目的:学习正则表达式
过程中遇到的问题:
item[1]后面忘记写逗号,导致item[2]执行时语法错误;
RE中引用的字符串中有"|",被优先识别为“或”,导致抓取的数据存储时另外成为一个集合,用"."替代即可;
python中range函数的用法,range(1,6)={1,2,3,4,5}
具体程序如下:
#起点月票榜TOP100
import requests
import re
import json
def request_qidian(url):
try:
response = requests.get(url)
if response.status_code == 200:
return response.text
except requests.RequestException:
return None
def parse_result(html):
pattern = re.compile('<div class="book-img-box">.*?>(\d+)<.*?<h4><a href=.*?"qd_C40".*?>(.*?)</a></h4>.*?<p class="author">.*?target="_blank".*?>(.*?)</a><em>.</em><a href=.*?>(.*?)</a>.*?<p class="intro">\r *(.*?)\r.*?</li>',re.S)
items = re.findall(pattern,html)
for item in items:
yield {
'No.': item[0],
'name' : item[1],
'author' : item[2],
'genre' : item[3],
'intro' : item[4]
}
def write_item_to_file(item):
print('开始写入数据 ====> ' + str(item))
with open('bookrank.txt', 'a', encoding='UTF-8') as f:
f.write(json.dumps(item, ensure_ascii=False) + '\n')
f.close()
def main(page):
url = 'https://www.qidian.com/rank/yuepiao?page=' + str(page)
html = request_qidian(url)
items = parse_result(html) # 解析过滤我们想要的信息
for item in items:
write_item_to_file(item)
if __name__ == "__main__":
for i in range(1,6):
main(i)