OpenSourceJoker/GetQzonehistory
3
0
Fork 0
mirror of https://github.com/LibraHp/GetQzonehistory.git synced 2025-02-23 14:09:07 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

修复获取说说时中途退出的bug

Browse Source
This commit is contained in:
LibraHp_0928 2024-09-10 15:37:41 +08:00
parent 38a4b95ed1
commit 9b56f514cf
2 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
/resource/
.idea
/myenv/

25
main.py
View File

@ -239,11 +239,23 @@ def get_message(start, count):
g_tk, g_tk,
], ],
} }
response = requests.get('https://user.qzone.qq.com/proxy/domain/ic2.qzone.qq.com/cgi-bin/feeds/feeds2_html_pav_all',
params=params, cookies=cookies, headers=headers) try:
response = requests.get(
'https://user.qzone.qq.com/proxy/domain/ic2.qzone.qq.com/cgi-bin/feeds/feeds2_html_pav_all',
params=params,
cookies=cookies,
headers=headers,
timeout=(5, 10) # 设置连接超时为5秒，读取超时为10秒
)
except requests.Timeout:
print("请求超时")
return None
return response return response
def get_login_user_info(): def get_login_user_info():
response = requests.get('https://r.qzone.qq.com/fcg-bin/cgi_get_portrait.fcg?g_tk=' + str(g_tk) + '&uins=' + uin, response = requests.get('https://r.qzone.qq.com/fcg-bin/cgi_get_portrait.fcg?g_tk=' + str(g_tk) + '&uins=' + uin,
headers=headers, cookies=cookies) headers=headers, cookies=cookies)
@ -319,20 +331,21 @@ if __name__ == '__main__':
for i in trange(int(count / 100) + 1, desc='Progress', unit='100条'): for i in trange(int(count / 100) + 1, desc='Progress', unit='100条'):
message = get_message(i * 100, 100).content.decode('utf-8') message = get_message(i * 100, 100).content.decode('utf-8')
time.sleep(0.2)
html = process_old_html(message) html = process_old_html(message)
if "li" not in html: if "li" not in html:
break continue
soup = BeautifulSoup(html, 'html.parser') soup = BeautifulSoup(html, 'html.parser')
for element in soup.find_all('li', class_='f-single f-s-s'): for element in soup.find_all('li', class_='f-single f-s-s'):
time = None put_time = None
text = None text = None
time_element = element.find('div', class_='info-detail') time_element = element.find('div', class_='info-detail')
text_element = element.find('p', class_='txt-box-title ellipsis-one') text_element = element.find('p', class_='txt-box-title ellipsis-one')
if time_element is not None and text_element is not None: if time_element is not None and text_element is not None:
time = time_element.get_text().replace('\xa0', ' ') put_time = time_element.get_text().replace('\xa0', ' ')
text = text_element.get_text().replace('\xa0', ' ') text = text_element.get_text().replace('\xa0', ' ')
if text not in [sublist[1] for sublist in texts]: if text not in [sublist[1] for sublist in texts]:
texts.append([time, text]) texts.append([put_time, text])
if len(texts) > 0: if len(texts) > 0:
save_data() save_data()