爬虫大作业

本次作业来源：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/3159

可以用pandas读出之前保存的数据：

newsdf = pd.read_csv(r'F:duymgzccnews.csv')

一.把爬取的内容保存到数据库sqlite3

import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
newsdf.to_sql('gzccnews',con = db)

with sqlite3.connect('gzccnewsdb.sqlite') as db:
df2 = pd.read_sql_query('SELECT * FROM gzccnews',con=db)

保存到MySQL数据库

• import pandas as pd
• import pymysql
• from sqlalchemy import create_engine
• conInfo = "mysql+pymysql://user:passwd@host:port/gzccnews?charset=utf8"
• engine = create_engine(conInfo,encoding='utf-8')
• df = pd.DataFrame(allnews)
• df.to_sql(name = ‘news', con = engine, if_exists = 'append', index = False）

二.爬虫综合大作业

1.主题        看了一部电影《绿皮书》，觉得挺不错，不知道网上的评价怎样，借此分析一下

                                                                                                                                                        图1-网页截图

2.爬取的对象   爬取排在前面的300条评论

                                                                                                                                              图2-爬取的内容

3.爬取内容的限制与约束

          这次爬取的是公网上的内容。不会涉及到很多的隐私性，所以应该没什么约束。不敢爬太多，怕被发现。内容里很多图片，但都没爬下来。主要是想拿数据来对手机做一个分析。

4。核心代码

  爬取评论的代码

import pandas
import requests
from bs4 import BeautifulSoup
import time
import random
import re


def getHtml(url):
    cookies = {
        'PHPSESSID': 'Cookie: bid=7iHsqC-UoSo; ap_v=0,6.0; __utma=30149280.1922890802.1557152542.1557152542.1557152542.1;<br> __utmc=30149280; __utmz=30149280.1557152542.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); __utma=223695111.1923787146.1557152542.1557152542.1557152542.1;<br> __utmb=223695111.0.10.1557152542; __utmc=223695111; __utmz=223695111.1557152542.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none);<br> _pk_ses.100001.4cf6=*; push_noty_num=0; push_doumail_num=0; __utmt=1; __utmv=30149280.19600; ct=y; ll="118281";<br> __utmb=30149280.12.9.1557154640902; __yadk_uid=6FEHGUf1WakFoINiOARNsLcmmbwf3fRJ; <br>_vwo_uuid_v2=DE694EB251BD96736CA7C8B8D85C2E9A7|9505affee4012ecfc57719004e3e5789;<br> _pk_id.100001.4cf6=1f5148bca7bc0b13.1557152543.1.1557155093.1557152543.; dbcl2="196009385:lRmza0u0iAA"'}
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}
    req = requests.get(url, headers=headers, cookies=cookies, verify=False);
    req.encoding = 'utf8'
    soup = BeautifulSoup(req.text, "html.parser")
    return soup;


def alist(url):
    comment = []
    for ping in soup.select('.comment-item'):
        pinglundict = {}
        user = ping.select('.comment-info')[0]('a')[0].text
        userUrl = ping.select('.comment-info')[0]('a')[0]['href']
        look = ping.select('.comment-info')[0]('span')[0].text
        score = ping.select('.comment-info')[0]('span')[1]['title']
        time = ping.select('.comment-time')[0]['title']
        pNum = ping.select('.votes')[0].text
        pingjia = ping.select('.short')[0].text
        pinglundict['user'] = user
        pinglundict['userUrl'] = userUrl
        pinglundict['look'] = look
        pinglundict['score'] = score
        pinglundict['time'] = time
        pinglundict['pNum'] = pNum
        pinglundict['pingjia'] = pingjia
        comment.append(pinglundict)
    return comment


url = 'https://movie.douban.com/subject/27060077/comments?start={}&limit=20&sort=new_score&status=P'

comment = []

for i in range(15):
    soup = getHtml(url.format(i * 20))
    comment.extend(alist(soup))
    time.sleep(random.random() * 5)
    print(len(comment))
print('--------------------------总共爬取 ', len(comment), ' 条-------------------------')
print(comment)

pingtheking = pandas.DataFrame(comment)
pingtheking.to_csv('jia.csv', encoding='utf_8_sig')

统计词频的代码

# coding=utf-8


# 导入jieba模块，用于中文分词
import jieba

# 获取所有评论
import pandas as pd
# 读取小说
f = open(r'jia.csv', 'r', encoding='utf8')
text = f.read()
f.close()
print(text)
ch="《》
：，,。、-!?0123456789"
for c in ch:
    text = text.replace(c,'')
print(text)
newtext = jieba.lcut(text)
te = {}
for w in newtext:
    if len(w) == 1:
        continue
    else:
        te[w] = te.get(w, 0) + 1
tesort = list(te.items())
tesort.sort(key=lambda x: x[1], reverse=True)

# 输出次数前TOP20的词语
for i in range(0, 20):
    print(tesort[i])
pd.DataFrame(tesort).to_csv('tongji.csv', encoding='utf-8')

生成词云的代码

import matplotlib.pyplot as plt
from wordcloud import WordCloud
import jieba

text_from_file_with_apath = open('jia.csv',encoding='utf-8').read()

wordlist_after_jieba = jieba.cut(text_from_file_with_apath, cut_all=True)
wl_space_split = " ".join(wordlist_after_jieba)

my_wordcloud = WordCloud(background_color="white",width=1000,height=860, font_path="C:\Windows\Fonts\STFANGSO.ttf").generate(wl_space_split)

plt.imshow(my_wordcloud)
plt.axis("off")
plt.show()

4.数据统计与分析

        

          我们从中发现很多观众都提到了种族歧视问题，有奥斯卡才来看的，有觉得演得很棒很有细节，有人表示司机的身份很巧妙，白人却是高高的钢琴师的矛盾。总的来说我觉得这片很成功，观众感受到影片要表达的。普遍好评。