1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
|
import gspread
from google.oauth2.service_account import Credentials
import requests
from bs4 import BeautifulSoup
import time
NEW_BOOK_URL = "https://www.books.com.tw/web/books_newbook/"
book_list_get = []
def main():
book_list = book_types(NEW_BOOK_URL)
for index,item in enumerate(book_list):
print(f"({index+1}) {item['title']}")
kind_no = int(input("輸入圖書分類:"))
if kind_no >= 1 and kind_no <= len(book_list):
get_books(kind_no, book_list[kind_no-1]['url'], book_list[kind_no-1]['title'])
save_to_google_sheet()
else:
print("分類錯誤!")
def get_books(index, url, title):
print(f"-- {index} {title} {url} --")
book_url = f"{url}?o=5&v=1"
try:
resp = requests.get(book_url)
except:
resp = None
pages = 0
start_index = 1
if resp and resp.status_code == 200:
soup = BeautifulSoup(resp.text, "html.parser")
try:
pages = int(soup.select_one(".cnt_page .page span").text)
except:
pages = 1
books_no = show_books(title, start_index, soup)
start_index += books_no
if (pages > 1):
for i in range(2, pages + 1):
book_url = f"{url}?o=5&v=1&page={str(i)}"
try:
resp = requests.get(book_url)
except:
resp = None
if resp and resp.status_code == 200:
soup = BeautifulSoup(resp.text, "html.parser")
books_no = show_books(title, start_index, soup)
start_index += books_no
def show_books(type_title, start_index, soup):
global book_list_get
books = soup.select(".wrap .item")
for index,book in enumerate(books):
title = book.select_one(".msg h4 a").text
img_url = book.select_one(".cover")['src']
info = book.select_one(".info").text.split('，')
author = info[0]
publisher = info[1]
publish_date = info[2].split("：")[1]
price_box = book.select(".price strong")
if len(price_box) == 1:
special_discount = '100'
special_price = price_box[0].text
else:
special_discount = price_box[0].text
special_price = price_box[1].text
content = book.select_one(".txt_cont").text.strip().replace("\n", "").replace(" ", "")
list_data = [type_title, title, img_url, author, publisher, publish_date, special_discount, special_price, content]
book_list_get.append(list_data)
return len(books)
def book_types(book_url):
book_list = []
try :
resp = requests.get(book_url)
except:
resp = None
if resp and resp.status_code == 200:
soup = BeautifulSoup(resp.text, "html.parser")
types = soup.select(".mod_b li a")
for type in types:
book_list.append(
{
'title': type.text,
'url': type['href'].split("?")[0]
}
)
return book_list
def save_to_google_sheet():
global book_list_get
scopes = [
"https://www.googleapis.com/auth/spreadsheets"
]
creds = Credentials.from_service_account_file("tutorial-sheets-421106-4878ffb056ac.json", scopes=scopes)
client = gspread.authorize(creds)
sheet_id = '1m6s3HXmc6vtVuvbgF5MytNIGB1BgdnovDWdqT7pJZJs'
workbook = client.open_by_key(sheet_id)
print("save books to google sheet..")
sheet = workbook.get_worksheet(0)
sheet.clear()
list_title = ["分類", "書名", "圖片網址", "作者", "出版社", "出版日期", "折扣", "優惠價", "內容"]
sheet.append_row(list_title)
for item in book_list_get:
sheet.append_row(item)
time.sleep(1.2)
if __name__ == '__main__':
main()
|
