僞代碼,當模板
import requests
import bs4
import re
def open_url(url):
headers = {
'user-agent': '網頁F12去找'
}
res = request.get(url,headers=headers)
return res
def find_movies(res):
soup = bs4.BeautifulSoup(res.text,'html.parser')
# 電影名
movies = []
targets = soup.find_all("div",class="hd")
for each in targets:
movies.append(each.a.span.text)
# 評分
ranks= []
targets = soup.find_all("span",class="rating_num")
for each in targets:
#ranks.append('評分:%s' % each.text)
ranks.append(each.text)
# 資料
messages = []
targets = soup.find_all("div",class="bd")
for each in targets:
try:
messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
except:
continue
result = []
length = len(movies)
for i in range(length):
#result.append(movies[i] + rank[i] + messages[i] + '\n')
result.append([movies[i],rank[i],messages[i]])
return result
# 找出一共多少個頁面
def find_depth(res):
soup = bs4.BeautifulSOup(res.text,'html.parser')
depth = soup.find('span',class_='next').previous_sibling.previous_sibling.text
return int(depth)
def save_to_excel(result):
wb = openpyxl.Workbook()
ws = wb.active
ws.append(['電影名稱','評分','資料'])
for each in result:
ws.append(each)
ws.save("1.xlsx)
def main():
host = "一個網頁的url"
res = open_url(host)
depth = find_depth(res)
result = []
for i in range(depth):
url = host + '/?start=' + str(25 * i)
res = open_url(url)
result.extend(find_movies(res))
'''
with open("1.txt","w",encoding="utf-8") as f:
for each in result:
f.write(each)
'''
save_to_excel(result)
main()