1.先获取到一个页面,状态码200是成功返回
def get_one_page(url):
# 获取一个页面
try:
response = requests.get(url)
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
2.解析一个页面,先创建一个正则表达式对象,接着进行正则匹配,然后通过键值对形式存储
def parse_one_page(html):
pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
items = re.findall(pattern,html)
for item in items:
yield {
'index': item[0],
'image': item[1],
'title': item[2],
'actor': item[3].strip()[3:],
'time': item[4].strip()[5:],
'score': item[5]+item[6]
}
3.写入文件中,encoding=”“和ensure_ascii=''“用来存储中文字符
def write_to_file(content):
with open('Top100.txt', 'a', encoding='utf-8') as f:
f.write(json.dumps(content, ensure_ascii=False)+'\n')
f.close()
最后附上完整的源代码
import json
import requests
from requests.exceptions import RequestException
import re
from multiprocessing import Pool
def get_one_page(url):
# 获取一个页面
try:
response = requests.get(url)
if response.status_code == 200:
return response.text
return None
except RequestException:
return None
def parse_one_page(html):
pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
'.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
items = re.findall(pattern,html)
for item in items:
yield {
'index': item[0],
'image': item[1],
'title': item[2],
'actor': item[3].strip()[3:],
'time': item[4].strip()[5:],
'score': item[5]+item[6]
}
def write_to_file(content):
with open('Top100.txt', 'a', encoding='utf-8') as f:
f.write(json.dumps(content, ensure_ascii=False)+'\n')
f.close()
def main(offset):
url = "http://maoyan.com/board/4?offset=" + str(offset)
html = get_one_page(url)
for item in parse_one_page(html):
print(item)
write_to_file(item)
if __name__ == "__main__":
pool = Pool()
pool.map(main, [i*10 for i in range(10)])
注:由于使用了线程池,因此不一定按顺序存储。但是速度上快了许多,如果对速度要求不高,期望按顺序存储可以不使用线程池,直接调用main(offset)方法即可!附上效果图: