python requests做爬蟲爬取oxford詞典單詞音標
阿新 • • 發佈:2018-12-16
import requests import re def phonetic_spelling(word): word=word.replace(" ","_") phoneticSpelling="" #url的格式有規律 request=requests.get("https://en.oxforddictionaries.com/definition/"+word) html=request.text #檢視網頁發現音標所處的行HTML格式有規律 使用正則表示式描述 regularExpression=r'<span\s+class="phoneticspelling">/([^\/]*)/</span>' matchObject=re.search(regularExpression,html,re.I) if matchObject: if matchObject.group(1): phoneticSpelling=matchObject.group(1) print("\nphoneticSpelling: ",word,"--->",phoneticSpelling) else: print("\nword \""+word+"\" has no phonetic spelling in the dictionary") else: print("\nword \""+word+"\" has no phonetic spelling in the dictionary") return phoneticSpelling #測試 print(phonetic_spelling("Chinese")) print(phonetic_spelling("English")) print(phonetic_spelling("translation")) print(phonetic_spelling("language")) print(phonetic_spelling("crawler"))