2019中国好声音火热开播，作为一名“假粉丝”，这一季每一期都刷过了，尤其刚播出的第六期开始正式的battle。视频视频看完了，那看下大家都是怎样评论的。
1.网页分析部分
本文爬取的是腾讯视频评论，第六期的评论地址是：http://coral.qq.com/4093121984
每页有10条评论，点击“查看更多评论”，可将新的评论加载进来，通过多次加载，可以发现我们要找的评论就在以v2开头的js类型的响应中。
请求为GET请求，地址是http://coral.qq.com/article/4093121984/comment/v2 ，通过传入不同的参数返回不同的评论内容。
图一：
图二：
经过对比发现，参数不同的地方只有两点，"cursor"和""。
先看"cursor"：第一页的"cursor"是0，后面每一页的都是前一页响应中"last"的值
再看下""：第一页的值似乎是随机生成的，而后面每一页都在前一页的基础上加1
图三：
图四：
OK，找到规律后，开始爬取每一页的评论
2.爬虫部分
（1）导入需要的库
import requests
import re
import random
import time
import json
import jieba
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import matplotlib.font_manager as fmgr
from wordcloud import WordCloud
from common import user_agent #自定义
from common import my_fanction #自定义其中common文件夹中自定义了一些方法：
user_agent
#!/usr/bin/env python
# -*- coding: utf-8 -*-
‘‘‘
@File : user_agent.py
@Author: Fengjicheng
@Date : 2019/8/11
@Desc :
‘‘‘
user_agent_list = [
# Opera
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60",
"Opera/8.0 (Windows NT 5.1; U; en)",
"Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50",
# Firefox
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
# Safari
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
# chrome
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
# 360
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
# 淘宝浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
# 猎豹浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
# QQ浏览器
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
# sogou浏览器
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)",
# maxthon浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36",
# UC浏览器
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36",
]my_function
#!/usr/bin/env python
# -*- coding: utf-8 -*-
‘‘‘
@File : file_writte.py
@Author: Fengjicheng
@Date : 2019/8/24
@Desc :
‘‘‘
def file_write(file_name,content):
if content:
if type(content) == list:
for i in content:
with open(file_name,‘a‘,encoding=‘utf-8‘) as f:
f.write(i + ‘\n‘)
if type(content) == str:
with open(file_name, ‘a‘, encoding=‘utf-8‘) as f:
f.write(content)
else:
print(content,"内容为空，跳过")
pass（2）爬取评论内容
这里总共爬取了三种类型的数据：用户评论、用户昵称、用户所在地区
#评论请求地址
url = ‘http://coral.qq.com/article/4093121984/comment/v2‘
agent = random.choice(user_agent.user_agent_list)
header = {
‘Host‘: ‘video.coral.qq.com‘,
‘User-Agent‘: agent,
‘Accept‘: ‘*/*‘,
‘Accept-Language‘: ‘zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2‘,
‘Accept-Encoding‘: ‘gzip, deflate, br‘,
‘Connection‘: ‘keep-alive‘,
‘Referer‘: ‘https://page.coral.qq.com/coralpage/comment/video.html‘,
‘TE‘: ‘Trailers‘
}
# 第一页
cursor = ‘0‘
vid = 1566724116229
def get_comment(a,b):
parameter = {
‘callback‘: ‘_varticle4093121984commentv2‘,
‘orinum‘: ‘10‘,
‘oriorder‘: ‘o‘,
‘pageflag‘: ‘1‘,
‘cursor‘: a,
‘scorecursor‘: ‘0‘,
‘orirepnum‘: ‘2‘,
‘reporder‘: ‘o‘,
‘reppageflag‘: ‘1‘,
‘source‘: ‘1‘,
‘_‘: str(b)
}
try:
html = requests.get(url,params=parameter,headers=header)
except Exception as e:
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()),"请求失败。",e)
else:
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()),"请求成功。")
content = html.content.decode(‘utf-8‘)
sep1 = ‘"last":"(.*?)"‘ # 下一个 cursor
sep2 = ‘"content":"(.*?)"‘ # 评论
sep3 = ‘"nick":"(.*?)"‘ # 昵称
sep4 = ‘"region":"(.*?)"‘ # 地区
global cursor
cursor = re.compile(sep1).findall(content)[0]
comment = re.compile(sep2).findall(content)
nick = re.compile(sep3).findall(content)
region = re.compile(sep4).findall(content)
my_fanction.file_write(‘txt/comment.txt‘,comment)
my_fanction.file_write(‘txt/nick.txt‘,nick)
my_fanction.file_write(‘txt/region.txt‘,region)效果如下：
（3）对用户评论进行分词
def cut_word(file_path):
with open(file_path,‘r‘,encoding=‘utf-8‘) as f:
comment_txt = f.read()
wordlist = jieba.cut(comment_txt, cut_all=True)
wl = " ".join(wordlist)
print(wl)
return wl #返回分词后的数据（4）生成词云
#词云形状图片
img1 = ‘lib/fangxing.png‘
img2 = ‘lib/xin.png‘
#词云字体
font = ‘lib/simsun.ttc‘
def create_word_cloud(file_path,img):
# 设置词云形状图片
wc_mask = np.array(Image.open(img))
# 设置词云的一些配置，如：字体，背景色，词云形状，大小
wc = WordCloud(background_color="white", max_words=200, mask=wc_mask, scale=4,
max_font_size=50, random_state=42, font_path=font)
# 生成词云
wc.generate(cut_word(file_path))
# 在只设置mask的情况下,你将会得到一个拥有图片形状的词云
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
#plt.figure()
plt.show()效果如下：
（5）对用户地区统计分析
国外地区忽略了，这里只对国内地区进行了分析
def create_region_histogram():
with open(‘txt/region.txt‘,‘r‘,encoding=‘utf-8‘) as f:
country_list = f.readlines()
country_list = [x.strip() for x in country_list if x.strip() != ‘::‘]
sep1 = ‘:‘
pattern1 = re.compile(sep1)
province_lit = []
province_count = []
other_list = []
other_count = []
for country in country_list:
country_detail = re.split(pattern1,country)
if ‘中国‘ in country_detail:
if country_detail[1] != ‘‘:
province_lit.append(country_detail[1])
else:
other_list.append(country_detail[0])
province_uniq = list(set(province_lit))
other_uniq = list(set(other_list))
for i in province_uniq:
province_count.append(province_lit.count(i))
for i in other_uniq:
other_count.append(other_list.count(i))
# 构建数据
x_data = province_uniq
y_data = province_count
# 自定义字体属性
fp = fmgr.FontProperties(fname=‘lib/simsun.ttc‘)
bar_width = 0.7
# Y轴数据使用range(len(x_data)
plt.barh(y=range(len(x_data)), width=y_data, label=‘count‘,
color=‘steelblue‘, alpha=0.8, height=bar_width)
# 在柱状图上显示具体数值, ha参数控制水平对齐方式, va控制垂直对齐方式
for y, x in enumerate(y_data):
plt.text(x+10, y - bar_width / 2, ‘%s‘ % x, ha=‘center‘, va=‘bottom‘)
# 为Y轴设置刻度值
plt.yticks(np.arange(len(x_data)) + bar_width / 2, x_data,fontproperties=fp)
# 设置标题
plt.title("各地区参与评论用户量",fontproperties=fp)
# 为两条坐标轴设置名称
plt.xlabel("人数",fontproperties=fp)
plt.ylabel("地区",fontproperties=fp)
# 显示图例
plt.legend()
plt.show()效果如下：
github地址：https://github.com/FJCAAAAA/python-spider
注：本文章只用于学习使用
原文地址：https://blog.51cto.com/fengjicheng/2432450
时间： 2024-07-29 16:19:52