爬去证件会的首次公开发行反馈意见并做词频分析
Posted
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了爬去证件会的首次公开发行反馈意见并做词频分析相关的知识,希望对你有一定的参考价值。
利用国庆8天假期,从头开始学爬虫,现在分享一下自己项目过程。
技术思路:
1,使用scrapy爬去证监会反馈意见
- 分析网址特点,并利用scrapy shell测试选择器
- 加载代理服务器:IP池
- 模拟浏览器:user-agent
- 编写pipeitem,将数据写入数据库中
2,安装并配置mysql
- 安装pymysql
- 参考mysql手册,建立数据库以及表格
3,利用进行数据分析
- 使用对反馈意见进行整理
- 利用jieba库进行分析,制作财务报表专用字典,获取词汇以及其频率
- 使用pandas分析数据并作图
- 使用tableau作图
分析思路:
- 分析公司名字是否含有地域信息
- 分析反馈意见的主要焦点:财务与法律
核心代码:
- 爬虫核心代码
# -*- coding: utf-8 -*- import scrapy from scrapy.selector import Selector from fkyj.items import FkyjItem import urllib.request from scrapy.http import htmlResponse from scrapy.selector import HtmlXPathSelector def gen_url_indexpage():
#证监会的网站是通过javascript生成的,因此网址无法提取,必须是自己生成 pre = "http://www.csrc.gov.cn/pub/newsite/fxjgb/scgkfxfkyj/index" url_list = [] for i in range(25): if i ==0: url = pre+".html" url_list.append(url) else: url = pre+"_"+str(i)+".html" url_list.append(url) return url_list class Spider1Spider(scrapy.Spider): name = ‘spider1‘ allowed_domains = [‘http://www.csrc.gov.cn‘] start_urls = gen_url_indexpage() def parse(self, response): item = FkyjItem() page_lst = response.xpath(‘//ul[@id="myul"]/li/a/@href‘).extract() name_lst = response.xpath(‘//ul[@id="myul"]/li/a/@title‘).extract() date_lst= response.xpath(‘//ul[@id="myul"]/li/span/text()‘).extract() for i in range(len(name_lst)): item["name"] = name_lst[i] item["date"] = date_lst[i] url_page = "http://www.csrc.gov.cn/pub/newsite/fxjgb/scgkfxfkyj" +page_lst[i] pre_final = "http://www.csrc.gov.cn/pub/newsite/fxjgb/scgkfxfkyj/" + page_lst[i].split("/")[1] res = Selector(text= urllib.request.urlopen(url_page).read().decode("utf-8")) #给res装上HtmlXPathSelector url_extract = res.xpath("//script").re(r‘<a href="(\\./P\\d+?\\.docx?)">|<a href="(\\./P\\d+?\\.pdf)">‘)[0][1:] url_final = pre_final+ url_extract print ("-"*10,url_final,"-"*10) item["content"] = "" try: file =urllib.request.urlopen(url_final).read() filepath = r"C:\\\\Users\\\\tc\\\\fkyj\\\\fkyj\\\\files\\\\" filetype = url_extract.split(".")[1] with open(filepath+item["name"]+"."+filetype,‘wb‘) as f: f.write(file) except urllib.request.HTTPError: item["content"] = "wrong:HTTPERROR" yield item
这里不足之处在于没有体现针对不同网站书写不同代码,建议建立不同callback函数
建议思路:
parse():正对初始网址
parse_page:针对导航页
parse_item:提取公司名称与日期
parse_doc:提取doc文档
---------------------------------------------------------------------pipeitem代码-------------------------------------------------------------
import pymysql
class FkyjPipeline(object):
def __init__(self):
#连接数据库
self.con = pymysql.connect(host=‘localhost‘, port=3306, user=‘root‘, passwd="密码",db="数据库名字")
def process_item(self, item, spider):
name = item["name"]
date = item["date"]
content = item["content"]
self.con.query("Insert Into zjh_fkyj.fkyj(name,date_fk,content) Values(‘" + name + "‘,‘" + date + "‘,‘"+content+"‘)")
#必须要提交,否则没用
self.con.commit()
return item
def close_spider(self):
#在运行时关闭数据库
self.con.close()
2,分析用代码--主要部分
In [9]:
import pandas as pd
In [10]:
data =pd.read_csv(r"C:\\\\Users\\\\tc\\\\fkyj\\\\fkyj.csv")
In [11]:
data.columns
Out[11]:
In [11]:
data.drop(["Unnamed: 0",‘id‘],axis=1,inplace = True)
In [12]:
def get_year_month(datetime):
return "-".join(datetime.split("-")[:2])
In [13]:
group_month_data = data.groupby(data["date"].apply(get_year_month)).count()
In [25]:
get_year_month("2017-2-1")
Out[25]:
In [6]:
%matplotlib
In [49]:
group_month_data["name"].plot(kind="bar")
Out[49]:
In [36]:
import matplotlib.pyplot as plt
In [38]:
from matplotlib import font_manager
zh_font = font_manager.FontProperties(fname=r‘c:\\windows\\fonts\\simsun.ttc‘, size=14)
In [66]:
fig, ax = plt.subplots()
width =0.35
ax.set_xticks(ticks=range(len(group_month_data)))
plt.xticks(rotation=20)
res = ax.bar(left = range(len(group_month_data)),height=group_month_data["name"])
ax.set_title("证监会反馈意见",fontproperties=zh_font)
ax.set_ylabel("数量",fontproperties=zh_font)
ax.set_xticklabels( i for i in (group_month_data.index.values))
plt.show()
In [47]:
ax.set_xticklabels(group_month_data.index.values)
plt.show()
In [50]:
group_month_data.index.values
Out[50]:
In [51]:
len(group_month_data)
Out[51]:
In [8]:
china_map = [("北京","|东城|西城|崇文|宣武|朝阳|丰台|石景山|海淀|门头沟|房山|通州|顺义|昌平|大兴|平谷|怀柔|密云|延庆"),
("上海","|黄浦|卢湾|徐汇|长宁|静安|普陀|闸北|虹口|杨浦|闵行|宝山|嘉定|浦东|金山|松江|青浦|南汇|奉贤|崇明"),
("天津","|和平|东丽|河东|西青|河西|津南|南开|北辰|河北|武清|红挢|塘沽|汉沽|大港|宁河|静海|宝坻|蓟县"),
("重庆","|万州|涪陵|渝中|大渡口|江北|沙坪坝|九龙坡|南岸|北碚|万盛|双挢|渝北|巴南|黔江|长寿|綦江|潼南|铜梁|大足|荣昌|壁山|梁平|城口|丰都|垫江|武隆|忠县|开县|云阳|奉节|巫山|巫溪|石柱|秀山|酉阳|彭水|江津|合川|永川|南川"),
("河北","|石家庄|邯郸|邢台|保定|张家口|承德|廊坊|唐山|秦皇岛|沧州|衡水"),
("山西","|太原|大同|阳泉|长治|晋城|朔州|吕梁|忻州|晋中|临汾|运城"),
("内蒙古","|呼和浩特|包头|乌海|赤峰|呼伦贝尔盟|阿拉善盟|哲里木盟|兴安盟|乌兰察布盟|锡林郭勒盟|巴彦淖尔盟|伊克昭盟"),
("辽宁","|沈阳|大连|鞍山|抚顺|本溪|丹东|锦州|营口|阜新|辽阳|盘锦|铁岭|朝阳|葫芦岛"),
("吉林","|长春|吉林|四平|辽源|通化|白山|松原|白城|延边"),
("黑龙江","|哈尔滨|齐齐哈尔|牡丹江|佳木斯|大庆|绥化|鹤岗|鸡西|黑河|双鸭山|伊春|七台河|大兴安岭"),
("江苏","|南京|镇江|苏州|南通|扬州|盐城|徐州|连云港|常州|无锡|宿迁|泰州|淮安"),
("浙江","|杭州|宁波|温州|嘉兴|湖州|绍兴|金华|衢州|舟山|台州|丽水"),
("安徽","|合肥|芜湖|蚌埠|马鞍山|淮北|铜陵|安庆|黄山|滁州|宿州|池州|淮南|巢湖|阜阳|六安|宣城|亳州"),
("福建","|福州|厦门|莆田|三明|泉州|漳州|南平|龙岩|宁德"),
("江西","|南昌市|景德镇|九江|鹰潭|萍乡|新馀|赣州|吉安|宜春|抚州|上饶"),
("山东","|济南|青岛|淄博|枣庄|东营|烟台|潍坊|济宁|泰安|威海|日照|莱芜|临沂|德州|聊城|滨州|菏泽"),
("河南","|郑州|开封|洛阳|平顶山|安阳|鹤壁|新乡|焦作|濮阳|许昌|漯河|三门峡|南阳|商丘|信阳|周口|驻马店|济源"),
("湖北","|武汉|宜昌|荆州|襄樊|黄石|荆门|黄冈|十堰|恩施|潜江|天门|仙桃|随州|咸宁|孝感|鄂州"),
("湖南","|长沙|常德|株洲|湘潭|衡阳|岳阳|邵阳|益阳|娄底|怀化|郴州|永州|湘西|张家界"),
("广东","|广州|深圳|珠海|汕头|东莞|中山|佛山|韶关|江门|湛江|茂名|肇庆|惠州|梅州|汕尾|河源|阳江|清远|潮州|揭阳|云浮"),
("广西","|南宁|柳州|桂林|梧州|北海|防城港|钦州|贵港|玉林|南宁地区|柳州地区|贺州|百色|河池"),
("海南","|海口|三亚"),
("四川","|成都|绵阳|德阳|自贡|攀枝花|广元|内江|乐山|南充|宜宾|广安|达川|雅安|眉山|甘孜|凉山|泸州"),
("贵州","|贵阳|六盘水|遵义|安顺|铜仁|黔西南|毕节|黔东南|黔南"),
("云南","|昆明|大理|曲靖|玉溪|昭通|楚雄|红河|文山|思茅|西双版纳|保山|德宏|丽江|怒江|迪庆|临沧"),
("西藏","|拉萨|日喀则|山南|林芝|昌都|阿里|那曲"),
("陕西","|西安|宝鸡|咸阳|铜川|渭南|延安|榆林|汉中|安康|商洛"),
("甘肃","|兰州|嘉峪关|金昌|白银|天水|酒泉|张掖|武威|定西|陇南|平凉|庆阳|临夏|甘南"),
("宁夏","|银川|石嘴山|吴忠|固原"),
("青海","|西宁|海东|海南|海北|黄南|玉树|果洛|海西"),
("新疆","|乌鲁木齐|石河子|克拉玛依|伊犁|巴音郭勒|昌吉|克孜勒苏柯尔克孜|博尔塔拉|吐鲁番|哈密|喀什|和田|阿克苏"),
("香港",""),
("澳门",""),
("台湾","|台北|高雄|台中|台南|屏东|南投|云林|新竹|彰化|苗栗|嘉义|花莲|桃园|宜兰|基隆|台东|金门|马祖|澎湖")]
city_map = {}
for i in china_map:
if i != "澳门" or i != "香港":
city_map[i[0]] = i[1].split("|")[1:]
elif i == "澳门" or i == "香港":
city_map[i[0]] = ""
In [27]:
def get_province(name,con_loc = False):
keys = city_map.keys()
for j in keys:
if j in name:
province = j
location = "province"
break
else:
for k in city_map[j]:
if k in name:
province = j
location = "city"
break
else:
province = "unknow"
location = "unknow"
if con_loc:
return (province,location)
else:
return province
#count the name that contain the location
In [31]:
data["province"] = data["name"].apply(get_province)
In [13]:
data["name"][:5]
Out[13]:
In [32]:
data["province"][:20]
Out[32]:
In [44]:
name_data = data.groupby(data["province"]).count()["name"]
fig, ax = plt.subplots()
width =0.35
ax.set_xticks(ticks=range(len(name_data)))
plt.xticks(rotation=60)
res = ax.bar(left = range(len(name_data)),height= name_data)
ax.set_title("反馈意见--公司名称是否含有地域信息",fontproperties=zh_font)
ax.set_ylabel("数量",fontproperties=zh_font)
ax.set_xticklabels( [i for i in name_data.index.values],fontproperties=zh_font)
plt.show()
In [15]:
import jieba
In [16]:
jieba.load_userdict(r"C:\\\\ProgramData\\\\Anaconda3\\\\Lib\\\\site-packages\\\\jieba\\\\userdict.txt")
In [17]:
import re
def remove_rn(data):
return re.sub("[\\\\n\\\\r]+","",data)
remove_rn("\\r\\n\\r")
Out[17]:
In [18]:
data["content"] = data["content"].apply(remove_rn)
In [11]:
data["content"][:1]
Out[11]:
In [17]:
remove_rn("\\r\\n\\r45463")
Out[17]:
In [14]:
data["content"] = data["content"].astype(str)
In [16]:
f1 = open(r"C:\\Users\\tc\\Desktop\\user_dict.txt",encoding ="utf-8")
f2 = open(r"C:\\Users\\tc\\Desktop\\userdict.txt","w")
for i in f1.readlines():
f2.write(i[:-1] + " 5 n\\n")
f1.close()
f2.close()
In [23]:
list(jieba.cut("hellotc") )
Out[23]:
In [24]:
list(jieba.cut("我是唐诚的弟弟"))
Out[24]:
In [19]:
type(pd.Series(list( jieba.cut(data["content"][1]))).value_counts())
Out[19]:
In [ ]:
s = pd.Series([0 for i in len(data["content"])],index = )
for i in data["content"]:
pd.Series(list( jieba.cut(data["content"][1]))).value_counts()
In [7]:
s1 = pd.Series(range(3),index = ["a","b","c"])
s2 = pd.Series(range(3),index = ["d","b","c"])
s1.add(s2,fill_value=0)
Out[7]:
In [8]:
def add_series(s1,s2):
r = {}
s1 = s1.to_dict()
s2 = s2.to_dict()
common = set(s1.keys()).intersection(s2.keys())
for i in common:
r[i] = s1[i]+s2[i]
for j in set(s1.keys()).difference(s2.keys()):
r[j] = s1[j]
for k in set(s2.keys()).difference(s1.keys()):
r[k] = s2[k]
return pd.Series(r)
In [21]:
series_list = []
for i in data["content"]:
series_list.append(pd.Series(list( jieba.cut(i))).value_counts())
In [23]:
start = pd.Series([0,0],index = [‘a‘,‘b‘])
for i in series_list:
start = add_series(start,i)
In [25]:
start[:4]
Out[25]:
In [26]:
start.sort_values()
start.to_csv(r"C:\\\\Users\\\\tc\\\\fkyj\\\\rank_word.csv")
3,分析结果--部分
以上是关于爬去证件会的首次公开发行反馈意见并做词频分析的主要内容,如果未能解决你的问题,请参考以下文章