写在前面
第一次写博客。。记录下自己学习python的过程。
这是一个标题
1:用到的包
import requests
import json
import time
import sys
2:构造URL
#构造url
urls = []
movieID = '1375'#这个是《活着》的电影ID
for i in range(100):
urls.append('https://m.maoyan.com/mmdb/comments/movie/' + movieID + '.json?v=yes&offset=' + str(i*15) + '&limit=20&ts=0')
#其实一行代码就能解决。。我太菜了
3:读取网页
def get_data(url,headers):
r = requests.get(url,headers = headers)
#r.encoding = r.apparent_encoding
#如果r.status_code = 200说明能够获取网页数据
if r.status_code == 200:
#print(r.status_code)
return r.text
else:
print('error')
return None
4:获取json数据
def parse_data(html):
#获取json数据,如果出了验证码则返回错误信息
try:
data = json.loads(html,encoding = 'utf-8').get('cmts')
#处理json数据防止乱码
non_bmp_map = dict.fromkeys(range(0x10000,sys.maxunicode + 1),0xfffd)
comments = []
#获取json数据中的'content'值
for i in range(len(data)):
comments.append(data[i]['content'].translate(non_bmp_map) + '\n')
#time.sleep(0.5)
return comments
except Exception as e:
print('无法获取json数据,请检查是否出现验证码!')
5:解决编码错误
#对于包含特殊字符的数据,调用sys进行处理
non_bmp_map = dict.fromkeys(range(0x10000,sys.maxunicode + 1),0xfffd)
#再对特殊字符串进行处理,如下
name.translate(non_bmp_map)
#不这样做的话会报编码错误
6:保存为txt
def save_data(urls,headers):
for url in urls:
try:
html = get_data(url,headers)
except Exception as e2:
print(e2)
comments = parse_data(html)
#影评保存为文本文件
for item in comments:
with open('yingping.txt','a',encoding = 'utf-8') as y:
y.write(item)
y.close()
#print(item)
#爬的太快了要停顿一下,不然为出现验证码
time.sleep(1)
7:主函数
if __name__ == '__main__':
#构造url
urls = []
movieID = '1375'
for i in range(100):
urls.append('https://m.maoyan.com/mmdb/comments/movie/' + movieID + '.json?v=yes&offset=' + str(i*15) + '&limit=20&ts=0')
#设置请求头
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
#如果文件不存在,则创建文件;如果文件存在,则清空文件内容
with open('yingping.txt','wt',encoding = 'utf-8') as y:
y.close()
try:
save_data(urls,headers)
except Exception as e1:
print(e1)
完整代码
import requests
import json
import time
import sys
def get_data(url,headers):
r = requests.get(url,headers = headers)
#r.encoding = r.apparent_encoding
#如果r.status_code = 200说明能够获取网页数据
if r.status_code == 200:
#print(r.status_code)
return r.text
else:
print('error')
return None
def parse_data(html):
#获取json数据,如果出了验证码则返回错误信息
try:
data = json.loads(html,encoding = 'utf-8').get('cmts')
#处理json数据防止乱码
non_bmp_map = dict.fromkeys(range(0x10000,sys.maxunicode + 1),0xfffd)
comments = []
#获取json数据中的'content'值
for i in range(len(data)):
comments.append(data[i]['content'].translate(non_bmp_map) + '\n')
#time.sleep(0.5)
return comments
except Exception as e:
print('无法获取json数据,请检查是否出现验证码!')
def save_data(urls,headers):
for url in urls:
try:
html = get_data(url,headers)
except Exception as e2:
print(e2)
comments = parse_data(html)
#影评保存为文本文件
for item in comments:
with open('yingping.txt','a',encoding = 'utf-8') as y:
y.write(item)
y.close()
#print(item)
#爬的太快了要停顿一下
time.sleep(1)
if __name__ == '__main__':
#构造url
urls = []
movieID = '1375'
for i in range(100):
urls.append('https://m.maoyan.com/mmdb/comments/movie/' + movieID + '.json?v=yes&offset=' + str(i*15) + '&limit=20&ts=0')
#设置请求头
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
#如果文件不存在,则创建文件;如果文件存在,则清空文件
with open('yingping.txt','wt',encoding = 'utf-8') as y:
y.close()
try:
save_data(urls,headers)
except Exception as e1:
print(e1)
结果
很好,没有出现乱码!
爬了有300条就这样了。。
写在后面
第一次写博客,不得不说,是一次很有意义的尝试呢。