Shikong/python-selenium-spider
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

批量爬取 fanbox

Browse Source
This commit is contained in:
shikong 2024-05-12 02:41:53 +08:00
parent 7456e3dd82
commit 4accaec286
1 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
run/__init__.py
View File

@ -76,7 +76,7 @@ def download_image(url: str, download_dir: str, proxies):
print(f"开始下载：{url}")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36",
"Referer": "https://monpetit17.fanbox.cc/",
"Referer": "https://www.fanbox.cc/",
"Cookie": "p_ab_id=0; p_ab_id_2=1; p_ab_d_id=1743506050; _gcl_au=1.1.1973053698.1715103653; cf_clearance=9nglHcFCr9D17iz8392jJQIJi4oN8TSpBsvlS4oPjvs-1715103654-1.0.1.1-DLbaQVWB8O8lyUZyJ5P8ToQD7Bx7dt5r_7KUz9aFqIcEM5GiAunuXwAQRu5BJ3c3zBOt242Oy13YvXz1omV5Dw; FANBOXSESSID=35206256_01xWtpm33E6tjKYTAdLoVaZq5xceRVNB; privacy_policy_agreement=6; privacy_policy_notification=0; _gid=GA1.2.1663028388.1715442061; __cf_bm=YRkVSwzNtFz96eLrGB3KhENnEVv7lkYdc898q2AF3G0-1715447846-1.0.1.1-yJ.D2R_c.jS8SErn4fAmIg6fShYSfc2h_m4vQrehVA5UpRV7rIsjnYCGTZLro7JW9nh1r0Hu853rOcvoy6hSrA; cf_clearance=QQWAR7NhgwYZjtKExO9v0IE2eHNkQweSMLRVugqL3mE-1715447848-1.0.1.1-JhfPisIW0GNy135ks_mIObi9.X.FmmorhRl_Fows5nrHEQuPBt2S7CY_lnB4vCipSp4Xq.QrKW5oscwSCMk_Hw; _gat_gtag_UA_1830249_145=1; _ga_D9TLP3EFER=GS1.1.1715442066.2.1.1715448098.22.0.0; _ga=GA1.1.530858074.1715103653"
}
save_path = os.path.join(download_dir, url.split("/")[-1])
@ -148,24 +148,31 @@ def main(driver: WebDriver, download_dir: str, proxies):
links = []
base_url = "https://www.fanbox.cc/@laserflip/posts"
page_url = base_url + "?page=%d"
post_url = base_url + "/%s"
start_page = 1
url = "https://monpetit17.fanbox.cc/posts?page=%d" % start_page
url = page_url % start_page
links += find_link(driver, url)
while has_next(driver):
start_page += 1
url = "https://monpetit17.fanbox.cc/posts?page=%d" % start_page
url = page_url % start_page
links += find_link(driver, url)
download_file_link(driver, links)
download_images(driver, links, download_dir, proxies)
links = []
for sub_dir in os.listdir(download_dir):
f = os.path.join(download_dir, sub_dir)
if os.path.isfile(f):
continue
if len(os.listdir(f)) == 0:
sub_page = "https://monpetit17.fanbox.cc/posts/%s" % sub_dir
sub_page = post_url % sub_dir
links.append(sub_page)
print("获取子页面链接", links)
download_file_link(driver, links)
download_images(driver, links, download_dir, proxies)