使用函数时，列表元素不分离

Question

我正在编写一些代码来从网站上抓取段落。虽然代码有点混乱和混乱，但我认为它仍然清晰易读。

唯一的问题是我在编写它时遇到了一个大障碍。当段落被写出时，它们似乎与该页面中的段落相连，我希望每个段落作为其单独的列表元素，而不是主列表中较小列表的一部分。

我想要的输出是与查询最相关的顶部段落。我已经有了所有的东西来检查哪些段落对查询的可靠性，但是就像我说的那样，当我将一页中的所有段落写到一个 txt 文件中进行检查时，它们似乎都组合在一起了。

这是我的代码：

#qresultsl is a list of links
for xa in range(0, qresultsl):
    URL=ALLresults[xa].format()
    URL=str(URL)
    URL=URL.replace("'","")
    URL=URL.replace("[","")
    URL=URL.replace("]","")
    pageURL=URL
    try:
        pr=requests.get(pageURL, headers=headers)
    except:
            print("Couldn't scrape ",pageURL)
            continue
    if pr.status_code==200:
        try:
            psoup=BeautifulSoup(pr.text, 'html.parser')
            paragraphs=[''.join(s.findAll(text=True))for s in
            psoup.findAll('p')]
            presults.append(paragraphs)
        except:
            print("Couldn't scrape ", pageURL)
            continue
    else:
            print("Couldn't scrape ",pageURL)
            continue
# Results

print("\r")
print(len(presults)," websites scraped of ", numresults)
print(len(presults)," pages of content ready for next phase of processing.")

paraList = []
for i in presults:
    #make all keywords one big list
    paraList = sum(presults, [])

presults = paraList
    
cleanparagraphs=[]
rangenum=len(presults)
print(presults)
def cleanresults():
  ct=0
  for dd in range(0,rangenum):
    cleaned=presults[ct]
    cleaned=str(cleaned)
    cleaned=cleaned.replace("/","")
    cleaned=cleaned.replace("]","")
    cleaned=cleaned.replace("[","")
    cleaned=cleaned.replace("'","")
    cleaned=cleaned.replace("\n","")
    NEWITEM=cleaned
    ct=ct+1
    cleanparagraphs.append(NEWITEM)
cleanresults()

presults = cleanparagraphs

paragraphs = []

for z in range(len(presults)):
    pagei=presults[z]
    pagei=str(pagei)
    pagei=pagei.replace("[","")
    pagei=pagei.replace("'","")
    pagei=pagei.replace("]","")
    pageHtml = pagei #i wasn't "stupid". 
    paragraphs.append(presults[z])
'''with open('paragraphs.txt', 'r') as f:
    paragraphs = ast.literal_eval(f.read())
'''
'''for i in paragraphs:
    #make all paragraphs one big list
    paragraphs = sum(paragraphs, [])'''
resultspara=[]
for le in paragraphs: 
    if le not in resultspara: 
        resultspara.append(le) 
paragraphs=resultspara
og=len(presults)
nl=len(paragraphs)
removed=og-nl
print(removed, " duplicates removed")
lst = []
cp=0
for para in paragraphs:
    lst.append(paragraphs[cp].lower())
    cp=cp+1
rem=str(lst)
rem=rem.replace("\r","")
rem=rem.replace("\n","")
rem=rem.replace('"\r\n','')
final_list=rem.split("#####")
phrase1 = query
phrase2 = query2
phrase3 = query3
phrase4 = query4
paragraphs=final_list

ammntRemoved = 0
for i in paragraphs:
    if len(i) < 20:
        paragraphs.remove(i)
        ammntRemoved = ammntRemoved + 1
print("removed " + str(ammntRemoved) + " small lines")

randomVariable = []
for i in paragraphs:
    randomVariable = sum(paragraphs, [])

paragraphs = randomVariable
def getRelated(phrase):
    splitWords = phrase.split() #split the sentence for proccessing
    associatedWords = [splitWords] #add spitwords to associatedWords; associatedWords will be     the main variable to add processed words to
    finalWords = [] #created the variable that will have the final parsde and deduped list 
    
    for word in splitWords:
        #get associated words for each word in the phrase
        html = requests.get("https://api.wordassociations.net/associations/v1.0/json/search?apikey=8c124543-3a0d-4ac9-b6b4-cda92d7d1411&text="+ word + "&lang=en")
        theJson = html.text
        source = json.loads(theJson)
        try:
            associatedWords.append([source["response"][0]["items"][0]["item"],source["response"][0]["items"][1]["item"],source["response"][0]["items"][2]["item"],source["response"][0]["items"][3]["item"],source["response"][0]["items"][4]["item"],source["response"][0]["items"][5]["item"]])
            numass=len(associatedWords)
            print(numass, " associations found for ", word)
        except:
                print("tested word - " + word + " - had no asocciations")
    
    for i in associatedWords:
        #make all keywords one big list
        finalWords = sum(associatedWords, [])
    
    relatedKeywords = []
    for word in finalWords:
        #make finalwords lowercase
        relatedKeywords.append(word.lower())
        return finalWords
#took that out and replaced it with a for loop that does them all beforehand
phrase1 = getRelated(query)
phrase2 = getRelated(query2)
phrase3 = getRelated(query3)
phrase4 = getRelated(query4)

topic = {}
subHead1 = {}
subHead2 = {}
subHead3 = {}

def getGoodParagraphs(keywords, dictionary):
    global length
    for para in paragraphs:
        #get the keyword frequencies in each paragraph
        x = 0
        for keyword in keywords:
            added = para.count(keyword)
            x = x + added
            dictionary[para] = x

#get the lengths of used paragraphs
length = 0
length1 = 0
length2 = 0
length3 = 0

def getLen(lengthVar, dictionary):
    for i in range(100):
        try:
            #count the number of words
            lengthVar = lengthVar + len(dictionary[i].split())
        except:
            #break if theres no more paragraphs in said list
            break
    
getGoodParagraphs(phrase1, topic)
getGoodParagraphs(phrase2, subHead1)
getGoodParagraphs(phrase3, subHead2)
getGoodParagraphs(phrase4, subHead3)

getLen(length, topic)
getLen(length1, subHead1)
getLen(length2, subHead2)
getLen(length3, subHead3)

#sort paragraphs least to greatest
topic = sorted(topic, key=lambda k: topic[k], reverse=True)
subHead1 = sorted(subHead1, key=lambda k: subHead1[k], reverse=True)
subHead2 = sorted(subHead2, key=lambda k: subHead2[k], reverse=True)
subHead3 = sorted(subHead3, key=lambda k: subHead3[k], reverse=True)

def appendTop10(inputList, outputList):
    try:
        for i in range(3):
            outputList.append(inputList[i])
    except:
            print("> Wasnt able to append all 3 paragraphs")

finalTopic = []
finalSubHead1 = []
finalSubHead2 = []
finalSubHead3 = []

appendTop10(topic, finalTopic)
appendTop10(subHead1, finalSubHead1)
appendTop10(subHead2, finalSubHead2)
appendTop10(subHead3, finalSubHead3)

with open("article.txt", "w") as outputFile:
  count=0
  count2=0
  count3=0
  count4=0
  for i in finalTopic:   
      filename = 'text.txt'
      with open(filename, mode="w") as outfile:  # also, tried mode="rb"
          for s in finalTopic:
              outfile.write("%s\n" % s)
          for s in finalSubHead1:
              outfile.write("%s\n" % s)
          for s in finalSubHead2:
              outfile.write("%s\n" % s)
          for s in finalSubHead3:
              outfile.write("%s\n" % s)
print("DONE")

没有对每个类别的顶部段落进行排序，我做错了什么？

我急需帮助，提前致谢

Answer 1

你总是可以这样做：

page_name = []

for paragraph in page:
   page_name.append(paragraph)

然后您可以通过打印每个列表来输出每个段落：

for page in page_name:
   print(page)