标题标题2026-09-11
⚠️ 是聚合列表：条目分布在 syzl/gggsXX、bmzysz/gsggl/gggsXX 等多个子栏目 → 全收
⚠️ 页脚「网站声明/联系我们」(/fzllm/wzxx/) 无日期 span，天然被过滤
详情: /bmzysz/gsgg/content/post_N.html (亦可能是子栏目 /xx/content/post_N.html)
meta ArticleTitle(完整标题) / PubDate(YYYY-MM-DD)
正文: div.article-content > div.txt ← 取 div.txt 可避开 h3 标题重复/subtitle/share/copyright
N)datetime timedelta)
BeautifulSoup
JSONL_PATH utf-8u 化州市-公告公示u 广东zcrawl_huazhou_gsgg.pyu 公告公示zhttp://www.huazhou.gov.cnz&http://www.huazhou.gov.cn/bmzysz/gsgg/z
index_%d.htmliG )daysz%Y-%m-%dzkMozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0 Safari/537.36z?text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8zzh-CN,zh;q=0.9)z
User-AgentAcceptzAccept-Language z--pages== z--pagesc ` | syt j | } | j dd j dd j dd j dd } t j dd| } t j dd| } t j dd | } | j S )
Nr u u u u u3 ^\s*(?:·|·|\u00b7)?\s*(?: |\u00a0)?\s*u ^[•·]\s*\s+ )html_libunescapereplaceresubstrip)ts crawl_huazhou_gsgg.py clean_titler < s ! A (B ''"5==hKSST\^`aA
Er1MA
~r1%A
vsA A 779 c t t }|r||d< d }t d D ] } dd l}dd l}|j |j j |j | ||d }|j dk( rt |_ |j c S d|j z }t j d t# d
| d d d |d
y # t $ r} t | d d }Y d } ~ Jd } ~ ww xY w)Nr
r F)headerstimeoutverify zHTTP %sP z [fetch fail] Z z -> Tflush)dictHEADERSrangerequestsurllib3disable_warnings
exceptionsInsecureRequestWarningget status_codeENCencodingtext Exceptionstrtimesleepprint)
urlr accepthlast_err_r) r* res
r fetchr? G s W
A
( H
1X # $ $ $W%7%7%N%N O S!WU KA}}#
vv
1==0H
1
s3Bx
:$G #1vcr{H #s A'CC C0C++C0c
)*+ | sddg fS t j dd| t j } t j dd| t j } t j dd| t j t j z } t j dd| t j t j z } g )i *t j dd| } t r t | d }|j d
g D ] }|j
|j d D ]N }|j d
xs dj dd j }d|v sd|v s?|j
P t | } t r t | d }|j dd D ] }|d }|j d sV|j d sEd|j d xs g v s.t j d|t j s d|v sd|v sp|xs dj }|j d xs |j d xs dj } |r(t j d |t j s|}
n| xs |}
|j d xs[ |j d xsH |j d xs5 t j" j% |
j' d! d xs d"} t( j* j- |
} )j/ | | f d#t1 * z }
d$| d%| d&*|
< |j3 |
|j d' D ]` }|j d( xs |j d xs d}t j d)|t j sQ|j
b |j d* D ]@ }|j d' }|s|j d r+g }|D ] }|j d( xs |j d xs d}|s.t( j* j- | } |j d+ xs |j d xs dj xs5 t j" j% |j' d! d xs d,} |j/ d$| d%| d& |sd-t1 * z }
d.d/j5 | z d0z *|
< |j3 |
C |j d' D ] }|j d( xs |j d xs d}|s.t( j* j- | } |j d+ xs |j d xs dj xs5 t j" j% |j' d! d xs d,} d-t1 * z }
d1| d%| d2*|
< |j3 |
t | } )*fd3}t j d4|| t j t j z } t r t | d }|j d D ]% }d5D ] }|j6 j9 |d6 ' |j d7 D ]h }|j d sD|j; d8 s3|j; d' s"|j; d s|j
Y|j= j t | } g ++fd9}t j d:| t j rd;nd}d6}|| k7 r@| }t j d<|| t j t j z } || k7 r@t j d0d=| t j } t j d>d?| t j } t j d@d| t j } g }| j' dA D ] }|j } | st j dBd| } t j dCd| } | j dDd j dEd } t j dFd| } t j dGd| } t? j@ | } | j dHd j dId } t j dJd| } | st j dK| r*jC D ] \ } } | j | | } tE + D ] \ } }!| j dL| z |! } t j dM| t j s*t j dN| t j rdO| z } |j/ | j dAj5 | }"*jC D ] \ } } |"j | | }" tE + D ] \ } }!|"j dL| z |! }" t j dPd|" }"t? j@ |" }"t j dQd?|" }"t j dRdA|" }"t j dFd|" }"tG g }$}#|"j' dA D ]W }t j dSdt j dGd| }
|
r|
|#v r6|#jI |
|$j/ | Y dAj5 |$ j }"g tG }&}%)D ]. \ }'}(|'|&v r |&jI |' |%j/ |'|(f 0 |"||%fS # t $ r Y
9w xY w# t $ r Y w xY w# t $ r Y w xY w)TuR 正文 HTML 清洗：保留 /