[已解决]xdm，爬虫求助

形影似我遁无声

python快期末了，快要交期末大作业了，但平时上课没好好听课，以及自学才刚学到类和对象，急需一份爬虫来完成大作业，如果有哪位朋友最近写了一份爬虫且有注释，希望可以借用一下，可以有偿，拜托了

最佳答案

月排行榜 / 总排行榜

小伤口

2021-6-6 14:09:26

这是我之前写的爬取京东评论和用户照片加上简单的可视化处理，你可以参考一下，

1. import requests
   
2. import json
   
3. import queue
   
4. import collections
   
5. import threading
   
6. import time
   
7. import numpy as np
   
8. import matplotlib.pyplot as plt
   
9. from matplotlib.font_manager import FontProperties
   
10. dict_data = []
    
11. dict_data2 = []
    
12. dict_data3 = []
    
13. zhao_pian = []
    
14. # 创建多线程
    
15. #爬取时间
    
16. class MyThread_j(threading.Thread):
    
17.     def __init__(self, q):
    
18.         threading.Thread.__init__(self)
    
19.         self.q = q
    
20.     #调用get_index()
    
21.     def run(self) -> None:
    
22.         self.get_index()
    
23.     def get_index(self):
    
24.         url = self.q.get()
    
25.         # 加请求头
    
26.         headers = {
    
27.             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
    
28.         res = requests.get(url, headers=headers )
    
29.         #处理数据
    
30.         jd = json.loads(res.text.lstrip("fetchJSON_comment98(").rstrip(");"))
    
31.         #将时间存在data2.txt文件中
    
32.         for i in jd['comments']:
    
33.             x_zuobiao=i['creationTime'].split(' ')
    
34.             x_zuobiao=x_zuobiao[0].split('-')
    
35.             x_zuobiao=x_zuobiao[0]+x_zuobiao[1]
    
36.             with open("data2.txt", "a", encoding="utf-8") as file:
    
37.                 file.write(x_zuobiao+ '\n')
    
38. for i in range(5,10):
    
39.     locals()['MyThread_j' + str(i)] = MyThread_j
    
40. # 创建多线程
    
41. #爬取评论
    
42. class MyThread(threading.Thread):
    
43.     def __init__(self, q):
    
44.         threading.Thread.__init__(self)
    
45.         self.q = q
    
46.     # 调用get_index()
    
47.     def run(self) -> None:
    
48.         self.get_index()
    
49.     def get_index(self):
    
50.         url = self.q.get()
    
51.         # 加请求头
    
52.         headers = {
    
53.             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
    
54.         res = requests.get(url, headers=headers)
    
55.         #处理数据
    
56.         jd = json.loads(res.text.lstrip("jQuery593159(").rstrip(");"))
    
57.         #将评论存在data.txt中
    
58.         with open("data.txt", "a", encoding="utf-8") as file:
    
59.             for i in jd['comments']:
    
60.                 file.write(i['content'] + '\n')
    
61.             #爬取照片并存在列表中
    
62.             try:
    
63.                 for each in i['images']:
    
64.                     photo = each['imgUrl'].split('//')
    
65.                     photo = photo[-1]
    
66.                     photo = 'https://' + photo
    
67.                     print(photo)
    
68.                     zhao_pian.append(photo)
    
69.             except:
    
70.                 pass
    
71. for i in range(5):
    
72.     locals()['MyThread_' + str(i)] = MyThread
    
73. def main(url_d):
    
74.     # 创建队列存储url
    
75.     q = queue.Queue()
    
76.     url_d = url_d.split('/')
    
77.     url_d = ''.join(url_d[-1])
    
78.     url_d = url_d.split('.')
    
79.     url_d = url_d[0]
    
80.     for i in range(5):
    
81.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(i) + "&pageSize=10&isShadowSku=0&fold=1"
    
82.         q.put(url)
    
83.         # 如果队列不为空，就继续爬
    
84.         while not q.empty():
    
85.             t = MyThread_j5(q)
    
86.             t.start()
    
87.             t.join()
    
88.     for i in range(5,10):
    
89.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
    
90.             i) + "&pageSize=10&isShadowSku=0&fold=1"
    
91.         q.put(url)
    
92.         # 如果队列不为空，就继续爬
    
93.         # 如果队列不为空，就继续爬
    
94.         while not q.empty():
    
95.             t_1 = MyThread_j6(q)
    
96.             t_1.start()
    
97.             t_1.join()
    
98.     for i in range(10,15):
    
99.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
    
100.             i) + "&pageSize=10&isShadowSku=0&fold=1"
     
101.         q.put(url)
     
102.         # 如果队列不为空，就继续爬
     
103.         # 如果队列不为空，就继续爬
     
104.         while not q.empty():
     
105.             t_2 = MyThread_j7(q)
     
106.             t_2.start()
     
107.             t_2.join()
     
108.     for i in range(15,20):
     
109.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
     
110.             i) + "&pageSize=10&isShadowSku=0&fold=1"
     
111.         q.put(url)
     
112.         # 如果队列不为空，就继续爬
     
113.         # 如果队列不为空，就继续爬
     
114.         while not q.empty():
     
115.             t_3 = MyThread_j8(q)
     
116.             t_3.start()
     
117.             t_3.join()
     
118.     for i in range(20,25):
     
119.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
     
120.             i) + "&pageSize=10&isShadowSku=0&fold=1"
     
121.         q.put(url)
     
122.         # 如果队列不为空，就继续爬
     
123.         # 如果队列不为空，就继续爬
     
124.         while not q.empty():
     
125.             t_4 = MyThread_j9(q)
     
126.             t_4.start()
     
127.             t_4.join()
     
128.     for i in range(5):
     
129.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=2&sortType=5&page=" + str(
     
130.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
131. 
     
132.         q.put(url)
     
133.         # 如果队列不为空，就继续爬
     
134.         while not q.empty():
     
135.             t = MyThread_0(q)
     
136.             t.start()
     
137.             t.join()
     
138.     for i in range(10):
     
139.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=1&sortType=5&page=" + str(
     
140.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
141.         q.put(url)
     
142. 
     
143.         # 如果队列不为空，就继续爬
     
144.         # 如果队列不为空，就继续爬
     
145.         while not q.empty():
     
146.             t_1 = MyThread_1(q)
     
147.             t_1.start()
     
148.             t_1.join()
     
149.     for i in range(10, 15):
     
150.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=2&sortType=5&page=" + str(
     
151.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
152. 
     
153.         q.put(url)
     
154.         # 如果队列不为空，就继续爬
     
155.         # 如果队列不为空，就继续爬
     
156.         while not q.empty():
     
157.             t_2 = MyThread_2(q)
     
158.             t_2.start()
     
159.             t_2.join()
     
160.     for i in range(15, 20):
     
161.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=3&sortType=5&page=" + str(
     
162.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
163.         q.put(url)
     
164.         # 如果队列不为空，就继续爬
     
165.         # 如果队列不为空，就继续爬
     
166.         while not q.empty():
     
167.             t_3 = MyThread_3(q)
     
168.             t_3.start()
     
169.             t_3.join()
     
170.     for i in range(20, 25):
     
171.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=3&sortType=5&page=" + str(
     
172.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
173.         q.put(url)
     
174.         # 如果队列不为空，就继续爬
     
175.         # 如果队列不为空，就继续爬
     
176.         while not q.empty():
     
177.             t_4 = MyThread_4(q)
     
178.             t_4.start()
     
179.             t_4.join()
     
180.     #读取并保存照片
     
181.     name = 0
     
182.     for i in zhao_pian[:]:
     
183.         r = requests.get(i)
     
184.         name += 1
     
185.         with open(str(name) + '.jpg', 'wb') as f:
     
186.             f.write(r.content)
     
187.     #将时间提取出来，并进行排序计数
     
188.     with open("data2.txt") as file:
     
189.         for line in file.readlines():
     
190.             dict_data.append(int(line))
     
191.     dict_data.sort()
     
192.     dic = collections.Counter(dict_data)
     
193.     for i in dic:
     
194.         dict_data2.append(str(i))
     
195.         dict_data3.append(dic[i])
     
196.     #绘制折线图
     
197.     x = np.array(dict_data2)
     
198.     y = np.array(dict_data3)
     
199.     fig=plt.figure(figsize=(25, 10))
     
200.     fig.patch.set_facecolor('Turquoise')
     
201.     ax = fig.add_subplot(111)
     
202.     ax.patch.set_facecolor('DeepSkyBlue')
     
203.     plt.plot(x, y, 'r')  # 折线 1 x 2 y 3 color
     
204.     plt.plot(x, y, 'red', lw=2)  # 4 line w
     
205.     plt.scatter(x, y, color='red', marker='o')
     
206.     font = FontProperties(fname="mnjzbh.ttf")
     
207.     plt.title("销售趋势(按时间顺序)", fontsize=24,fontproperties=font)
     
208.     plt.xlabel("时间(年，月)", fontsize=14,fontproperties=font)
     
209.     plt.ylabel("销售数量(件)", fontsize=14,fontproperties=font)
     
210.     plt.savefig('Figure_1.png', bbox_inches='tight')
     
211.     plt.show()
     
212. if __name__ == '__main__':
     
213.     url_d = input('输入网址:')
     
214.     start_time = time.time()
     
215.     main(url_d)
     
216.     end_time = time.time()
     
217.     print("耗时%d" % (end_time - start_time))
     

复制代码

跳转到最佳答案楼层

zhangli742

1. import requests
   
2. import re
   
3. import csv
   
4. #设置查找条件
   
5. obj = re.compile(r'<li>.*?<span class="title">(?P<name>.*?)</span>.*?<br>(?P<year>.*?)&nbsp.*?<span class="rating_num" '
   
6.                  r'property="v:average">(?P<score>.*?)</span>.*?<span>(?P<num>.*?)人评价</span>',re.S)
   
7. #设置请求头
   
8. headers = {
   
9.     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.128 Safari/537.36'
   
10. }
    
11. #输入流
    
12. f = open('./imgs/top250电影排行榜.csv',mode='w',encoding="utf-8")
    
13. csvwriter = csv.writer(f)
    
14. #爬取数据
    
15. for page in range(0,250,25):
    
16.     #url地址
    
17.     url = 'https://movie.douban.com/top250?start={}&filter='.format(page)
    
18.     #发送请求
    
19.     response = requests.get(url,headers=headers)
    
20.     #获取页面信息
    
21.     page_content = response.text
    
22.     #查找需要爬取的内容
    
23.     result = obj.finditer(page_content)
    
24.     #将信息写入文件
    
25.     for it in result:
    
26.         dic = it.groupdict()
    
27.         dic['year'] = dic['year'].strip()
    
28.         csvwriter.writerow(dic.values())
    
29. f.close()
    
30. print('抓取完毕')
    

复制代码

suchocolate

具体问题是什么？

形影似我遁无声

suchocolate 发表于 2021-6-6 08:39
具体问题是什么？

没有具体问题，就是你想做什么就做什么，爬虫分会相对高点

wp231957

形影似我遁无声 发表于 2021-6-6 08:42
没有具体问题，就是你想做什么就做什么，爬虫分会相对高点

最简单的爬虫也就几行代码，也能拿高分？？

形影似我遁无声

wp231957 发表于 2021-6-6 08:45
最简单的爬虫也就几行代码，也能拿高分？？

那肯定是不能的，糊弄他也不能这么糊弄啊。但如果就做个游戏啥的，不管你做的多好，即使是你做了很久很精美的游戏，他也只会给个及格分，相比而言爬虫，数据可视化之类的好拿分多了

路神

981048327

形影似我遁无声

zhangli742 发表于 2021-6-6 03:02

多谢了

小伤口

这是我之前写的爬取京东评论和用户照片加上简单的可视化处理，你可以参考一下，

1. import requests
   
2. import json
   
3. import queue
   
4. import collections
   
5. import threading
   
6. import time
   
7. import numpy as np
   
8. import matplotlib.pyplot as plt
   
9. from matplotlib.font_manager import FontProperties
   
10. dict_data = []
    
11. dict_data2 = []
    
12. dict_data3 = []
    
13. zhao_pian = []
    
14. # 创建多线程
    
15. #爬取时间
    
16. class MyThread_j(threading.Thread):
    
17.     def __init__(self, q):
    
18.         threading.Thread.__init__(self)
    
19.         self.q = q
    
20.     #调用get_index()
    
21.     def run(self) -> None:
    
22.         self.get_index()
    
23.     def get_index(self):
    
24.         url = self.q.get()
    
25.         # 加请求头
    
26.         headers = {
    
27.             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
    
28.         res = requests.get(url, headers=headers )
    
29.         #处理数据
    
30.         jd = json.loads(res.text.lstrip("fetchJSON_comment98(").rstrip(");"))
    
31.         #将时间存在data2.txt文件中
    
32.         for i in jd['comments']:
    
33.             x_zuobiao=i['creationTime'].split(' ')
    
34.             x_zuobiao=x_zuobiao[0].split('-')
    
35.             x_zuobiao=x_zuobiao[0]+x_zuobiao[1]
    
36.             with open("data2.txt", "a", encoding="utf-8") as file:
    
37.                 file.write(x_zuobiao+ '\n')
    
38. for i in range(5,10):
    
39.     locals()['MyThread_j' + str(i)] = MyThread_j
    
40. # 创建多线程
    
41. #爬取评论
    
42. class MyThread(threading.Thread):
    
43.     def __init__(self, q):
    
44.         threading.Thread.__init__(self)
    
45.         self.q = q
    
46.     # 调用get_index()
    
47.     def run(self) -> None:
    
48.         self.get_index()
    
49.     def get_index(self):
    
50.         url = self.q.get()
    
51.         # 加请求头
    
52.         headers = {
    
53.             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
    
54.         res = requests.get(url, headers=headers)
    
55.         #处理数据
    
56.         jd = json.loads(res.text.lstrip("jQuery593159(").rstrip(");"))
    
57.         #将评论存在data.txt中
    
58.         with open("data.txt", "a", encoding="utf-8") as file:
    
59.             for i in jd['comments']:
    
60.                 file.write(i['content'] + '\n')
    
61.             #爬取照片并存在列表中
    
62.             try:
    
63.                 for each in i['images']:
    
64.                     photo = each['imgUrl'].split('//')
    
65.                     photo = photo[-1]
    
66.                     photo = 'https://' + photo
    
67.                     print(photo)
    
68.                     zhao_pian.append(photo)
    
69.             except:
    
70.                 pass
    
71. for i in range(5):
    
72.     locals()['MyThread_' + str(i)] = MyThread
    
73. def main(url_d):
    
74.     # 创建队列存储url
    
75.     q = queue.Queue()
    
76.     url_d = url_d.split('/')
    
77.     url_d = ''.join(url_d[-1])
    
78.     url_d = url_d.split('.')
    
79.     url_d = url_d[0]
    
80.     for i in range(5):
    
81.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(i) + "&pageSize=10&isShadowSku=0&fold=1"
    
82.         q.put(url)
    
83.         # 如果队列不为空，就继续爬
    
84.         while not q.empty():
    
85.             t = MyThread_j5(q)
    
86.             t.start()
    
87.             t.join()
    
88.     for i in range(5,10):
    
89.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
    
90.             i) + "&pageSize=10&isShadowSku=0&fold=1"
    
91.         q.put(url)
    
92.         # 如果队列不为空，就继续爬
    
93.         # 如果队列不为空，就继续爬
    
94.         while not q.empty():
    
95.             t_1 = MyThread_j6(q)
    
96.             t_1.start()
    
97.             t_1.join()
    
98.     for i in range(10,15):
    
99.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
    
100.             i) + "&pageSize=10&isShadowSku=0&fold=1"
     
101.         q.put(url)
     
102.         # 如果队列不为空，就继续爬
     
103.         # 如果队列不为空，就继续爬
     
104.         while not q.empty():
     
105.             t_2 = MyThread_j7(q)
     
106.             t_2.start()
     
107.             t_2.join()
     
108.     for i in range(15,20):
     
109.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
     
110.             i) + "&pageSize=10&isShadowSku=0&fold=1"
     
111.         q.put(url)
     
112.         # 如果队列不为空，就继续爬
     
113.         # 如果队列不为空，就继续爬
     
114.         while not q.empty():
     
115.             t_3 = MyThread_j8(q)
     
116.             t_3.start()
     
117.             t_3.join()
     
118.     for i in range(20,25):
     
119.         url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + url_d + "&score=1&sortType=6&page=" + str(
     
120.             i) + "&pageSize=10&isShadowSku=0&fold=1"
     
121.         q.put(url)
     
122.         # 如果队列不为空，就继续爬
     
123.         # 如果队列不为空，就继续爬
     
124.         while not q.empty():
     
125.             t_4 = MyThread_j9(q)
     
126.             t_4.start()
     
127.             t_4.join()
     
128.     for i in range(5):
     
129.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=2&sortType=5&page=" + str(
     
130.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
131. 
     
132.         q.put(url)
     
133.         # 如果队列不为空，就继续爬
     
134.         while not q.empty():
     
135.             t = MyThread_0(q)
     
136.             t.start()
     
137.             t.join()
     
138.     for i in range(10):
     
139.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=1&sortType=5&page=" + str(
     
140.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
141.         q.put(url)
     
142. 
     
143.         # 如果队列不为空，就继续爬
     
144.         # 如果队列不为空，就继续爬
     
145.         while not q.empty():
     
146.             t_1 = MyThread_1(q)
     
147.             t_1.start()
     
148.             t_1.join()
     
149.     for i in range(10, 15):
     
150.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=2&sortType=5&page=" + str(
     
151.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
152. 
     
153.         q.put(url)
     
154.         # 如果队列不为空，就继续爬
     
155.         # 如果队列不为空，就继续爬
     
156.         while not q.empty():
     
157.             t_2 = MyThread_2(q)
     
158.             t_2.start()
     
159.             t_2.join()
     
160.     for i in range(15, 20):
     
161.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=3&sortType=5&page=" + str(
     
162.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
163.         q.put(url)
     
164.         # 如果队列不为空，就继续爬
     
165.         # 如果队列不为空，就继续爬
     
166.         while not q.empty():
     
167.             t_3 = MyThread_3(q)
     
168.             t_3.start()
     
169.             t_3.join()
     
170.     for i in range(20, 25):
     
171.         url = "https://club.jd.com/comment/productPageComments.action?callback=jQuery593159&productId=" + url_d + "&score=3&sortType=5&page=" + str(
     
172.             i) + "&pageSize=10&pin=null&_=1616905936767"
     
173.         q.put(url)
     
174.         # 如果队列不为空，就继续爬
     
175.         # 如果队列不为空，就继续爬
     
176.         while not q.empty():
     
177.             t_4 = MyThread_4(q)
     
178.             t_4.start()
     
179.             t_4.join()
     
180.     #读取并保存照片
     
181.     name = 0
     
182.     for i in zhao_pian[:]:
     
183.         r = requests.get(i)
     
184.         name += 1
     
185.         with open(str(name) + '.jpg', 'wb') as f:
     
186.             f.write(r.content)
     
187.     #将时间提取出来，并进行排序计数
     
188.     with open("data2.txt") as file:
     
189.         for line in file.readlines():
     
190.             dict_data.append(int(line))
     
191.     dict_data.sort()
     
192.     dic = collections.Counter(dict_data)
     
193.     for i in dic:
     
194.         dict_data2.append(str(i))
     
195.         dict_data3.append(dic[i])
     
196.     #绘制折线图
     
197.     x = np.array(dict_data2)
     
198.     y = np.array(dict_data3)
     
199.     fig=plt.figure(figsize=(25, 10))
     
200.     fig.patch.set_facecolor('Turquoise')
     
201.     ax = fig.add_subplot(111)
     
202.     ax.patch.set_facecolor('DeepSkyBlue')
     
203.     plt.plot(x, y, 'r')  # 折线 1 x 2 y 3 color
     
204.     plt.plot(x, y, 'red', lw=2)  # 4 line w
     
205.     plt.scatter(x, y, color='red', marker='o')
     
206.     font = FontProperties(fname="mnjzbh.ttf")
     
207.     plt.title("销售趋势(按时间顺序)", fontsize=24,fontproperties=font)
     
208.     plt.xlabel("时间(年，月)", fontsize=14,fontproperties=font)
     
209.     plt.ylabel("销售数量(件)", fontsize=14,fontproperties=font)
     
210.     plt.savefig('Figure_1.png', bbox_inches='tight')
     
211.     plt.show()
     
212. if __name__ == '__main__':
     
213.     url_d = input('输入网址:')
     
214.     start_time = time.time()
     
215.     main(url_d)
     
216.     end_time = time.time()
     
217.     print("耗时%d" % (end_time - start_time))
     

复制代码

arrexxxx

小伤口 发表于 2021-6-6 14:09
这是我之前写的爬取京东评论和用户照片加上简单的可视化处理，你可以参考一下，

请问这里运行不了该怎么解决 求指教
Exception in thread Thread-11:
Traceback (most recent call last):
  File "E:\新建文件夹\lib\threading.py", line 973, in _bootstrap_inner
    self.run()
  File "C:/Users/admin/Desktop/京东评论区.py", line 22, in run
    self.get_index()
  File "C:/Users/admin/Desktop/京东评论区.py", line 30, in get_index
    jd = json.loads(res.text.lstrip("fetchJSON_comment98(").rstrip(");"))
  File "E:\新建文件夹\lib\json\__init__.py", line 346, in loads
    return _default_decoder.decode(s)
  File "E:\新建文件夹\lib\json\decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "E:\新建文件夹\lib\json\decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Exception in thread Thread-12:
Traceback (most recent call last):
  File "E:\新建文件夹\lib\threading.py", line 973, in _bootstrap_inner
    self.run()
  File "C:/Users/admin/Desktop/京东评论区.py", line 22, in run
    self.get_index()
  File "C:/Users/admin/Desktop/京东评论区.py", line 30, in get_index
    jd = json.loads(res.text.lstrip("fetchJSON_comment98(").rstrip(");"))
  File "E:\新建文件夹\lib\json\__init__.py", line 346, in loads
    return _default_decoder.decode(s)
  File "E:\新建文件夹\lib\json\decoder.py", line 337, in decode
    obj, end = self.raw_decode(s, idx=_w(s, 0).end())
  File "E:\新建文件夹\lib\json\decoder.py", line 355, in raw_decode
    raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

小伤口

arrexxxx 发表于 2021-8-31 21:20
请问这里运行不了该怎么解决 求指教
Exception in thread Thread-11:
Traceback (most recent ...

你现在再运行一下试试

arrexxxx

小伤口 发表于 2021-8-31 23:48
你现在再运行一下试试

还是不能正常运行，输入网址后显示的是这个东西
输入网址:https://item.jd.com/10027959220343.html
https://img30.360buyimg.com/n0/s ... 08933aa4c629b55.jpg
Traceback (most recent call last):
  File "C:\Users\admin\Desktop\京东评论区.py", line 215, in <module>
    main(url_d)
  File "C:\Users\admin\Desktop\京东评论区.py", line 210, in main
    plt.savefig('Figure_1.png', bbox_inches='tight')
  File "E:\新建文件夹\lib\site-packages\matplotlib\pyplot.py", line 966, in savefig
    res = fig.savefig(*args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\figure.py", line 3015, in savefig
    self.canvas.print_figure(fname, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\backend_bases.py", line 2230, in print_figure
    self.figure.draw(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 74, in draw_wrapper
    result = draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 51, in draw_wrapper
    return draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\figure.py", line 2790, in draw
    mimage._draw_list_compositing_images(
  File "E:\新建文件夹\lib\site-packages\matplotlib\image.py", line 132, in _draw_list_compositing_images
    a.draw(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 51, in draw_wrapper
    return draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\_api\deprecation.py", line 431, in wrapper
    return func(*inner_args, **inner_kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\axes\_base.py", line 2881, in draw
    self._update_title_position(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\axes\_base.py", line 2822, in _update_title_position
    if title.get_window_extent(renderer).ymin < top:
  File "E:\新建文件夹\lib\site-packages\matplotlib\text.py", line 903, in get_window_extent
    bbox, info, descent = self._get_layout(self._renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\text.py", line 306, in _get_layout
    _, lp_h, lp_d = renderer.get_text_width_height_descent(
  File "E:\新建文件夹\lib\site-packages\matplotlib\backends\backend_agg.py", line 239, in get_text_width_height_descent
    font = self._get_agg_font(prop)
  File "E:\新建文件夹\lib\site-packages\matplotlib\backends\backend_agg.py", line 274, in _get_agg_font
    font = get_font(fname)
  File "E:\新建文件夹\lib\site-packages\matplotlib\font_manager.py", line 1424, in get_font
    return _get_font(filename, hinting_factor,
  File "E:\新建文件夹\lib\site-packages\matplotlib\font_manager.py", line 1405, in _get_font
    return ft2font.FT2Font(
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\admin\\Desktop\\mnjzbh.ttf'
>>>

arrexxxx

小伤口 发表于 2021-8-31 23:48
你现在再运行一下试试

还是不行，输入网址后显示的是这样

https://img30.360buyimg.com/n0/s ... 08933aa4c629b55.jpg
Traceback (most recent call last):
  File "C:\Users\admin\Desktop\京东评论区.py", line 215, in <module>
    main(url_d)
  File "C:\Users\admin\Desktop\京东评论区.py", line 210, in main
    plt.savefig('Figure_1.png', bbox_inches='tight')
  File "E:\新建文件夹\lib\site-packages\matplotlib\pyplot.py", line 966, in savefig
    res = fig.savefig(*args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\figure.py", line 3015, in savefig
    self.canvas.print_figure(fname, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\backend_bases.py", line 2230, in print_figure
    self.figure.draw(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 74, in draw_wrapper
    result = draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 51, in draw_wrapper
    return draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\figure.py", line 2790, in draw
    mimage._draw_list_compositing_images(
  File "E:\新建文件夹\lib\site-packages\matplotlib\image.py", line 132, in _draw_list_compositing_images
    a.draw(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 51, in draw_wrapper
    return draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\_api\deprecation.py", line 431, in wrapper
    return func(*inner_args, **inner_kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\axes\_base.py", line 2881, in draw
    self._update_title_position(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\axes\_base.py", line 2822, in _update_title_position
    if title.get_window_extent(renderer).ymin < top:
  File "E:\新建文件夹\lib\site-packages\matplotlib\text.py", line 903, in get_window_extent
    bbox, info, descent = self._get_layout(self._renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\text.py", line 306, in _get_layout
    _, lp_h, lp_d = renderer.get_text_width_height_descent(
  File "E:\新建文件夹\lib\site-packages\matplotlib\backends\backend_agg.py", line 239, in get_text_width_height_descent
    font = self._get_agg_font(prop)
  File "E:\新建文件夹\lib\site-packages\matplotlib\backends\backend_agg.py", line 274, in _get_agg_font
    font = get_font(fname)
  File "E:\新建文件夹\lib\site-packages\matplotlib\font_manager.py", line 1424, in get_font
    return _get_font(filename, hinting_factor,
  File "E:\新建文件夹\lib\site-packages\matplotlib\font_manager.py", line 1405, in _get_font
    return ft2font.FT2Font(
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\admin\\Desktop\\mnjzbh.ttf'
>>>

arrexxxx

小伤口 发表于 2021-8-31 23:48
你现在再运行一下试试

还是没有过 只能打出图片

arrexxxx

arrexxxx 发表于 2021-9-1 11:31
还是没有过 只能打出图片

Traceback (most recent call last):
  File "C:\Users\admin\Desktop\京东评论区.py", line 215, in <module>
    main(url_d)
  File "C:\Users\admin\Desktop\京东评论区.py", line 210, in main
    plt.savefig('Figure_1.png', bbox_inches='tight')
  File "E:\新建文件夹\lib\site-packages\matplotlib\pyplot.py", line 966, in savefig
    res = fig.savefig(*args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\figure.py", line 3015, in savefig
    self.canvas.print_figure(fname, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\backend_bases.py", line 2230, in print_figure
    self.figure.draw(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 74, in draw_wrapper
    result = draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 51, in draw_wrapper
    return draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\figure.py", line 2790, in draw
    mimage._draw_list_compositing_images(
  File "E:\新建文件夹\lib\site-packages\matplotlib\image.py", line 132, in _draw_list_compositing_images
    a.draw(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\artist.py", line 51, in draw_wrapper
    return draw(artist, renderer, *args, **kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\_api\deprecation.py", line 431, in wrapper
    return func(*inner_args, **inner_kwargs)
  File "E:\新建文件夹\lib\site-packages\matplotlib\axes\_base.py", line 2881, in draw
    self._update_title_position(renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\axes\_base.py", line 2822, in _update_title_position
    if title.get_window_extent(renderer).ymin < top:
  File "E:\新建文件夹\lib\site-packages\matplotlib\text.py", line 903, in get_window_extent
    bbox, info, descent = self._get_layout(self._renderer)
  File "E:\新建文件夹\lib\site-packages\matplotlib\text.py", line 306, in _get_layout
    _, lp_h, lp_d = renderer.get_text_width_height_descent(
  File "E:\新建文件夹\lib\site-packages\matplotlib\backends\backend_agg.py", line 239, in get_text_width_height_descent
    font = self._get_agg_font(prop)
  File "E:\新建文件夹\lib\site-packages\matplotlib\backends\backend_agg.py", line 274, in _get_agg_font
    font = get_font(fname)
  File "E:\新建文件夹\lib\site-packages\matplotlib\font_manager.py", line 1424, in get_font
    return _get_font(filename, hinting_factor,
  File "E:\新建文件夹\lib\site-packages\matplotlib\font_manager.py", line 1405, in _get_font
    return ft2font.FT2Font(
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\admin\\Desktop\\mnjzbh.ttf'
>>>

arrexxxx

小伤口 发表于 2021-8-31 23:48
你现在再运行一下试试

打印图片之后是这样子的报错T T

arrexxxx

arrexxxx 发表于 2021-9-1 11:33
打印图片之后是这样子的报错T T

评论也是能打出来的，但是不明白为啥还是会报错。。

小伤口

arrexxxx 发表于 2021-9-1 11:33
打印图片之后是这样子的报错T T

这个是正常现象因为好像这个方法要弃用了，所以会显示这个