From 18e5e2255a7eaaad03fec395af2621994d8bd9c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=83=91=E9=9F=B6=E5=9D=A4?= <2509165013@student.example.com> Date: Sun, 5 Jul 2026 16:55:56 +0800 Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?= =?UTF-8?q?=20q2=5F1=5Fcrawler?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- q2_1_crawler/ii.py | 88 ++++++++++++++++++++++++++++++++++ q2_1_crawler/q2_2.py | 43 +++++++++++++++++ q2_1_crawler/sandian.py | 25 ++++++++++ q2_1_crawler/zhifang_rating.py | 21 ++++++++ 4 files changed, 177 insertions(+) create mode 100644 q2_1_crawler/ii.py create mode 100644 q2_1_crawler/q2_2.py create mode 100644 q2_1_crawler/sandian.py create mode 100644 q2_1_crawler/zhifang_rating.py diff --git a/q2_1_crawler/ii.py b/q2_1_crawler/ii.py new file mode 100644 index 0000000..22bb961 --- /dev/null +++ b/q2_1_crawler/ii.py @@ -0,0 +1,88 @@ +import requests +from bs4 import BeautifulSoup as bs +import json + +url = 'https://exam.detr.top/exam-b/movies' +headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/149.0.0.0 Safari/537.36 Edg/149.0.0.0', + 'Referer':'https://exam.detr.top/exam-b/movies'} +req = requests.get(url, headers=headers) +req.encoding="utf-8" + +data=[] + +soup=bs(req.text,"html.parser") +# print(soup) +#id, title, director, year, rating, duration, genre, actors-count + +items=soup.select('.item-row') +# movie_list=[] +for i in range(len(items)): + id=items[i].find("td",class_="item-id").get_text() + title=items[i].find("td",class_="item-title").get_text().strip() + director=items[i].find("td",class_="item-director").get_text().strip() + year=items[i].find("td",class_="item-year").get_text() + rating=items[i].find("td",class_="item-rating").get_text() + duration=items[i].find("td",class_="item-duration").get_text() + genre=items[i].find("td",class_="item-genre").get_text() + actors_count=items[i].find("td",class_="item-actors-count").get_text() + + data.append({ + "id":id, + "title":title, + "director":director, + "year":year, + "rating":rating, + "duration":duration, + "genre":genre, + "actors_count":actors_count + + }) + +print(data) + +# for tr in item: +# tds=tr.find_all("td") +# tds=list(tds) +# # print(tds) +# if len(tds)<8: +# continue +# movie={ +# "id":tds[0].get_text(strip=True), +# "title":tds[1].get_text(strip=True), +# "director":tds[2].get_text(strip=True), +# "year":tds[3].get_text(strip=True), +# "rating":tds[4].get_text(strip=True), +# "duration":tds[5].get_text(strip=True), +# "genre":tds[6].get_text(strip=True), +# "actors_count":tds[7].get_text(strip=True) +# } +# movie_list.append(movie) +# print(movie_list) + + +with open('movie.json', 'w', encoding='utf-8') as f: + json.dump(data, f, ensure_ascii=False, indent=2) + +with open("movie.html","w",encoding='utf-8') as f: + json.dump(data, f, ensure_ascii=False, indent=2) + + + + + +# for i in range(len(items)): +# rank=i+1 +# title=items[i].find("span",class_="title").get_text() +# actors=items[i].find("div",class_="bd").get_text().strip() +# try: +# actors=actors.split("主演：")[1].split("\n")[0] +# except: +# actors="无" +# quote=items[i].find("p",class_="quote").get_text().strip() + +# data.append({ +# "rank":rank, +# "title":title, +# "actors":actors, +# "quote":quote +# }) \ No newline at end of file diff --git a/q2_1_crawler/q2_2.py b/q2_1_crawler/q2_2.py new file mode 100644 index 0000000..afbe81a --- /dev/null +++ b/q2_1_crawler/q2_2.py @@ -0,0 +1,43 @@ +# ① 找出评分最高和最低的电影，打印电影名 + 评分。 +# ② 统计各类型的电影数量，用字典格式输出。 +# ③ 统计各导演的电影数量，用字典格式输出。 +# ④ 统计 2020 年（含）以后上映的电影数量。 + +import json + + + +with open('movie.json', 'r', encoding='utf-8') as f: + data=json.load(f) + # print(data) + + +sort_movie=sorted(data,key=lambda x:x["rating"]) +min=sort_movie[0] +max=sort_movie[-1] +print("评分最低的电影",min["title"],min["rating"]) +print("评分最高的电影",max["title"],max["rating"]) + +genre_shu={} +for g in data: + ge=g["genre"] + if ge in genre_shu: + genre_shu[ge]+=1 + else: + genre_shu[ge]=1 +print("各类型的电影数量",genre_shu) + +director_shu={} +for d in data: + di=d["director"] + if di in director_shu: + director_shu[di]+=1 + else: + director_shu[di]=1 +print("各导演的电影数量",director_shu) + +a=0 +for y in data: + if int(y["year"]) >= 2020: + a+=1 +print("2020 年（含）以后上映的电影数量",a) \ No newline at end of file diff --git a/q2_1_crawler/sandian.py b/q2_1_crawler/sandian.py new file mode 100644 index 0000000..23ee22c --- /dev/null +++ b/q2_1_crawler/sandian.py @@ -0,0 +1,25 @@ +import matplotlib.pyplot as plt +import json + +rating=[] +duration=[] + +with open('movie.json', 'r', encoding='utf-8') as f: + data=json.load(f) + # print(data) + for i in data: + rating.append(i["rating"]) + duration.append(i["duration"]) +plt.figure(figsize=(12, 8)) +plt.scatter(duration, rating, + c='red', + s=80, # 点的大小 + alpha=0.6, # 透明度 + edgecolors='white') # 点的边框 +plt.title('时长与评分关系散点图', fontsize=14) +plt.xlabel('时长', fontsize=12) +plt.ylabel('评分', fontsize=12) +plt.grid(True, linestyle='--', alpha=0.5) +plt.show() +plt.savefig("q4_2_scatter.png",dpi=150,format='png') + diff --git a/q2_1_crawler/zhifang_rating.py b/q2_1_crawler/zhifang_rating.py new file mode 100644 index 0000000..ffde26d --- /dev/null +++ b/q2_1_crawler/zhifang_rating.py @@ -0,0 +1,21 @@ +import matplotlib.pyplot as plt +import json + +rating=[] + +with open('movie.json', 'r', encoding='utf-8') as f: + data=json.load(f) + # print(data) + for i in data: + rating.append(i["rating"]) + +plt.figure(figsize=(12,8)) +plt.hist(rating, # 数据 + bins=10, # 分成几个柱子 + color='#3498DB', # 颜色 + edgecolor='white') # 柱子边框颜色 +plt.title('评分分布', fontsize=14) +plt.xlabel('评分', fontsize=13) +plt.grid(True, linestyle='--', alpha=0.5, axis='y') +plt.show() +plt.savefig("q4_3a_hist.png",dpi=150,format='png') \ No newline at end of file