Python 爬取淘帖里的帖子标题（1）

qiuyouzhi

Python 爬取淘帖里的帖子标题

from requests import get
from bs4 import BeautifulSoup as BS

def get_Tz(res):
    soup = BS(res.text, "html.parser")
    targ = soup.find_all("a",class_="xst", target="_blank")
    for each in targ:
        print(each.text)
        #print(each['title'])
        print(each['href'])

def get_Tz_write(res, f):
    soup = BS(res.text, "html.parser")
    targ = soup.find_all("a",class_="xst", target="_blank")
    for each in targ:
        f.write(each.text)
        f.write(each['href'])
        f.write('\n')

def main():
    n = int(input("请输入要下载的次数："))
    f = open("淘帖.txt", "w")

    for i in range(1,n):
        url = "https://fishc.com.cn/forum.php?mod=collection&action=view&ctid=%d" % i
        res = get(url)
        get_Tz_write(res, f)
    f.close()

if __name__ == "__main__":
    main()

有时候会报错，是正常现象，重新运行就好

不要爬太多哦~