BeautifulSoup(sspicturepromptpage.content, "html.parser")
sspictureprompttext = sspicturepromptsoup.find("h3")
print("sweet and short picture prompts (up to 300 words): \033[1m" + sspictureprompttext.text.lower() + "\033[0m (" + sspictureprompt + ")\n")
thefile.write("- [[" + sspictureprompt + "][sweet and short picture prompts]] (up to 300 words): *" + sspictureprompttext.text.lower() + "*\n")
vocab = "https://vocab-drabbles.dreamwidth.org/?style=light&tag=challenge" vocab = "https://vocab-drabbles.dreamwidth.org/?style=light&tag=challenge"
vocabpage = requests.get(vocab) vocabpage = requests.get(vocab)
vocabsoup = BeautifulSoup(vocabpage.content, "html.parser") vocabsoup = BeautifulSoup(vocabpage.content, "html.parser")
@ -270,9 +397,7 @@ vocabprompt = (vocaburl["href"])
vocabpromptnew = (vocaburl["href"] + "?style=light") vocabpromptnew = (vocaburl["href"] + "?style=light")
vocabpromptpage = requests.get(vocabpromptnew) vocabpromptpage = requests.get(vocabpromptnew)
vocabpromptsoup = BeautifulSoup(vocabpromptpage.content, "html.parser") vocabpromptsoup = BeautifulSoup(vocabpromptpage.content, "html.parser")
vocablist = [] vocabprompttext = vocabpromptsoup.find(class_="entry-content")
for listitem in vocabpromptsoup.find_all("strong"): vocabtheprompt = vocabprompttext.find("strong")
vocablist.append(listitem.text.lower()) print("vocab-drabbles (50–500 words): \033[1m" + vocabtheprompt.text.lower() + "\033[0m (" + vocabprompt + ")\n")
vocabformat = "; ".join(vocablist) thefile.write("- [[" + vocabprompt + "][vocab-drabbles]] (50–500 words): *" + vocabtheprompt.text.lower() + "*\n")
print("vocab-drabbles (50–500 words): \033[1m" + vocabformat + "\033[0m (" + vocabprompt + ")\n")
thefile.write("- [[" + vocabprompt + "][vocab-drabbles]] (50–500 words): *" + vocabformat + "*\n")