5.18

图书评论爬取

import re

from collections import Counter

 

import requests

from lxml import etree

import pandas as pd

import jieba

import matplotlib.pyplot as plt

from wordcloud import WordCloud

 

headers = {

    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39"

}

 

comments = []

words = []

 

 

def regex_change(line):

    # 前缀的正则

    username_regex = re.compile(r"^\d+::")

    # URL，为了防止对中文的过滤，所以使用[a-zA-Z0-9]而不是\w

    url_regex = re.compile(r"""

        (https?://)?

        ([a-zA-Z0-9]+)

        (\.[a-zA-Z0-9]+)

        (\.[a-zA-Z0-9]+)*

        (/[a-zA-Z0-9]+)*

    """, re.VERBOSE | re.IGNORECASE)

    # 剔除日期

    data_regex = re.compile(u"""        #utf-8编码

        年 |

        月 |

        日 |

        (周一) |

        (周二) |

        (周三) |

        (周四) |

        (周五) |

        (周六)

    """, re.VERBOSE)

    # 剔除所有数字

    decimal_regex = re.compile(r"[^a-zA-Z]\d+")

    # 剔除空格

    space_regex = re.compile(r"\s+")

    regEx = "[\n”“|,，；;''/?! 。的了是]"  # 去除字符串中的换行符、中文冒号、|，需要去除什么字符就在里面写什么字符

    line = re.sub(regEx, "", line)

    line = username_regex.sub(r"", line)

    line = url_regex.sub(r"", line)

    line = data_regex.sub(r"", line)

    line = decimal_regex.sub(r"", line)

    line = space_regex.sub(r"", line)

    return line

 

 

def getComments(url):

    score = 0

    resp = requests.get(url, headers=headers).text

    html = etree.HTML(resp)

    comment_list = html.xpath(".//div[@class='comment']")

    for comment in comment_list:

        status = ""

        name = comment.xpath(".//span[@class='comment-info']/a/text()")[0]  # 用户名

        content = comment.xpath(".//p[@class='comment-content']/span[@class='short']/text()")[0]  # 短评内容

        content = str(content).strip()

        word = jieba.cut(content, cut_all=False, HMM=False)

        time = comment.xpath(".//span[@class='comment-info']/a/text()")[1]  # 评论时间

        mark = comment.xpath(".//span[@class='comment-info']/span/@title")  # 评分

        if len(mark) == 0:

            score = 0

        else:

            for i in mark:

                status = str(i)

            if status == "力荐":

                score = 5

            elif status == "推荐":

                score = 4

            elif status == "还行":

                score = 3

            elif status == "较差":

                score = 2

            elif status == "很差":

                score = 1

        good = comment.xpath(".//span[@class='comment-vote']/span[@class='vote-count']/text()")[0]  # 点赞数（有用数）

        comments.append([str(name), content, str(time), score, int(good)])

        for i in word:

            if len(regex_change(i)) >= 2:

                words.append(regex_change(i))

 

 

def getWordCloud(words):

    # 生成词云

    all_words = []

    all_words += [word for word in words]

    dict_words = dict(Counter(all_words))

    bow_words = sorted(dict_words.items(), key=lambda d: d[1], reverse=True)

    print("热词前10位：")

    for i in range(10):

        print(bow_words[i])

    text = ' '.join(words)

 

    w = WordCloud(background_color='white',

                     width=1000,

                     height=700,

                     font_path='simhei.ttf',

                     margin=10).generate(text)

    plt.show()

    plt.imshow(w)

    w.to_file('wordcloud.png')

 

 

print("请选择以下选项:")

print("   1.热门评论")

print("   2.最新评论")

info = int(input())

print("前10位短评信息：")

title = ['用户名', '短评内容', '评论时间', '评分', '点赞数']

if info == 1:

    comments = []

    words = []

    for i in range(0, 60, 20):

        url = "https://book.douban.com/subject/10517238/comments/?start={}&limit=20&status=P&sort=new_score".format(

            i)  # 前3页短评信息（热门）

        getComments(url)

    df = pd.DataFrame(comments, columns=title)

    print(df.head(10))

    print("点赞数前10位的短评信息：")

    df = df.sort_values(by='点赞数', ascending=False)

    print(df.head(10))

    getWordCloud(words)

elif info == 2:

    comments = []

    words=[]

    for i in range(0, 60, 20):

        url = "https://book.douban.com/subject/10517238/comments/?start={}&limit=20&status=P&sort=time".format(

            i)  # 前3页短评信息（最新）

        getComments(url)

    df = pd.DataFrame(comments, columns=title)

    print(df.head(10))

    print("点赞数前10位的短评信息：")

    df = df.sort_values(by='点赞数', ascending=False)

    print(df.head(10))