爬虫大作业

f = open("C:/Users/ZD/PycharmProjects/test/test.txt", 'w+', encoding='utf8')
import jieba
import requests
from bs4 import BeautifulSoup


def songlist(url):
    res = requests.get(url)
    res.encoding = 'UTF-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    songname = soup.select('.song')
    for i in songname[1:]:
        url = i.select('a')[0].attrs['href']
        songread(url)


def songread(url):
    f = open("C:/Users/ZD/PycharmProjects/test/test.txt", 'w+', encoding='utf8')
    res = requests.get(url)
    res.encoding = 'UTF-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    song = soup.select('.lrcItem')
    for i in song:
        f.write(i.text)


songlist('http://www.kuwo.cn/geci/a_336/?')
f = open("C:/Users/ZD/PycharmProjects/test/test.txt", 'r', encoding='utf8')
str = f.read()
f.close()

wordList = jieba.cut(str)
wordList = list(jieba.cut(str))

wordDic = {}
for i in set(wordList):
    wordDic[i] = wordList.count(i)

sort_word = sorted(wordDic.items(), key=lambda d: d[1], reverse=True)
for i in range(60):
    print(sort_word[i])

fo = open("C:/Users/ZD/PycharmProjects/test/test1.txt", 'w', encoding='utf8')
for i in range(60):
    fo.write(sort_word[i][0] + '\n')

fo.close()

转载于:https://www.cnblogs.com/XiaoFengLuo/p/9077183.html