lamp/pixiv-popular-downloader
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Compare commits

base: lamp:a1c603edcfbedcc7bcd853de05be39bd45ce2969
Branches Tags
lamp:master
lamp:nodejs-puppeteer
lamp:mongo
..
compare: lamp:666628dfc739ecfb2f780471a58689de9d6b0306
Branches Tags
lamp:nodejs-puppeteer
lamp:master
lamp:mongo

No commits in common. "a1c603edcfbedcc7bcd853de05be39bd45ce2969" and "666628dfc739ecfb2f780471a58689de9d6b0306" have entirely different histories.
a1c603edcf ... 666628dfc7

1 changed files with 6 additions and 27 deletions
Show Stats Expand all files Collapse all files

33
pixiv-popular-downloader.py
View File

@ -38,7 +38,7 @@ def download_popular(tag, startpagenum = 1, numpages = 1):
# record this search session in the database
search_document_id = search_collection.insert_one({
"date": datetime.now(), # date started
"query": tag, # the tag being searched
"query": None, # the tag being searched
"current_page": startpagenum, # keep track of the page we're on
"current_illust": None, # keep track of which item is being downloaded
"search_data": [], # save each payload
@ -100,28 +100,6 @@ def download_popular(tag, startpagenum = 1, numpages = 1):
if (illust_ajax_data['error']):
print("error from ajax api:", illust_ajax_data['message'])
# save animated works
ugoira_data = None
if (illust_ajax_data['body']['illustType'] == 2):
illust_ugoira_url = illust_ajax_url + "/ugoira_meta"
print("get", illust_ugoira_url)
illust_ugoira_data = rqs.get(illust_ugoira_url, cookies={"PHPSESSID": os.environ["PHPSESSID"]}, headers={"host":"www.pixiv.net"}).json()
if (illust_ugoira_data['error']):
print("error from ajax ugoira api:", illust_ugoira_data['message'])
else:
original_ugoira_url = illust_ugoira_data['body']['originalSrc']
print("get", original_ugoira_url)
res = rqs.get(original_ugoira_url, headers={'referer':'https://www.pixiv.net'})
print("gridfs put", original_ugoira_url)
ugoira_data = {
"gridfs_id": gridfs.put(res.content, filename=original_ugoira_url.split('/').pop(), original_url=original_ugoira_url, ugoira=True),
"ugoira_meta": illust_ugoira_data
}
# illust_ajax_data does not have "page" data (additional image urls)
# download that
illust_pages_url = illust_ajax_url + "/pages"
@ -136,9 +114,8 @@ def download_popular(tag, startpagenum = 1, numpages = 1):
document = {
"_id": illust_id, # use the unique artwork id for document id so we can't have duplicates
"illust_ajax_data": illust_ajax_data, # save all the metadata for the artwork
"illust_pages_data": illust_pages_data, # save all the image urls of the data
"illist_pages_data": illust_pages_data, # save all the image urls of the data
"downloaded_images": {}, # map of image filenames to gridfs ids
"ugoira_data": ugoira_data, # animation data
"date_saved": datetime.now()
}
@ -152,13 +129,15 @@ def download_popular(tag, startpagenum = 1, numpages = 1):
res = rqs.get(original_image_url, headers={'referer':'https://www.pixiv.net'})
print("gridfs put", res.url)
gridfs_id = gridfs.put(res.content, filename=original_image_filename, original_url=original_image_url)
gridfs_id = gridfs.put(res.content)
document['downloaded_images'][original_image_filename] = gridfs_id
# add to db
illustration_collection.insert_one(document)
search_collection.update_one({"_id": search_document_id}, {"$push": {"results": illust_id}})
search_collection.update_one({"_id": search_document_id}, {"$push": {"results":{
"id": illust_id
}}})
search_collection.update_one({"_id": search_document_id}, {"$set":{"completed": True}})
print("end of loop")