我用Python爬虫爬取并分析了C站前100用户最高访问的2000篇文章
Posted FrigidWinter
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了我用Python爬虫爬取并分析了C站前100用户最高访问的2000篇文章相关的知识,希望对你有一定的参考价值。
写在前面
最近系统地学习了正则表达式,发现正则表达式最大的应用之一——网络爬虫之前一直没有涉猎,遂借此契机顺带写一个爬虫的demo备用。选择对象是CSDN排行榜前100用户,各自按访问量从高到低排序的前20篇文章,使用一些简单的数据分析手段看看技术热点,方便今后拓宽技术栈。
项目总述
主要爬取的数据是文章标题和访问量,先总体可视化总体文章的技术关键词;然后按访问量分组,可视化每个访问段的技术热点。
数据爬取
获得服务器API
首先我们要知道通过什么接口可以获得网站数据:首先进入博客总榜,按F12进入控制台,选中Network
选项卡监视网络请求,然后刷新网页。从下图可以看到在API"https://blog.csdn.net/phoenix/web/blog/all-rank?page=1&pageSize=20"
中我们可以拿到我们想要的用户信息——主要是用户名
现在到用户博客首页,同样地,按F12进入控制台,选中Network
选项卡监视网络请求,然后点击按访问量排序,则可以发现另一个关键APIhttps://blog.csdn.net/community/home-api/v1/get-business-list?page=1&size=20&businessType=blog&orderby=ViewCount&noMore=false&username={}
,如下图所示。
我们与服务器的交互就依靠这两个API进行。
程序总体设计
思考一下,我们总共有如下的公共变量:
# 请求头
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
# 排行榜url
rankUrl = "https://blog.csdn.net/phoenix/web/blog/all-rank?page={}&pageSize=20"
# 按访问量排行的文章列表
mostViewArtical = "https://blog.csdn.net/community/home-api/v1/get-business-list?page=1&size=20&businessType=blog&orderby=ViewCount&noMore=false&username={}"
userNames =[] # 用户名列表
titleList = [] # 文章标题列表
viewCntList = [] # 访问量列表
为便于管理,引入一个类进行爬虫,专门负责与服务器进行数据交互
class GetInfo:
def __init__(self) -> None:
# 请求头
self.headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
# 排行榜url
self.rankUrl = "https://blog.csdn.net/phoenix/web/blog/all-rank?page={}&pageSize=20"
# 按访问量排行的文章列表
self.mostViewArtical = "https://blog.csdn.net/community/home-api/v1/get-business-list?page=1&size=20&businessType=blog&orderby=ViewCount&noMore=false&username={}"
self.userNames = []
self.titleList, self.viewCntList = [], []
交互完成后,再使用别的库进行数据分析,将两个过程分离开
用户名爬取
定义一个私有的初始化函数
def __initRankUsrName(self):
usrNameList = []
for i in range(5):
response = requests.get(url=self.rankUrl.format(i),
headers=self.headers)
response.encoding = 'utf-8'
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
information = json.loads(str(soup))
for item in information['data']['allRankListItem']:
usrNameList.append(item['userName'])
return usrNameList
这里获取用户名主要是为了动态生成第二个API
文章爬取
再定义一个私有函数,输入参数是用户名列表:
def __initArticalInfo(self, usrList):
titleList = []
viewCntList = []
for name in usrList:
url = self.mostViewArtical.format(name)
# print(url)
response = requests.get(url=url, headers=self.headers)
response.encoding = 'utf-8'
response.raise_for_status()
titleList.extend(re.findall(r"\\"title\\":\\"(.*?)\\"", response.text))
viewCntList.extend(re.findall(r"\\"viewCount\\":(.*?),", response.text))
return titleList, viewCntList
这里我使用正则表达式直接处理字符串,并返回文章标题列表、访问量列表。可以随便访问一个API做实验,这里以我的用户名为例,可以看到要获取文章标题就是以\\"title\\":\\"(.*?)\\"
去匹配,其中\\
用于转义;要获取访问量就是以\\"viewCount\\":(.*?),
去匹配,访问数字没有加引号。
事实上,用正则匹配不需要将返回的字符串加载为Json字典,可能有更快的处理效率(但不如json灵活)
这个爬虫类就设计好了,完整代码如下:
class GetInfo:
def __init__(self) -> None:
# 请求头
self.headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
# 排行榜url
self.rankUrl = "https://blog.csdn.net/phoenix/web/blog/all-rank?page={}&pageSize=20"
# 按访问量排行的文章列表
self.mostViewArtical = "https://blog.csdn.net/community/home-api/v1/get-business-list?page=1&size=20&businessType=blog&orderby=ViewCount&noMore=false&username={}"
self.userNames = self.__initRankUsrName()
self.titleList, self.viewCntList = self.__initArticalInfo(
self.userNames)
def __initArticalInfo(self, usrList):
titleList = []
viewCntList = []
for name in usrList:
url = self.mostViewArtical.format(name)
# print(url)
response = requests.get(url=url, headers=self.headers)
response.encoding = 'utf-8'
response.raise_for_status()
titleList.extend(re.findall(r"\\"title\\":\\"(.*?)\\"", response.text))
viewCntList.extend(
re.findall(r"\\"viewCount\\":(.*?),", response.text))
return titleList, viewCntList
def __initRankUsrName(self):
usrNameList = []
for i in range(5):
response = requests.get(url=self.rankUrl.format(i),
headers=self.headers)
response.encoding = 'utf-8'
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
information = json.loads(str(soup))
for item in information['data']['allRankListItem']:
usrNameList.append(item['userName'])
return usrNameList
info = GetInfo()
使用也很方便,只需要实例化调用其中的列表属性即可。
数据分析
数据存储
将文本数据存成csv
格式,先设计表头:
if not os.path.exists("articalInfo.csv"):
#创建存储csv文件存储数据
with open('articalInfo.csv', "w", encoding="utf-8-sig", newline='') as f:
csv_head = csv.writer(f)
csv_head.writerow(['title', 'viewCnt'])
注意编码格式为utf-8-sig
,否则会乱码
接下来存数据:
length = len(info.titleList)
for i in range(length):
if info.titleList[i]:
with open('articalInfo.csv', 'a+', encoding='utf-8-sig') as f:
f.write(info.titleList[i] + ',' + info.viewCntList[i] + '\\n')
总体数据可视化
新建一个模块专门用于可视化数据,与爬虫分离开,因为爬虫是慢IO过程,会影响调试效率,后面可以试试用协程来处理爬虫。
首先,把爬虫的信息读取到txt文件去
df = pd.read_csv('articalInfoNor.csv', encoding='utf-8-sig',usecols=['title', 'viewCnt'])
titleList = ','.join(df['title'].values)
with open('text.txt','a+', encoding='utf-8-sig') as f:
f.writelines(titleList)
如何返回分词结果:
def getKeyWordText():
# 读取文件信息
file = open(path.join(path.dirname(__file__), 'text.txt'), encoding='utf-8-sig').read()
return ' '.join(jieba.cut(file))
借助词云库可视化一下:
bg_pic = imread('2.jpg')
#生成词云
wordcloud = WordCloud(font_path=r'C:\\Windows\\Fonts\\simsun.ttc',mask=bg_pic,background_color='white',scale=1.5).generate(text)
image_colors = ImageColorGenerator(bg_pic)
#显示词云图片
plt.imshow(wordcloud)
plt.axis('off')
plt.show()
#保存图片
wordcloud.to_file('test.jpg')
这个大大的“的”是什么鬼?显然高频关键词里有太多语气助词、连接词,我们最好设置一个停用词列表把这些明显不需要的词屏蔽掉。我这里采用修饰器的方法让代码更简洁,关于修饰器的内容可以参考Python修饰器
def splitText(mode):
stopWords = ["的","与","和","建议","收藏","使用","了","实现","我","中","你","在","之","年","月","日"]
def warpper(func):
def warp():
textSplit = func()
if mode:
temp = [word for word in textSplit if word not in stopWords]
return ' '.join(temp)
else:
return ' '.join(textSplit)
return warp
return warpper
当mode=True时启用屏蔽,否则关闭屏蔽,那么之前的函数应该修改为:
# 返回关键词文本
@splitText(False)
def getKeyWordText():
# 读取文件信息
file = open(path.join(path.dirname(__file__), 'text.txt'), encoding='utf-8-sig').read()
return jieba.cut(file)
再来一次:
现在就正常多了。可以看到Python和Java是绝对的领先,之后是各位总结的方法论等等,算法的词频反而不高?
数据分组
我把数据进一步分层为
1、访问量>10W
2、访问量5W~10W
3、访问量1W~5W
4、访问量5K~1W
5、访问量5K以下
先来看看数据分布情况:
我猜如果分段分得再细一点可能趋于正态分布~
分组可视化看看:
感觉从这里开始更百花齐放一些,似乎也更关注具体问题的解决
不得不感叹python在每个阶段都是牌面
完整代码
import requests
from bs4 import BeautifulSoup
import os, json, re, csv
class GetInfo:
def __init__(self) -> None:
# 请求头
self.headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
# 排行榜url
self.rankUrl = "https://blog.csdn.net/phoenix/web/blog/all-rank?page={}&pageSize=20"
# 按访问量排行的文章列表
self.mostViewArtical = "https://blog.csdn.net/community/home-api/v1/get-business-list?page=1&size=20&businessType=blog&orderby=ViewCount&noMore=false&username={}"
self.userNames = self.__initRankUsrName()
self.titleList, self.viewCntList = self.__initArticalInfo(
self.userNames)
def __initArticalInfo(self, usrList):
titleList = []
viewCntList = []
for name in usrList:
url = self.mostViewArtical.format(name)
# print(url)
response = requests.get(url=url, headers=self.headers)
response.encoding = 'utf-8'
response.raise_for_status()
titleList.extend(re.findall(r"\\"title\\":\\"(.*?)\\"", response.text))
viewCntList.extend(
re.findall(r"\\"viewCount\\":(.*?),", response.text))
return titleList, viewCntList
def __initRankUsrName(self):
usrNameList = []
for i in range(5):
response = requests.get(url=self.rankUrl.format(i),
headers=self.headers)
response.encoding = 'utf-8'
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
information = json.loads(str(soup))
for item in information['data']['allRankListItem']:
usrNameList.append(item['userName'])
return usrNameList
info = GetInfo()
if not os.path.exists("articalInfo.csv"):
#创建存储csv文件存储数据
with open('articalInfo.csv', "w", encoding="utf-8-sig", newline='') as f:
csv_head = csv.writer(f)
csv_head.writerow(['title', 'viewCnt'])
length = len(info.titleList)
for i in range(length):
if info.titleList[i]:
with open('articalInfo.csv', 'a+', encoding='utf-8-sig') as f:
f.write(info.titleList[i] + ',' + info.viewCntList[i] + '\\n')
from wordcloud import WordCloud,ImageColorGenerator
import matplotlib.pyplot as plt
from imageio import imread
import jieba
import pandas as pd
from os import path
df = pd.read_csv('articalInfoCom.csv', encoding='utf-8-sig',usecols=['title', 'viewCnt'])
titleList = ','.join(df['title'].values)
with open('text.txt','a+', encoding='utf-8-sig') as f:
f.writelines(titleList)
def splitText(mode):
stopWords = ["的","与","和","建议","收藏","使用","了","实现","我","中","你","在","之","年","月","日"]
def warpper(func):
def warp():
textSplit = func()
if mode:
temp = [word for word in textSplit if word not in stopWords]
return ' '.join(temp)
else:
return ' '.join(textSplit)
return warp
return warpper
# 返回关键词文本
@splitText(True)
def getKeyWordText():
# 读取文件信息
file = open(path.join(path.dirname(__file__), 'text.txt'), encoding='utf-8-sig').read()
return jieba.cut(file)
text = getKeyWordText()
#读取txt文件、背景图片
bg_pic = imread('2.jpg')
#生成词云
wordcloud = WordCloud(font_path=r'C:\\Windows\\Fonts\\simsun.ttc',mask=bg_pic,background_color='white',scale=1.5).generate(text)
image_colors = ImageColorGenerator(bg_pic)
#显示词云图片
plt.imshow(wordcloud)
plt.axis('off')
plt.show()
#保存图片
wordcloud.to_file('test.jpg')
以上是关于我用Python爬虫爬取并分析了C站前100用户最高访问的2000篇文章的主要内容,如果未能解决你的问题,请参考以下文章
Python爬虫实战,Scrapy实战,爬取并简单分析知网中国专利数据
冻成狗啦 我用Python爬取某宝2008条棉袄,终于买到心仪的棉袄了
冻成狗啦 我用Python爬取某宝2008条棉袄,终于买到心仪的棉袄了