网易云评论爬虫
作者:互联网
import requests
import json
import my_fake_useragent
import threading
def getHTMLText(url):
try:
headers = {"user-agent": my_fake_useragent.UserAgent().random()}
r = requests.get(url, headers=headers)
r.raise_for_status()
# r.encoding = r.apparent_encoding #这里自动识别编码方式会乱码,注释掉就行了
return r.text
except:
#print("getHTMLText失败!")
#return ""
pass
def fillList(music_id, url, commentlist):
new_url = url + "{0}".format(music_id)
#print("new_url======>", new_url)
html = getHTMLText(new_url)
#print("html======>", html)
try:
json_dict = json.loads(html) # 利用json方法把json类型转成dict
#print(json_dict)
# likedCount 点赞数量
likedCount = json_dict['hotComments'][0]['likedCount']
# print(type(likedCount))
#print("点赞数======>",likedCount)
# 如果点赞数大于30万
if likedCount > 300000:
comments = json_dict['hotComments']
# print("comments======>",comments)
# print("type======>",type(comments))
# print("type======>",len(comments))
# commentlist.append([item['user']['nickname'], item['content']])
m = "点赞数===>" + str(likedCount) + " 歌曲ID===>" + str(music_id) + " 用户===>" + comments[0]['user']['nickname'] + " 评论===>" + comments[0][
'content']
print(m)
save(m, "./网抑云.txt")
except:
pass
def save(m, path):
with open(path, 'a', encoding='utf-8') as f:
f.write(m + "\n")
f.close()
def main():
mutex = threading.Lock()
mutex.acquire()
i = 254574
mutex.release()
#新歌的ID 1882041535 18亿
while i <= 2000000000:
music_id = str(i)
url = "http://music.163.com/api/v1/resource/comments/R_SO_4_"
commentlist = []
fillList(music_id, url, commentlist)
i = i + 1
#print("url_id======>",music_id)
def thread():
for i in range(6):
t = threading.Thread(target=main())
t.start()
main_thread = threading.currentThread()
for t in threading.enumerate():
if t is main_thread:
continue
t.join()
thread()
参考:https://blog.csdn.net/weixin_43881394/article/details/109240813
标签:网易,url,爬虫,comments,json,评论,likedCount,print,dict 来源: https://www.cnblogs.com/yzgblogs/p/15473514.html