Handle exceptions properly in prompt scraper

10 months ago · 31f4a80ddc
parent bd85f72186
commit 31f4a80ddc
1 changed files with 376 additions and 328 deletions
--- a/promptscrape.py
+++ b/promptscrape.py
@ -18,6 +18,7 @@ today = int(date.today().strftime("%d"))
 month = str(date.today().strftime("%B"))
 monthstring = ".*" + month + ".*"

+try:
    cent = "https://100words.dreamwidth.org/tag/!prompt?style=light&tag=%21prompt"
    centpage = requests.get(cent)
    centsoup = BeautifulSoup(centpage.content, "html.parser")
@ -32,6 +33,8 @@ 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")
+except:
+    pass

 # 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
 # now defunct??
@ -65,6 +68,7 @@ thefile.write("- [[" + centprompt + "][100words]] (100 words): *" + centthepromp
 # thefile.write("- [[" + thirtyoneprompt + "][31-days]] (any): *" + thirtyonetheprompt.lower() + "*\n")


+try:
    ad = "https://anythingdrabble.dreamwidth.org/tag/mod!+post?style=light&tag=mod%21+post"
    adpage = requests.get(ad)
    adsoup = BeautifulSoup(adpage.content, "html.parser")
@ -82,7 +86,10 @@ 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")
+except:
+    pass

+try:
    dove = "https://dove-drabbles.dreamwidth.org/?style=light"
    dovepage = requests.get(dove)
    dovesoup = BeautifulSoup(dovepage.content, "html.parser")
@ -97,7 +104,10 @@ 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")
+except:
+    pass

+try:
    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"
@ -128,8 +138,11 @@ with requests.Session() as s:
        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")
+except:
+    pass

 # for this one, have to get prompts from comments
+try:
    ffa = "https://fail-fandomanon.dreamwidth.org/?style=light"
    ffapage = requests.get(ffa)
    ffasoup = BeautifulSoup(ffapage.content, "html.parser")
@ -168,9 +181,12 @@ if ffacent:
                ffaformat = "; ".join(ffacentnew)
        print("fail-fandomanon (any): \033[1m" + ffaformat.lower() + "\033[0m (" + ffaprompt + ")\n")
        thefile.write("- [[" + ffaprompt + "][fail-fandomanon]] (any): *" + ffaformat.lower() + "*\n")
+except:
+    pass

    
 # for this one, prompts are unavailable on tuesdays and wednesdays
+try:
    weekprogress = datetime.now().weekday()
    if not 0 < weekprogress < 3:
        fandom = "https://fandomweekly.dreamwidth.org/?style=light&tag=%23challenge"
@ -187,7 +203,10 @@ if not 0 < weekprogress < 3:
        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")
+except:
+    pass

+try:
    flash = "https://fan-flashworks.dreamwidth.org/?style=light&tag=admin"
    flashpage = requests.get(flash)
    flashsoup = BeautifulSoup(flashpage.content, "html.parser")
@ -202,7 +221,10 @@ 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")
+except:
+    pass

+try:
    femslash = "https://femslashficlets.dreamwidth.org/tag/challenges?style=light&tag=challenges"
    femslashpage = requests.get(femslash)
    femslashsoup = BeautifulSoup(femslashpage.content, "html.parser")
@ -218,7 +240,10 @@ 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")
+except:
+    pass

+try:
    with requests.Session() as s:
        response = s.post(login_url , data)
        fffc = "https://fffc.dreamwidth.org/tag/!challenges?style=light&tag=%21challenges"
@ -267,7 +292,10 @@ with requests.Session() as s:
        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")
+except:
+    pass

+try:
    ficlet = "https://ficlet-zone.dreamwidth.org/tag/challenge+post?style=light&tag=challenge+post"
    ficletpage = requests.get(ficlet)
    ficletsoup = BeautifulSoup(ficletpage.content, "html.parser")
@ -282,8 +310,11 @@ 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")
+except:
+    pass

 # first calculate the hour of the month …
+try:
    hourselapsed = (today - 1) * 24
    hourstoday = int(datetime.now().strftime("%H"))
    currenthour = (hourselapsed + hourstoday)
@ -305,7 +336,10 @@ with requests.Session() as s:
        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")
+except:
+    pass

+try:
    if 30 > today > 21:
        ssbingo = "https://sweetandshort.dreamwidth.org/tag/challenge:+bingo?style=light&tag=challenge:+bingo"
        ssbingopage = requests.get(ssbingo)
@ -326,7 +360,10 @@ if 30 > today > 21:
            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")
+except:
+    pass

+try:
    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)
@ -351,7 +388,10 @@ if 16 > today > 7:
        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")
+except:
+    pass

+try:
    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")
@ -370,7 +410,10 @@ 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")
+except:
+    pass

+try:
    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)
@ -386,7 +429,10 @@ if today > 14:
        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")
+except:
+    pass

+try:
    vocab = "https://vocab-drabbles.dreamwidth.org/?style=light&tag=challenge"
    vocabpage = requests.get(vocab)
    vocabsoup = BeautifulSoup(vocabpage.content, "html.parser")
@ -401,3 +447,5 @@ vocabprompttext = vocabpromptsoup.find(class_="entry-content")
    vocabtheprompt = vocabprompttext.find("strong")
    print("vocab-drabbles (50–500 words): \033[1m" + vocabtheprompt.text.lower() + "\033[0m (" + vocabprompt + ")\n")
    thefile.write("- [[" + vocabprompt + "][vocab-drabbles]] (50–500 words): *" + vocabtheprompt.text.lower() + "*\n")
+except:
+    pass