From fb2f791356c134d8a26817e0a69b3b67ba7fc62d Mon Sep 17 00:00:00 2001
From: hjCodeCloud <7482185+hjcodecloud@user.noreply.gitee.com>
Date: Tue, 29 Jun 2021 17:38:21 +0800
Subject: [PATCH] =?UTF-8?q?=E8=85=BE=E8=AE=AF=E5=8A=A8=E6=BC=AB=E7=88=AC?=
 =?UTF-8?q?=E8=99=AB=E4=BB=A3=E7=A0=81?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 ...54\350\231\253\344\273\243\347\240\201.py" | 75 +++++++++++++++++++
 1 file changed, 75 insertions(+)
 create mode 100644 "NO10/\350\205\276\350\256\257\345\212\250\346\274\253\347\210\254\350\231\253\344\273\243\347\240\201.py"

diff --git "a/NO10/\350\205\276\350\256\257\345\212\250\346\274\253\347\210\254\350\231\253\344\273\243\347\240\201.py" "b/NO10/\350\205\276\350\256\257\345\212\250\346\274\253\347\210\254\350\231\253\344\273\243\347\240\201.py"
new file mode 100644
index 0000000..fa94a2a
--- /dev/null
+++ "b/NO10/\350\205\276\350\256\257\345\212\250\346\274\253\347\210\254\350\231\253\344\273\243\347\240\201.py"
@@ -0,0 +1,75 @@
+import requests
+from fake_useragent import UserAgent
+import re
+import threading
+
+
+def replace_mark(my_str):
+    return my_str.replace(",", "，").replace('"', "“")
+
+
+def format_html(html):
+    li_pattern = re.compile(
+        '<li\sclass="ret-search-item clearfix">[\s\S]+?</li>')
+    title_url_pattern = re.compile(
+        '<a href="(.*?)" target="_blank" title=".*?">(.*?)</a>')
+    sign_pattern = re.compile('<i class="ui-icon-sign">签约</i>')
+    exclusive_pattern = re.compile('<i class="ui-icon-exclusive">独家</i>')
+    author_pattern = re.compile(
+        '<p class="ret-works-author" title=".*?">(.*?)</p>')
+    tags_pattern = re.compile('<span href=".*?" target="_blank">(.*?)</span>')
+    score_pattern = re.compile('<span>人气：<em>(.*?)</em></span>')
+    items = li_pattern.findall(html)
+    for item in items:
+        title_url = title_url_pattern.search(item)
+        title = title_url.group(2)
+        url = title_url.group(1)
+        sign = 0
+        exclusive = 0
+        if sign_pattern.search(item) is not None:
+            sign = 1
+        if exclusive_pattern.search(item) is not None:
+            exclusive = 1
+
+        author = author_pattern.search(item).group(1)
+
+        tags = tags_pattern.findall(item)
+
+        score = score_pattern.search(item).group(1)
+        lock.acquire()
+        with open("./qq.csv", "a+", encoding="utf-8") as f:
+            f.write(
+                f'{replace_mark(title)},{url},{sign},{exclusive},{replace_mark(author)},{"#".join(tags)},"{replace_mark(score)}" \n')
+
+        lock.release()
+
+
+def run(index):
+
+    ua = UserAgent(use_cache_server=False)
+
+    response = requests.get(
+        f"https://ac.qq.com/Comic/index/page/{index}", headers={'User-Agent': ua.random})
+    html = response.text
+    format_html(html)
+    semaphore.release()
+
+
+lock = threading.Lock()
+if __name__ == "__main__":
+
+    num = 0
+
+    semaphore = threading.BoundedSemaphore(5)
+    lst_record_threads = []
+    for index in range(1, 462):
+        print(f"正在抓取{index}")
+        semaphore.acquire()
+        t = threading.Thread(target=run, args=(index, ))
+        t.start()
+        lst_record_threads.append(t)
+
+    for rt in lst_record_threads:
+        rt.join()
+
+    print("数据爬取完毕")
-- 
GitLab